The links below indicate the page to which the relevant discussion has been moved. They are removed every few days. Discussions that have not moved (such as announcements of new policy) can be removed completely, or summarised in this section. Bug reports and feature requests are replaced with a reminder that MediaZilla: should be used for these. If you want discussions to last more than a few days, start them elsewhere and just link to them here. Questions can be moved to the user talk page of the person who asked them without a link from this section. An example format for this section is
*Section header as it was before removal --> [[title of page the related discussion is on or has moved to]].
This page is currently inactive and is retained for historical reference. Either the page is no longer relevant or consensus on its purpose has become unclear. To revive discussion, seek broader input via a forum such as the village pump.
I understand this is sort of a perennial proposal, but hear me out for this one:
Instead of censoring wikipedia, which goes against WP:NOTCENSORED, we should have a separate, kid-friendly version of wikipedia called "Wikipedia Kids"(bit like how mobile wikipedia is slightly different). This does not go against WP:NOTCENSORED, and protects children at the same time.
Many children use wikipedia for a variety of purposes(hell, I'm still a teenager) and i would rather not have people seeing some not so kid friendly stuff here.
Here is how i think it should work:
Normal version remains uncensored and has no changes
The Kids version is practically the normal version, but:
Sexually explicit articles cannot be accessed and are not available on the kids version(to what extent it should not be available can be debated, such as should we make them unavailable completely or just have a smaller, safe, educational version of the article that focuses on stuff the kids actually need to cover in say, biology).
Gory or violent pictures are unavailable. The pages are still available for reading, e.g. we still keep the nanjing massacre article up however the photos will be removed. This ensures we aren't doing stuff like Holocaust or Nanjing massacre denial while still protecting kids.
Overall this is similar in function to WP:CENSORMAIN
Would like to hear your opinion on this. Additionally, to what extent sexually explicit/violent articles is censored, and what counts as "sexually explicit" or "violent" can be debated. Thehistorianisaac (talk) 15:32, 10 April 2025 (UTC)[reply]
maybe it could theoretically work on paper as an option that can be toggled (in which case i'd be against having it on by default), but it absolutely wouldn't work out as its own site (even if it was mostly a mirror) due to the sheer size of the wp-en
even then, i think it'd be way too hard to program, harder to enforce, and even harder to maintain, since how would those filters even work outside of trudging through the entirety of the wmf to filter things on what's effectively a case by case basis?
lastly, it also depends on conflicting definitions of "for kids", because you know one of those ankle-biters will have to study up on world war 2 at some point, or sex, or that one time the british colonized a place, or that one time the americans killed people and took over their land manifested their destiny, or literally anything even tangentially related to any religion that isn't satirical (nyarlathotep help them if they're in a jw or mormon environment), and keeping them out of it would only really cause easily avoidable headaches consarn(prison phone)(crime record)17:18, 10 April 2025 (UTC)[reply]
I agree on kids the "for kids" definition. That is why I would suggest for the kids version, sex-related articles with no connections to sex ed be unavailable, while sex-related articles related to sex ed only show diagrams and be reduced. As for violence, I would not suggest censoring anything other than some of the photos, or possibly even limiting it to a "Show photo-Disclaimer: may contain violence". Thehistorianisaac (talk) 17:33, 10 April 2025 (UTC)[reply]
Why pick on sexually explicit articles? I don't mind my children or grandchildren (the latter of which are aged five, three, and a month) accessing details about sex, but would prefer that they didn't access some other material, such as graphic violence or material about suicide. I'm sure that there are many different views from parents and grandparents. Phil Bridger (talk) 18:03, 10 April 2025 (UTC)[reply]
let's say that happens. how, then, do you know what will be taught in sex ed? how would you attempt to reduce what is shown in order to make it less explicit without touching the text? how wo- actually, having to choose to see the pictures is nice, no complaints there consarn(prison phone)(crime record)18:45, 10 April 2025 (UTC)[reply]
Did you do some thinking on how this can be implemented and how much workforce will be required and how much bitter squabbling will follow on whether a picture of a buttocks is permitted and whether sucking the dick properly is part of sex education. (You may think the latter was a joke, but I remember seeing on a Disney Channel an episode where two low-teen girls pressed a boy to explain them how to suck the dick properly.) --Altenmann>talk18:04, 10 April 2025 (UTC)[reply]
i say this as a former child from a country best known for playstation 2 piracy (which is to say i knew about the hot coffee mod when i was 8): nearly anything we could do would at best do absolutely nothing to protect children lmao. if anything, it'd just fan the flames of their curiosity, because they wanna see the buttocks!! hell, even the idea of it working by censorship comes off more as pandering to overly sensitive parents than attempting to "protect" the leeches on their legs. even then, protect from what? from knowing what "fuck" means? from knowing what a peepee (that could potentially be the one in their own lower torso) looks like and does? from knowing about that angry mustache model who hated jews for existing?
for better or worse, children will find their way into whatever they want, regardless of whether or not they can handle it (though they usually can), and drawing an arbitrary line would only make them want to cross it more than their tiny, evil brains already instinctively urge them to consarn(prison phone)(crime record)18:39, 10 April 2025 (UTC)[reply]
This is a great idea for a third-party service, as they can select for inclusion whatever materials they feel meets their own sense of restriction. The Wikipedia license gives them the freedom to do so, and there could even be various versions with different perspectives as to what is appropriate.
It makes a horrible project for Wikipedia itself to do, however, because then we have to establish an Official Standard for what is improper, and that will both lead to endless bickering and complaints from those who want to provide the censored version that we are not censoring the things that they wish to have censored. You can see how we would face massive complaints if we decided, say, that material on drag entertainment was suitable for kids, or if we said that it wasn't. The group control that Wikipedia projects have and our spot at the most visible source of data would just make this too fraught. -- Nat Gertler (talk) 18:10, 10 April 2025 (UTC)[reply]
"For kids" versions of reference materials are usually written for a specific audience based on age/intellectual ability. To meet the expectations set up by the name, the articles should be specifically organized and written at a less complex level, which can mean different ways of breaking down topic areas as well as a different language level. simple:Simple English Wikipedia currently exists to fill that niche, and would be a better starting point for a kids version. As you noted, though, there are a lot of objections from the community to embedding content filtering as a core function that requires altering the underlying base articles. So at present, any filtering would need to be entirely add-on and optional, and using categorization being stored elsewhere, such as on Wikidata. isaacl (talk) 18:14, 10 April 2025 (UTC)[reply]
Simple English Language Wikipedia is decidedly not aimed at children in the way contemplated here. It includes sexual topics, for example, and even has entries for Fuck and Fucking (the latter a disambiguation page), and graphically illustrated articles at Human penis and Vagina. BD2412T00:11, 29 April 2025 (UTC)[reply]
I could see something like this becoming its own project, similar to simple English wikipedia. I'd even contribute to it, I enjoy the mental challenge of simplifying a difficult concept into something a child could understand mgjertson (talk) (contribs) 19:26, 10 April 2025 (UTC)[reply]
Since this discussion seems to be moving away from child-protective censorship and towards child-centred language simplification, I'll not the existence of b:Wikijunior, a worthy project. Cremastratalk19:53, 10 April 2025 (UTC)[reply]
This is just censorship, with all the typical problems that come with the idea (the non-neutrality of determining what is and is not appropriate). ꧁Zanahary꧂05:06, 20 April 2025 (UTC)[reply]
Points 1) and 2) skate over the perennial practical issues that confound such initiatives (putting aside philosophical ones), which are: who decides what is appropriate, and who tracks what is (in)appropriate. Saying these "can be debated" is putting the cart before the horse. CMD (talk) 07:39, 20 April 2025 (UTC)[reply]
We don't need to do anything to enable that, any school or institution controlling their own internet systems can selectively block urls of their choice. CMD (talk) 00:40, 22 April 2025 (UTC)[reply]
I don't hate this idea. A separate version of Wikipedia along these lines could serve as an entry point for potential Wikipedians who would mature to engage in other aspects of the project, and could also serve as a place to which to point those who fret about illustrations of mature topics on the main Wikipedia. BD2412T00:20, 22 April 2025 (UTC)[reply]
I'm not really sure we should do this under Wikimedia (to start, what's considered generally appropriate for children in one culture may not be in another, and is our hypothetical "kid" 5 or 15?), but if anyone wants to do something like that, Wikipedia is CC-BY-SA for a reason. So if you think "The Children's Encyclopedia" or whatever you'd like to call it is a good idea, go do that, you don't need anyone's permission. (Just remember you can't call it Wikipedia or anything close to that due to it being trademarked.)SeraphimbladeTalk to me00:32, 22 April 2025 (UTC)[reply]
What if we started something from the opposite direction, beginning with building child-directed articles on things that virtually everyone would agree should be in such a resource (e.g., what is a Lion, what is an Alphabet, what is a Guitar, what is Multiplication, what is Pluto), with near-unanimity required to add or post a topic or image? BD2412T18:16, 22 April 2025 (UTC)[reply]
that'd still be a logistical nightmare from the start, because even the most banal topics could be a little much for some children, and as seraphimblade mentioned, the target audience could be 5 or 15, and we can't really target both, since their tastes and needs are guaranteed to clash. plus, wikipedia is right here, so anything beyond that borders on being a choosing beggar consarn(prison phone)(crime record)18:54, 22 April 2025 (UTC)[reply]
@Chipmunkdavis: I'm not suggesting that we should copy-and-paste our current content, just that these are subjects that would be reasonably uncontroversial for inclusion as topics of coverage for a kid's encyclopedia. BD2412T18:27, 25 April 2025 (UTC)[reply]
I have obtained a Herit*ge Found*tion document titled Our Real Strategy, which envisages surreptitiously encouraging the creation of Wi/kids, placing obnoxious material in it alongside contentious material that woke hostiles will defend, and the material's eventual discovery by the HF's grass-roots division. They seem confident of destroying all Wikipedia in the ensuing storm. NebY (talk) 18:00, 22 April 2025 (UTC)[reply]
Anyone is free to WP:FORK Wikipedia and censor it however they want. I for one won't be a part of that project, but if others want to be, have at it. Headbomb {t · c · p · b}18:25, 22 April 2025 (UTC)[reply]
I like the idea of how Basque Wikipedia did this: having a second tab next to article. I'm not keen on making any type of censored version for kids, maybe except extreme violence, but see a use for explaining things in much easier terms. For medical content, the tone would be more akin to the NHS than to academic literature. We do lose a large audience on Wikipedia, which is a shame. In terms of culture, I hope that more people learn to write for an appropriately broad audience, and that our normal articles become easier to digest too. But perhaps it'll be used for the opposite ("if you don't understand the default article, go to the kids one"). —Femke 🐦 (talk) 07:17, 23 April 2025 (UTC)[reply]
a use for explaining things in much easier terms this is why the Simple English Wikipedia exists. We should do a much better job of making its existence known - currently it's only linked in the other languages list, where most people wont think to look for it and because this is arranged alphabetically "Simple English" can be several screens down the list on articles that exist in many languages (for me it's right at the bottom of the second page down when starting from the top of the languages section at Aspirin for example). Thryduulf (talk) 11:45, 23 April 2025 (UTC)[reply]
The OP started this discussion to be about having a censored version of Wikipedia, but many people have taken it in the direction of having a version which has language that can be understood by kids, whether targeted at 5-year-olds or 15-year-olds or something between, and commenters have said that that role is fulfilled by the Simple English Wikipedia. These are two very different topics, but any new WMF project should be discussed at Meta, not here. I think the only thing that belongs on this project is Femke's proposal of a separate tab. Maybe such a tab could point to the Simple English version of the article, if it exists. That would also address Thryduulf's point about making the Simple English Wikipedia more visible. Phil Bridger (talk) 12:35, 23 April 2025 (UTC)[reply]
Personally, I would like an opt-in ability to hide/blur sexually explicit and/or gory images. Sometimes I browse Wikipedia in a public place and don't want people around me to think I'm looking at pornography.
@Chess What are the objective definition of "sexually explicit" and "gory" that you are using? It's been a while since I looked at the state of AI image classifiers, but last time I did the reliability was very poor (e.g. Facebook believes this image of a white daisy contains "violent or graphic content" while not recognising an image containing penetrative sex as pornographic (possibly because both people in the image were essentially fully clothed). I don't know if it is still the case, but distinguishing images of roast chicken from images of naked people was also very tricky for classifiers. Thryduulf (talk) 22:21, 28 April 2025 (UTC)[reply]
@Thryduulf: I'm fine with the false positives. Blurring anything with a bunch of flesh tones isn't perfect but it means I don't have to worry about opening something NSFW in class or at work. Chess (talk) (please mention me on reply)22:24, 28 April 2025 (UTC)[reply]
Given the wide range of human flesh tones, that is a lot of images getting unnecessarily blurred. Flesh is also far from the only thing that is not safe for some workplaces (but also perfectly safe for others) Thryduulf (talk) 22:26, 28 April 2025 (UTC)[reply]
consider that if we make it a policy, or better yet, clarify it in some legal document somewhere, we can then safely refer to any given parent's reaction as an ill skissue. a skiss illue. a slick issun. a silk insure. a- you get the idea, a skill issue on their part, failing to protect their totally not desensitized child from seeing a girl nipple (someone please cover that with a family-friendly male nipple!). why is this important? because it would be really funny consarn(prison phone)(crime record)19:31, 30 April 2025 (UTC)[reply]
I don't expect parents to be responsible for this if they believe all of Wikipedia's articles is for all ages with "no explicit content" Gonna eatpizza (talk) 19:18, 5 May 2025 (UTC)[reply]
Well if for some reason they got that idea into their heads it's their fault. I wouldn't expect a modern paper encyclopedia to be censored, and there's no reason for anyone to believe that an online one would be either. Cremastratalk19:32, 5 May 2025 (UTC)[reply]
Many years separate me from kidhood, but I still remember one thing pretty clearly: it was totally worth hunting down the stepladder so I could reach those books that were way up there on the top shelf. Sometimes I wonder if they stimulated a germ of an interest in some of the presumptively taboo topics I began to contribute to decades later at Wikipedia. Should we label the tantalizing allure of the top shelf to kids the "Baby Streisand effect"? Mathglot (talk) 20:47, 2 May 2025 (UTC)[reply]
English wikipedia is WP:NOTCENSORED, but in my view there's also nothing on English wikipedia that's inappropriate for children? Some parents or guardians may disagree, and may restrict their own children's access to wikipedia, but many authoritarian governments also disagree, and restrict their citizen's access to wikipedia, and we don't censor wikipedia on their behalf either! This is ultimately a fake problem, there is no solution needed. Psychastes (talk) 22:21, 24 May 2025 (UTC)[reply]
How about as a compromise wikipedia does not censor or remove explicit articles outright, but rather limits them from appearing in things like top read or featured articles, thus preventing anyone who is not intentionally seeking them out(like children) from viewing them? 74.65.238.2 (talk) 16:35, 29 May 2025 (UTC)[reply]
Censoring top read, featured articles and similar comes with the exact same set of challenges that censoring the project as a whole does about how you determine which articles should be censored and which ones are fine. Thryduulf (talk) 17:51, 29 May 2025 (UTC)[reply]
Put the classifications to a vote amongst the volunteers or even users as a whole. Not perfect but better than doing nothing. 74.65.238.2 (talk) 23:18, 29 May 2025 (UTC)[reply]
Make a site wide poll for like a week that says “Should X thing be censored on top read”. You take nominations from volunteers and vote amongst each other on whether they should be put to general vote. 74.65.238.2 (talk) 01:41, 30 May 2025 (UTC)[reply]
So that's an average of, extremely conservatively, 1.1 votes per article taking a minimum of 1 week each. If there are 1000 concurrent votes and only 1% of articles have the potential to be top-read and/or featured that's still over 10 years to conclude all the votes. And that's assuming that we get no more articles in the meanwhile and none of the existing articles need voting on again (e.g because their scope changed or standards changed). Thryduulf (talk) 02:01, 30 May 2025 (UTC)[reply]
You don’t have to do votes for every single article, there are some things that can pretty logically be wrapped into one vote like “should all photos of nude humans be hidden” “should all photos of corpses be hidden” etc. 74.65.238.2 (talk) 20:58, 30 May 2025 (UTC)[reply]
That’s how literally every election ever works. People voted against Hillary cause she was a woman, doesn’t mean their vote should be invalid. 74.65.238.2 (talk) 23:43, 30 May 2025 (UTC)[reply]
There’s just simply no way to know with that kinda stuff, you just have to hope that the people voting for shallow reasons aren’t a big enough factor to swing results. 74.65.238.2 (talk) 23:51, 30 May 2025 (UTC)[reply]
i wouldn't rely on a method even you admit would be a crapshoot for what is ultimately a non-issue. children, the people those changes would allegedly "protect", are easily the group most likely to want to see that stuff in the first place, and preventing people from finding things is the literal exact opposite of what wikipedia is supposed to do
but even ignoring this, a voting system this widespread would rely on...
a lot of people voting
strict enough criteria
criteria timeless enough to not require constant change or adaptation
voters knowing about the criteria
voters respecting the criteria
voters not deliberately manipulating the votes (via canvassing, logged out editing, and whatever else)
programming a poll system
the poll system in question not being out of the way of casual readers and/or editors
polls that would be all but guaranteed to eventually trickle down into individual articles anyway
which is, in my opinion, way too much effort for something that, at its absolute best, would be unreliable, unwieldy, and... uh... unlikely to not cause headaches when faulty votes inevitably turn up? i don't have a good third adjective, sorry consarn(grave)(obituary)00:03, 31 May 2025 (UTC)[reply]
The idea that something not being able to be implemented perfectly somehow renders it completely worthless is a common logical flaw that comes up often in policy debate. Take something like gun control for example, there is no country on earth where guns can’t be purchased illegally, and yet there has been a consistent theme that nations with strict controls have substantially lower gun violence rates than those without. 74.65.238.2 (talk) 05:03, 31 May 2025 (UTC)[reply]
Right, so we have a ranked-choice ballot that transfers into a pseudo-second ballot if the voter's third preference is not leading; otherwise a Borda count is used, but if one option under that system gains more than (number of voters x pi) points we transfer to an MMP system and all bets are off. (Except the bets placed under the ranked ballot system; they roll over into the two-option preferred vote. Obviously.) Cremastra (u — c) 03:34, 31 May 2025 (UTC)[reply]
Has anybody identified an actual problem that's been caused by explicit articles being on these lists? Because this does sound like a solution in search of a problem -- Nat Gertler (talk) 01:52, 30 May 2025 (UTC)[reply]
Yes children or adults suffering from trauma being unintentionally exposed to material that they don’t have the capability to emotionally comprehend. 74.65.238.2 (talk) 04:59, 31 May 2025 (UTC)[reply]
Can you point to evidence of this happening to some significant degree, making it an actual problem? Or is this just theoretical people suffering theoretical trauma after theoretically being directed to an article from top read or featured article lists? -- Nat Gertler (talk) 05:25, 31 May 2025 (UTC)[reply]
And before you say “This is TV not Wikipedia!” such findings can reasonably be linked to similar content types on here as well. 74.65.238.2 (talk) 07:25, 31 May 2025 (UTC)[reply]
Okay, so something that makes literally zero mention of Wikipedia, much less the specific lists of Wikipedia that you wish to censor, in a document that is not supposed to be a guide for content. (And if you think the content types are matching, when they say "Overall, media are much more likely to portray casual sex than provide education or portrayal of sexually responsible behaviors", can you point to pages that we are linking to on those lists that are not providing education?) So we have zero examples of anyone being damaged by any articles that appear on the lists you wish to censors. In fact, so far we have zero specific examples of articles that have appeared on those lists that you would have removed. This is an entirely theoretical concern. -- Nat Gertler (talk) 15:59, 31 May 2025 (UTC)[reply]
The specific article that prompted my concern was of a “magic cross piercing” which prominently featured a penis in its thumbnail and was near the top of top read. Additionally, the source never states that things cannot be both educational and inappropriate(like with wikipedia) it merely states that tv media was more likely to be entirely devoid of educational value, further extenuating it’s lack of necessity. 74.65.238.2 (talk) 17:33, 31 May 2025 (UTC)[reply]
Further more, just because something has not been recorded in formal study does not mean it has not caused harm or will not cause harm in the future, as evident by the fact that you routinely have individuals coming in here to make similar suggestions about moderation. You do not have to wait until there is overwhelming evidence of damage to take action in prevention of it. 74.65.238.2 (talk) 17:41, 31 May 2025 (UTC)[reply]
Just because an actual problem has not been identified does suggest that we should not be routing significant editor effort into inherently imperfect efforts to address the situation. The fact that people have made similar request is not actually evidence that any harm has been or will be caused. There are plenty of supposedharms that people have rallied around that have had no basis in reality. -- Nat Gertler (talk) 21:39, 31 May 2025 (UTC)[reply]
And were you harmed by viewing that image of a penis? Because if so, then at least we'd have anecdote, although not data. Trying to read that not-a-study you presented which had the central point of "kids are doing too much media" and taking it to mean we should be hiding encyclopedia articles seems akin to taking a document saying that kids eat too much and interpreting it to mean we need to hide the celery. -- Nat Gertler (talk) 21:28, 31 May 2025 (UTC)[reply]
If celery had verifiable harmful effects on kids then that would be an apt comparison, and would warrant such a response. I’m not saying it’s a colossal issue, but it’s also one that would entail an extremely basic level of effort to counteract, an effort that even I would be willing to put forth if I had the perception that it wouldn’t be fervently opposed and immediately reversed. 74.65.238.2 (talk) 22:40, 31 May 2025 (UTC)[reply]
If celery had verifiable harmful effects on kids what people are asking you for is evidence that viewing these articles on lists has "verifiable harmful effects on kids". So far you haven't provided any. Thryduulf (talk) 22:43, 31 May 2025 (UTC)[reply]
Do you have any studies that it doesn’t cause harm? What is your basis for a lack of moderation? We are both basing our views on logic and extensions of studies in other areas, so trying to attack me from this angle doesn’t really make sense. There isn’t any evidence to verify if jumping off the Brooklyn Bridge when the city’s under Chinese occupation will result in bodily harm either so in that event should just let people do some belly flops into the East River? 74.65.238.2 (talk) 02:34, 1 June 2025 (UTC)[reply]
It’s semantics but I understand how the word “verifiable” could be perceived wrong in that context. No there is no large scale academic findings that show it, but my conclusions about the material can be presumed upon other factors. 74.65.238.2 (talk) 02:43, 1 June 2025 (UTC)[reply]
That you choose to presume something despite lack of evidence should not be taking as a basis for assuming that others would or should. That the idea that we don't have specific studies that these articles don't cause harm would seem like setting up a base for removing all articles, as there have not been studies on them either.... and in fact, that would be as much in line with the larger claim of that PDF, that kids are facing too much content, as the application of the "Sex" section is to the things you wish to control. -- Nat Gertler (talk) 05:04, 1 June 2025 (UTC)[reply]
There isn’t any evidence to verify if jumping off the Brooklyn Bridge when the city’s under Chinese occupation will result in bodily harm either There are many, many studies that verify that jumping from bridges the height of the Brooklyn Bridge into water will result in bodily harm. AFAIK Brooklyn has never been under Chinese occupation, but even if it were it would be completely irrelevant.
No there is no large scale academic findings that show it, but my conclusions about the material can be presumed upon other factors What factors? Thryduulf (talk) 02:45, 1 June 2025 (UTC)[reply]
It amazes me sometimes how some people forget what it is like being a child. I'm 67 now, but I remember clearly that it's much more likely that a child would seek out such content than an adult. And who defines what is "explicit"? You? Phil Bridger (talk) 18:10, 29 May 2025 (UTC)[reply]
81 here, and yeah, I was adept at finding the tidbits in encyclopedias and other books that adults didn't realize I was reading, as well as studying the X-rated playing cards and Cuban post cards that other boys snuck out of their houses for private show-and-tell. And what passed for sexual knowledge among pre-adolescent boys at the time may have been as harmful as anything they can now find on the Internet. Donald Albury19:12, 29 May 2025 (UTC)[reply]
This keeps coming up in my watchlist so I'll comment. This idea seems like it would be a massive waste of time and energy. If someone wants to make a mirror site that hosts filtered versions of Wikipedia that meet their standard of ideological purity, then I think they are already free to do so. I can't imagine the nightmare of trying to define what counts as "kid-friendly" on the talk pages, and vandalism would be a serious concern. We struggle to get enough people patrolling the English Wikipedia for vandalism as it is, there would likely be far fewer people interested in watching a kids version. Furthermore, the second you market something as "kid-friendly" you open yourself up to serious controversy when the inevitable bad thing leaks through, just look at the section "Filtering issues" on the "YouTube Kids" page. As it stands, if parents are letting their kids have access to the Internet, Wikipedia in its current form is among the least of the websites I'd be concerned about.
Several problems with this; here are two of them: 1. Everyone has their own version/definition/opinion of what kids shouldn't see. And so it gets classified based on politics. 2. So if the uncensored Wikipedia is readily available, what's to stop kids from looking at it? And they will. North8000 (talk) 19:43, 5 May 2025 (UTC)[reply]
RE: "protects children at the same time", As mentioned in several places above, protect them from what? who decides? And as also mentioned above several times, if they already have access to Wikipedia, a separate version is not going to protect them, if a child has access to click on whatever they want, nothing we do here is going to "Protect the children". Jeepday (talk) 12:05, 23 May 2025 (UTC)[reply]
I would imagine that there are applications which allow parents to set parameters of what websites their children can visit (and the Wikipedia is probably outside of those parameters). BD2412T23:27, 24 May 2025 (UTC)[reply]
There totally are, and the reasons I would see the Wikipedia blocked is if its a whitelist system (which would be manually set by the parent) or it uses keyword parameters. Gonna eatpizza (talk) 16:25, 27 May 2025 (UTC)[reply]
Words cannot express how strongly I oppose the first half of this, qedk, at least as applies to gaming. Are you actually, with a straight face, proposing that we amend the procedure meant to hold admins accountable for violating policies, in order to exempt violations of a policy we routinely block non-admins for violating? I'd strongly encourage any other admins to consider what supporting that would convey about whether they support holding admins to the same standard as non-admins. Forbidding petitions based only on inactivity without a gaming element... meh. Let's worry about that if it ever happens. Upping inactivity rules, sure. Put me down in support of anything more strict than the status quo. But it absolutely should not be paired with amnesty for admins who violate a specific policy. -- Tamzin[cetacean needed] (they|xe|🤷) 12:59, 25 May 2025 (UTC)[reply]
I am, with a straight face, saying that. The community should align expectations from admins and make it sufficiently clear such that the question if someone is gaming does not need to be a problem that the community needs to solve. It's a waste of the community's time and energy that is better spent elsewhere. I also do not appreciate the comparison to the other actually disruptive applications of gaming the system (a guideline) - that is a strawman argument that is not at all pertinent to the problem we're seeking to solve. --qedk (t愛c)13:13, 25 May 2025 (UTC)[reply]
If your proposal is based on the idea that admins making de minimis edits to evade the inactivity rules for years, as they drift farther and farther out of touch with community norms, is not disruptive, then I think that's a better rebbutal to the proposal than anything I can say. -- Tamzin[cetacean needed] (they|xe|🤷) 13:45, 25 May 2025 (UTC)[reply]
The incorrect assumption being made here is that just because they're inactive (or gaming the system, which is not ethical to be clear), they're unaware of community norms. No one is perfect, and like every other editor, it's also unfair to expect admins to be subject to assumptions of gaming and non-awareness of community norms. Similarly, inactivity itself can be due to a multitude of reasons, we don't care about why they are away but what we should care about is - what level of inactivity is unacceptable from a currently standing admin - such that, we're sure that they are not aware of present-day community norms? --qedk (t愛c)17:19, 25 May 2025 (UTC)[reply]
I would argue that an admin that does nothing, by definition, can't be disrupting anything. If that admin then does something bad/wrong, whether due to being out of touch with the rules or otherwise, then that would be disruptive, yes. Or if the admin's account got hacked, that would be disruptive, too. Or people bringing up conversation about that admin (via recall or otherwise), then that person is causing a disruption about the admin, but the admin didn't cause the disruption. A number of disruptive things can stem from the admin's inactivity, sure, but the inactivity itself cannot be a disruption. Useight (talk) 16:46, 28 May 2025 (UTC)[reply]
Recall is, almost per definition, a process that says "they aren't breaking the rules, we just don't have enough trust in them to be sure they're not going to break them in the future." Therefore, there's no need to exclude gaming activity. If 20 people think they're gaming, they can either resign or re-RFA. If 20 people don't think they're just gaming, they're good. (And I'm speaking as someone who has gone through an attempted recall.) And if someone files against everyone who's just cleared the requirements, that's disruptive and sanctionable. --SarekOfVulcan (talk)17:52, 28 May 2025 (UTC)[reply]
Fiddling with various thresholds to trying to have rules that can't be gamed doesn't seem worthwhile to me; it reminds me of the adage about how trying to make something foolproof just leads to the universe inventing a bigger fool. If you make the requirements stricter, that just increases the incentive for people to game it.As to the counterproposal of having the rules say "no gaming", meh, discussion will still be needed to determine whether there's actually gaming or not. Since we already have Wikipedia:Administrator recall, why would it be better to hold discussions over whether an admin is gaming or not at WP:BN instead of there? Do we trust 'crats to do a better job than whatever mob shows up at the recall petition? If so, then perhaps the recall process needs to be revisited as a whole instead of trying to make carve-outs. Anomie⚔13:22, 25 May 2025 (UTC)[reply]
There are problems with administrator recall, as I've expressed in multiple discussions about it in various fora, but this is not the way to solve them.
What the admin activity requirements should be is a separate question. I don't think there is a way of avoiding thresholds completely but they are evidently not quite aligned with what the community desires, which is for admins to remain engaged with the project and to keep in touch with evolving policies and norms. If we want to continue measuring this by edit count (which is easy to measure but imperfectly reliable) then something closer to the following might work:
Admins are expected to demonstrate that they remain in touch with the community. Ideally admins should be making multiple non-trivial edits or logged actions most months, but must average at least 10 edits or logged actions every six months over a two year period. Administrators who consistently fall below this activity level or who attempt to game the requirements may be subject to recall no sooner than three months after being alerted.
Administrators will be procedurally desysopped if they fail to make at least one edit or logged action in any 12 month period or 100 edits in any five-year period.
Administrators who appear to be gaming activity requirements and/or who appear to have not kept up to date with policies or community norms may be subject to recall no sooner than three months after being alerted (this does not preclude recall petitions being initiated over other matters, including egregiously bad departures from contemporary community norms).
On a personal level, if I correctly understand your proposal that admins...must average 10 edits or logged actions every six months over a two year period, and it had been in force in the past, I would have been forced out on more than one occasion, and yet I do not feel that I have ever lost touch with policies and community norms. Now, I am not a particularly active admin, although, to my continuing surprise, the number of my logged actions is in the middle range of all admins, and losing the bit would merely free my time up a bit, I cannot support such a strict rule. Donald Albury16:10, 25 May 2025 (UTC)[reply]
As I stated on the admin recall talk page, I do think the community should have a discussion on the expectations on admin activity. I feel the community wants its admins to have some ongoing connection with the community, and uses recent edits as a metric to determine this. It's imperfect, but I think it's a reasonable approach, with corner cases able to be handled separately. I also made a suggestion in that same discussion that one possible approach is to shift the emphasis to no-fault removal of administrative privileges to reduce the scope for security vulnerabilities, with the current restoration process available for admins to regain their privileges. This would help smooth the way for a much higher activity threshold, which can better satisfy community expectations. isaacl (talk) 16:07, 25 May 2025 (UTC)[reply]
I think we need to step back and figure out what we're trying to accomplish here, because the best solution depends more on the root goal than the intermediate one of "desysop inactive admins". Some possibilities:
Are we trying to improve security, by minimizing the chances that a compromise of a long-inactive administrator account will go unnoticed by its owner?
Then the initial system of zero edits in a year was the right answer all along. If that proved insufficient - say, there were multiple compromises of minimally-active admins that were used to slant content, as opposed to the usual "Hey, I've just deleted the main page and blocked Jimbo, obviously I need to be blocked" - then the proper refinement is to shorten the time period, not to introduce a longer-term one like our current 100 edits/5-year rule.
Are we trying to ensure each admin is still using their bit to benefit the encyclopedia?
Then you measure inactivity by the number of logged actions in mainspace only, with the understanding that admins who are close to the threshold will be flagged for manual review, and clearly-frivolous actions like creating a page just so you can immediately speedy it as G7 don't qualify.
Do we want to show that every admin maintains the community's confidence?
Then the most direct way is to periodically run every admin through the recall process, or skip it and go directly to re-RFAs. {{Deityname}} have mercy on the souls of the first few dozen.
Is it most important that whatever inactivity rule we have is hard to game?
Then solely basing it on a hard limit of some sort is a bad idea, because any hard limit, no matter how absurd, can be gamed. Grade on a curve on instead: three or four times a year, find the 1% or 5% or 10% or whatever admins who've been the least active by whatever measure - edit count or logged actions or support percentage in reRFAs or whatever - and desysop those. Maybe combine with a moderately-absurd hard limit on the order of 100 edits per month to protect us from the "best" case where even that would fall into the lowest 1%.
I am reminded of the old Microsoft rule that the bottom 5% (or whatever it was) of productive programmers were routinely sacked to go work for Boeing.
Having said that, it's an egregious rule (like so much early Microsoft thinking - we can argue 'early'), especially for a volunteer project. And I do note that becoming an admin these days is actually quite hard - the RfA process these days is pretty rigorous. It wasn't always so - WP has changed a lot.
So maybe you have a review process, say a 5-year review. No hard bright lines, just consensus that x is still a productive admin, broadly construed. It could even be a peer review - admins agreeing on admins rather than making it open to all editors. As a non-admin, I'd support that, TBH... Best Alexandermcnabb (talk) 17:06, 25 May 2025 (UTC)[reply]
(edit conflict) The problem with a temporary tenure before was that RfA was atrocious and it would be unfair to subject editors to it more than once. I think with elections, that alleviates the issue, if we make elections more frequent, I do not think that's a bad idea. This would also make adminship not a big deal as it was originally intended. --qedk (t愛c)17:25, 25 May 2025 (UTC)[reply]
I like Alexander's idea of peer review.
(Microsoft was not the most aggressive at weeding out low performers; other companies did larger percentages. At one company, if you were the bottom 10% of the chosen metrics two quarters in a row for your own team, then you were fired – even if the reason for that is that the rest of your team was the top performers in the whole company, and you were above average compared to the whole company, or even if the low performance was due to temporary reasons.) WhatamIdoing (talk) 18:19, 30 May 2025 (UTC)[reply]
Re your 3rd point, Cryptic, in a perfect world I'd like to see proper admin reconfirmations here. Nothing heavyweight, something like a straw poll where the two options are "reconfirm" and "send to re-RfA", max 50 words' rationale per user, 50% to pass. But I don't expect that to happen anytime soon, so, re your 4th point, I think the easiest solution is to create a discretionary zone, just like we have at RfA and with resysop activity. This could address both inactivity-gaming and the loophole that allowed Gimmetrow to be resysopped in the first place. Something like, Bureaucrats may at their discretion deny resysop if they feel the requester would not have met the WP:RESYSOP criteria but for actions taken solely for de minimis compliance with those criteria. Similarly, bureaucrats may at their discretion include an administrator in the monthly inactivity desysop list if they feel that the administrator would meet the criteria for an inactivity desysop but for such actions. The resysop procedures for such an ex-administrator are the same as for any other administrator desysopped for inactivity. In an eventuality where bureaucrats have such power, I would be okay with inactivity-gaming being exempt from RECALL, although I wouldn't support the idea either. -- Tamzin[cetacean needed] (they|xe|🤷) 17:23, 25 May 2025 (UTC)[reply]
A few thoughts:
I don't want a minority who want a stricter admin activity threshold than community consensus supports to be able to do an end-run around consensus by recalling admins who are likely too disengaged to desire running a new RRFA promptly. I don't think the two most recent recalls are a problem, but I do want caution.
I don't think our current admin activity policy is significantly misaligned, but I do wish that crats used discretion more aggressively for any account just skirting the exact fringes of our brightline policy. A good analogy is edit warring versus the 3 revert rule - our inactivity policy is the analogue of the 3RR as a brightline where if you cross it you are almost certainly edit warring/inactive, and we can take action in most cases accordingly. However, you absolutely can edit war while staying within the letter of the 3RR, and you absolutely can be more inactive than the community is willing to tolerate while staying inside the letter of the inactivity policy.
I dislike the idea of carving out reasons why an admin explicitly may not be recalled, which feels inelegant.
Perhaps a good solution for less active admins would be to apply the "grace thresholds" to the next RRFA/admin election they run in, even if it falls outside the 1 month window. The tools would still be removed after a month. That way, an admin recalled in this way would be able to return to activity, make a number of edits to show that they are in touch with community norms, and then make a compelling case for getting the bit back on their schedule.
I agree with Tazerdadog: I don't want a minority who want a stricter admin activity threshold than community consensus supports to be able to do an end-run around consensus. It's not fair for the community to say, out of one side of our mouth, "Here's the minimum acceptable level of activity" and then out of the other side of our mouth, to say "By the way, 'only' meeting the minimum is unacceptable". That's gaming the recall system, to allege that someone is gaming the activity standards.
If we want to have higher activity standards, then we need to have a higher activity standard. It's not okay to have a consensus that one edit per year is enough, and then have two dozen individuals say "That's nice, but we are enforcing a higher standard, and we don't have to have a consensus for our higher standard". WhatamIdoing (talk) 18:23, 30 May 2025 (UTC)[reply]
I disagree with the premise that the current activity requirements are out of sync with community expectations. The cases that have made their way to successful recalls were based on pretty clear gaming and unmet promises to return to activity. Enforcement of inactivity requirements is better handled through bureaucrats. Recall is a poor fit for this type of policy enforcement because it's a heavyweight community process and it adds unnecessary delays to resolve what should be a narrow and factual question. I think it's also extremely unlikely for any re-RFA to be successful in cases of inactivity so it's just a bad fit in every respect.
I think Tamzin's proposal for a discretionary zone would also enhance the bureaucrats' ability to handle these exceptional cases quickly and fairly, specifically by allowing bureaucrats to desysop in cases where activity barely meets the technical threshold but clearly falls short in substance. A discretionary zone also allows for bureaucrats to consider evidence of activity that may not be visible in the logs.
Finally, it might help to add a requirement that administrators being resysopped after a period of low activity (e.g., less than 1,000 edits or actions in the previous two years) must meet a somewhat higher threshold to retain their tools (perhaps 1,000 edits and 100 actions in the following year). This also seems like something appropriately handled by bureaucrats. Daniel Quinlan (talk) 18:27, 25 May 2025 (UTC)[reply]
I would agree with the above views that the recent "inactivity" RECALLs were more accurately "gaming" and "communication" (in different ways) recalls. Neither demonstrated a clear community desire to move inactivity requirements, and even less so raise any great ideas about what new requirements could be. As for excluding admins from guidelines/policies, that seems the opposite direction to what the RECALLs wanted, which is admins in touch with community expectations. CMD (talk) 01:54, 26 May 2025 (UTC)[reply]
I don't see the purpose of this. The recalls occurred because of a clear end run around existing rules. The rules don't need to be changed just because someone tried to get around them. Community action when someone is end-running around edit warring, as another example, is more than sufficient to deal with the problem rather than trying to make edit warring policy more extensive. Similarly, the recall process has worked perfectly as a community action system for someone end-running around the inactivity rules (and other admin problems re prior recall cases). Recall is already an existing method to deal with such edge cases and has worked perfectly well so far. I see no reason to change inactivity rules at this time. And I certainly see no need to alter recall rules until we actually have examples of inappropriate cases going through, which hasn't occurred even a single time thus far. SilverserenC02:20, 26 May 2025 (UTC)[reply]
That is exactly the point of concern. Gaming is not a bright-line policy that we can apply to inactivity because it's inherently impossible to figure out the actual situation that these real people are in and even whether if someone's actual intention is to game the system. When we talk about people not being allowed to game the system we should first and foremost be talking about disincentivizing gaming rather than punishing people who we think are gaming the system. If it was true that the current numbers are aligned with our inactivity standards, why do we care so much that they're gaming to exactly keep their rights? Is it true that they engaged in misconduct or showed that they were somehow out of touch with community norms? The answer is a resounding no. As I said before, the current example is one of recency bias where there is certain validity to the claims of gaming - but when we use for-cause processes to conduct processes that effectively sidestep procedural policy, it's only a question of when, rather than if, things will go wrong. --qedk (t愛c)08:44, 26 May 2025 (UTC)[reply]
Gaming is not a bright-line policy that we can apply to inactivity it's never possible to know for certain that somebody's intent is to game the system in any situation. Admin activity is not special there. That's not even a particularly unusual feature in terms of Wikipedian practice: people are routinely blocked as WP:NOTHERE or WP:VANDAL despite the fact that we don't actually know their intent for sure; similarly it's not unusual to see blocks for edit warring even when everyone involved stays on the right side of the bright-line WP:3RR. The fact that GAMING is not a bright-line policy means that we cannot automatically apply it, but if you think that we cannot realistically apply GAMING at all the solution is to abolish the policy entirely, not just say that admins don't have to follow it. No wonder people think the Super Mario effect is a problem. Caeciliusinhorto (talk) 18:36, 28 May 2025 (UTC)[reply]
This may not be very helpful, but I looked at some data regarding how many accounts are (even possibly) out of line with community standards and have or could have admin flags. 1) I assume that the activity of the 438 accounts at Wikipedia:List of administrators/Active is not in question. 2) There are 307 semi-active admin accounts. Some of these could be making minimal edits, but they would eventually hit the 100-edit/5-year cutoff in that case. 3) There are 94 inactive admin accounts. Changing the standards for these would really only matter if they actually lose their flags for inactivity and then ask for them back. 4) There are about 200 former admin accounts that were desysopped in the last five years due to inactivity or resignation (not "for cause" or other reasons that would make the account ineligible for re-sysopping) and haven't hit the logged action rule. Of these, Wikipedia:Former administrators/reason/resigned#Active and Wikipedia:Former administrators/reason/inactive#Active seem to indicate there are 78 (58+20) active accounts that would normally be eligible for re-sysopping after a hold to review the case. That leaves the list at Wikipedia:Former administrators/reason/inactive#Admins desysopped due to having made fewer than 100 edits in five years (criterion 2), who would need to establish a return to activity, a list of 123 accounts. If that's the list we are considering, then there is no ongoing risk of damage and a relatively small number of accounts that would be the target of any new rule; it seems like a case-by-case evaluation is possible since few of them are likely to ever ask for the tools back. If we are really trying to redefine inactivity to encompass more of the 307 semi-active and 94 inactive admin accounts, then I wonder what evidence there is of an actual problem under the current standards. How many of those 401 admin accounts are actually out of line with community standards and unable to be taken care of eventually under the current inactivity rules? (Open to correction on any classifications I've gotten incorrect here.) Dekimasuよ!06:08, 26 May 2025 (UTC)[reply]
I should clarify that even proposals that are adjacent or in opposition to what I think are quite doable - it's community consensus after-all. Currently, I see three (most of which are disagreed to mine, some agreement on BN, but whatever):
Tamzin's suggestion to allow crats to determine gaming - and have them determine if they should resysop. Theoretically, we can also extend resysop periods beyond 24 hours to allow for community input - this serves similar to recall with lesser requirement of community input but crats make the final call.
Thryduulf's suggestion of strengthening the criteria and enshrine not gaming as part of inactivity rules.
28bytes' suggestion (from BN) to simply enshrine gaming inactivity rules as part of the recall process.
I think it's a middling example of how it could be. I suspect it can be made more procedural like a crat chat, so the community aspect is more reserved. --qedk (t愛c)14:33, 26 May 2025 (UTC)[reply]
This is conceptually wrong. The whole point of things like Admin Recall is precisely to handle vague situations like gaming. The system worked fine, there's no need to change anything, other than perhaps convincing people that the system doing what it was intended to do is not some accidental slip-up. Inactivity rules are in place for a good reason. Enforcing them is a good thing, not a bad thing. The recall process worked and was "constructive" in this case. As edit count is a very weak signal, the standards are intentionally on the low side so as to avoid ensnaring innocent bystanders (e.g. still active admins but who are mostly active on other Wikimedia projects or other languages). Things like recall cover the case where the edit count is overstating their contribution, rather than understating it, because the 100 edits were all of an irrelevant "fixed a typo" kind. Or, put another way: the hard limits should be lenient. But that doesn't mean the subjective limit is lenient. This is, again, good practice, and not a mistake, but an intentional choice. SnowFire (talk) 16:33, 27 May 2025 (UTC)[reply]
And that's exactly why it's a bad idea. You create a rule - and then you provide a backdoor around the rule that does subsumes exactly what the rule was supposed to be for in the first place. How would we expect inactive or semi-active admins to automatically figure out what our soft limits are, is that not an utterly unrealistic expectation per se? --qedk (t愛c)07:33, 28 May 2025 (UTC)[reply]
No, it is not unrealistic for admins to stay in touch with community expectations. There's also no backdoor here, the hard limits are triggers for automatic deadminship, no more, and they are certainly not a target to aim for. CMD (talk) 08:53, 28 May 2025 (UTC)[reply]
I think we need to discuss what "stay in touch with community expectations" means. There are various adminny areas that I do not work in, so I have no idea what community expectations are in these areas. (So if I choose to do some work in those areas I will lurk first and try to find out what community expectations are). To fully understand what community expectations about admin candidates and admin behaviour is in general, one needs to spend quite a bit of time at places like RFA, village pump, ANI. These unwritten expectations (often about things that have nothing to do with the use of admin tools) can be hard to keep up with. I find it unreasonable to expect familiarity with all of this from people going through phases of low activity. Overall, we should remember that we do not have a functioning process for making new admins at the moment, so semi-active, inactive and former admins are our main source of future active admins. Why do we try so hard to make them unwelcome? —Kusma (talk) 13:05, 30 May 2025 (UTC)[reply]
Re QEDK: Nothing is unrealistic here. This isn't rocket science. All of the recalls-for-inactivity so far have been the kind where the inactivity was inarguable and obvious, and that the only conceivable argument against the recalls is "I disagree inactivity should be a criterion for de-adminship" (which, well, sure, but just say that then). Any attempted recalls on more arguable cases aren't likely to start to begin with, and aren't likely to succeed if they do.
Or, and feel free to correct me if I misinterpreted you: you phrase it as "create a rule." But 100 edits per 5 years isn't the operative concern; inactivity is the concern. 100 edits per 5 years is just the extreme level where the process becomes automatic because there's no argument otherwise. Everywhere else has wiggle room, which is good not bad to repeat, that means we're using human judgment rather than gameable rules. Just 200 edits but is caught up doing tech work and MediaWiki patch requests? Sure, no problem. 200 edits but they're substantial ones including admin work? No problem. 200 edits that are fixed a typo or editing their own user talk page to avoid automatic de-adminship? That's still inactive. Anyway, don't take it from me, ask someone you trust in real life, but change the domain and don't say which side you're on. e.g. is it acceptable for the aviation club to revoke admin-level access from some guy who just checks into the hangar for 2 minutes twice a year and does nothing but is over the bare minimum standard for automatic revocation. SnowFire (talk) 13:49, 28 May 2025 (UTC)[reply]
Okay, so you do understand me then? If an aviation club says you have to check in once a year to not have your access revoked and you do, they will literally abide by that expectation. It literally doesn't matter to them if you stay for 2 minutes or an hour. --qedk (t愛c)18:29, 28 May 2025 (UTC)[reply]
Please humor me and ask a friend, without cueing them what answer you "want" to hear. My expectation is that they will say that the letter of the requirements was met, but not the spirit, and the spirit is what's important, and the aviation club would be well-justified in revoking access anyway. It's certainly what Wikipedia does elsewhere (again, Extended Confirmed the most obvious example, it is not just a raw "any 500 edits, our hands are tied"). SnowFire (talk) 18:59, 28 May 2025 (UTC)[reply]
What? You want me to hypothesize but when I disagree with your hypothesis - I have to ask a friend (who I guess will have to agree with you)? Also what does gaming EC have anything to do with the actual points of discussion here? What if someone makes 500 pointless (non-disruptive) edits and then edits constructively? They should get blocked? What if they make 250 pointless edits? Or 50? Anyway, I don't that that's relevant and I'd prefer if you'd stick to the actual issues being discussed here instead of bringing up very slightly adjacent applications of gaming that very clearly do not apply here. --qedk (t愛c)08:50, 29 May 2025 (UTC)[reply]
Are two inactivity recalls too many inactivity recalls, such that the rules should be modified to reduce the number of inactivity recalls? Levivich (talk) 17:21, 27 May 2025 (UTC)[reply]
No, but two recalls in the span of a month both related to inactivity instead of actual conduct issues is too many. --qedk (t愛c)
I've seen only a few situations where it became a problem; in both cases it was incompetence. Probably a combination of the lower bar from "got in back when it was easy" combined with inactivity. Ironically, these both because problems when they did something. Ironically, those with zero activity do no harm. On one the incompetent one was given the bit back out of courtesy with just a simple request. How about raise the bar a bit and when and when an inactive admin runs into it the need to make a self-assessment statement that they feel that are current enough to do do the job properly in which case it gets waived? North8000 (talk) 18:24, 27 May 2025 (UTC)[reply]
I propose the opposite: add a mention to WP:INACTIVITY that these standards exist because we expect inactive admins to hand in their tools, and that doing the bare minimum to keep admin tools may be seen as gaming the system to subvert these expectations. Thebiguglyalien (talk) 🛸19:20, 27 May 2025 (UTC)[reply]
I think if the community wants inactive admins to relinquish administrative privileges, then the most straightforward approach is to just remove the privileges, rather than say the community might decide to remove the privileges at some point. isaacl (talk) 00:29, 28 May 2025 (UTC)[reply]
That's what WP:INACTIVITY is. The problem is that we have people cheating the system so they don't get the removal when they're supposed to. The solution is to say that they still get the removal if it's determined that they're cheating the system. Thebiguglyalien (talk) 🛸00:45, 28 May 2025 (UTC)[reply]
You're suggesting to add a mention that inactive admins are expected to relinquish administrative privileges, without defining the level of activity when that expectation starts. I'm saying the community should discuss if its expectations on when administrative privileges should be removed matches the current removal procedure, and if not, then change the criteria so they do. There are reasonable security concerns for doing so, and I don't feel it's a good idea to set up a sword of Damocles. If the community wants to make removal (and restoration when activity resumes) a normal occurrence, with no fault attached, it should just do it, and skip having a discussion about whether or not a particular case should be considered insincere. isaacl (talk) 01:05, 28 May 2025 (UTC)[reply]
We have done this. If an admin comes back within 3 years of their last edit they can simply request restoration with no fault attached. CMD (talk) 08:56, 28 May 2025 (UTC)[reply]
Unless they get recalled you mean, which is also exactly the problem we're talking about. Nothing simple about it. --qedk (t愛c)10:30, 28 May 2025 (UTC)[reply]
It sounds like the problem you refer to is that consensus can change, in which case I suppose there is no way around it and nothing simple as that's a building block of Wikipedia. However, it is not particularly or uniquely relevant to the point at hand, and I assume that on average admins are more aware of WP:CCC than most editors. CMD (talk) 11:13, 28 May 2025 (UTC)[reply]
That is an absurd reduction of what I'm trying to say. What we're doing is basically drawing a line in the sand, pointing admins that way and then saying "welp! there's actually an invisible line you didn't know about (because we didn't tell you), sorry!" and showing them out the door. --qedk (t愛c)11:40, 28 May 2025 (UTC)[reply]
This is exactly how edit warring works. You can comply with 3RR or even 1RR and still be blocked for edit warring. No one is promising that editors who comply with 3RR won't be blocked for edit warring. The rule isn't "don't cross 3RR," the rule is "don't edit war." Similarly, you can comply with inactivity requirements and still be recalled for inactivity. The rule is "be active." Also, unlike edit warring blocks, a desysop is not showing an admin out the door. Levivich (talk) 11:58, 28 May 2025 (UTC)[reply]
This is not "exactly how edit warring works" - editwarring, 3RR and 1RR are all very explicit that editwarring is not (just) a bright line issue. Admin inactivity, prior to the recent recalls, has been an explicitly bright line issue. When admins have become out of touch through inactivity they have been brought before ANI/Arbcom/Recall for the disruption their being out of touch has caused, not for being inactive. Thryduulf (talk) 16:51, 28 May 2025 (UTC)[reply]
Indeed, and so removals were restricted to situations where there was actual demonstrated harm. Nobody has articulated what harm someone minimally active but not misusing the tools is actually causing. Thryduulf (talk) 15:15, 30 May 2025 (UTC)[reply]
If you can show evidence that the basis for my opinion is wrong then I'll gladly reconsider. However all I'm seeing is refusal to engage on your part. Thryduulf (talk) 15:31, 31 May 2025 (UTC)[reply]
We have (mostly) not had a discussion yet about whether or not the community's expectations on inactivty matches the current criteria. (The discussion has been mostly about whether we should have a discussion.) We are not encouraging admins to request the restoration of administrative privileges by having a recall discussion using terms that bring their sincerity into doubt when removing privileges. If there is a community consensus for a much higher level of ongoing activity, then let's put it into effect without any recall discussion to trigger removal. isaacl (talk) 17:22, 28 May 2025 (UTC)[reply]
So you think that we should treat making occasional edits – just not as many edits as some people want – as being the same as "Making unconstructive or trivial edits"? PGAME has a numbered list, but that's the only item in the whole section. WhatamIdoing (talk) 01:42, 31 May 2025 (UTC)[reply]
If an occasional edit (singular) is made just in the nick of time to avoid a desysop, yes, they are defeating the spirit of the rule, which is exactly what WP:GAME is about. You can hand in the tools temporarily if life is getting in the way, and that's not a bad thing. Every single reminder admins are sent gives them the instructions to avoid making token edits to keep the tools and gives a link to BN to resign if needed. HouseBlaster (talk • he/they)03:03, 31 May 2025 (UTC)[reply]
What we're doing is basically drawing a line in the sand, pointing admins that way and then saying "welp! there's actually an invisible line you didn't know about (because we didn't tell you), sorry!" and showing them out the door: Yes, we are, and that's a feature, not a bug. The entire point of the inactivity requirements is that we shouldn't need to tell admins about "invisible lines" (read: community norms). They should already be familiar with those lines, because they're active in the community, and if they're not, they should turn in their adminship. If someone is gaming the deliberately low bar to keep their admin status, that feels like a perfect use case for recall. I don't see what problem any of this is trying to solve. Writ Keeper⚇♔14:22, 28 May 2025 (UTC)[reply]
The entire point of the inactivity requirements is that we shouldn't need to tell admins about "invisible lines" (read: community norms). They should already be familiar with those lines, because they're active in the community, and if they're not, they should turn in their adminship. I've been trying to think of how to phrase my thoughts on this, and Writ Keeper nailed it. ScottishFinnishRadish (talk) 14:46, 28 May 2025 (UTC)[reply]
Except we're changing the rules on them without telling them. We've spent the past quite a few years now telling admins that "being active in the community" means making at least N edits in (period of time). Now we are saying that's not true and "being active in the community" means doing that and a bunch of nebulous other things that are undefined and unknowable but if you don't do them someone will recall you. If you happen not to be paying attention to Wikipedia during a particular 24-hour period (if you're lucky) you could be out on your ear before you even know anybody is upset at you not doing something you didn't know you were meant to be doing. Thryduulf (talk) 15:26, 28 May 2025 (UTC)[reply]
Is that what has happened? Or have admins that have clearly gamed the activity requirements been recalled? WP:GAME has been a guideline long enough that it can legally vote in a couple months, so I don't think the community enforcing it is sudden or unexpected. The only difference is now the community has a path to address activity gaming by admins. ScottishFinnishRadish (talk) 15:43, 28 May 2025 (UTC)[reply]
Also, what we actually tell admins, in {{inactive admin}} and {{inactive admin 2}}, is: Inactive administrators are encouraged to rejoin the project in earnest rather than to make token edits to avoid loss of administrative permissions. So even if we accept your silly premise that admins must be spoon-fed their standards and expectations like a five-year-old, we are already doing that in this case. Writ Keeper⚇♔15:46, 28 May 2025 (UTC)[reply]
It's not a silly premise at all and I absolutely reject the bad faith associated with your comment, both towards me and towards those admins who are maintaining activity according the explicit standards we set for them. If we want to change those standards, that's fine, but what is not fine is pretending that we are doing something other than changing the standards and holding people to those standards before they have been changed. Thryduulf (talk) 16:04, 28 May 2025 (UTC)[reply]
Nah, I don't think you're in bad faith, I just think you're being silly. We at least nominally elect admins based on their cluefulness, which implies--perhaps even is defined by--the ability to read and apply these "unwritten rules" of community norms. If admins needed everything spelled out for them, then we could just replace RfA with a basic reading comprehension test. After all, it's not like the concept of "the written rule is a deliberately low bar that doesn't define the minimum acceptable behavior" is a foreign concept on Wikipedia; several others have already pointed out 3RR as an example. If we can't expect admins to pick up on both the community's feelings and the strong hints in the notification templates about activity, why do we expect non-admins to grasp the nuances of edit-warring beyond the bright-line 3RR? Writ Keeper⚇♔16:19, 28 May 2025 (UTC)[reply]
Those unwritten rules would be fine in theory if they didn't directly contradict the written rules. 3RR and edit warring are both explicit that edit warring isn't (just) a bright line issue. The activity reminders say that you should be engaged with the community - which is what the written rules say meeting the activity requirements is. Thryduulf (talk) 16:37, 28 May 2025 (UTC)[reply]
It doesn't, though. WP:INACTIVITY defines the threshold at which one is subject to procedural desysopping due to inactivity. It doesn't define what the meaning of "engaged with the community" vs. "inactive" is. (Nor should it, because such a definition would never be agreed upon by everyone--which is why we now have a community process in admin recall to handle it on a case-by-case basis, rather than a semi-automated process to decide it). Nowhere in there does it say "an active admin is considered to be..." or "an inactive admin is one that hasn't...". Which, again, shouldn't matter regardless, because we expect admins to be able to grasp the spirit of a rule without being slavishly devoted to the letter of a rule. Like, there's also no rule that explicitly says I shouldn't blank Jimbo's user page and replace it with a wikilink to Bomis Babe--he outright welcomes people to edit his page, and it's not a non-sequitur or anything. But I don't, because "reading the room" is a skill we expect admins to possess, and that applies here just as much as anywhere else. Writ Keeper⚇♔16:57, 28 May 2025 (UTC)[reply]
(de-indent, re Thryduulf above) What would it take to convince you that, even if you disagree as a matter of preference, that there is no "contradiction" here? Inactivity has always been a matter of human judgment. You can argue that it shouldn't be, but right now it is, and that's what the community wants. We want a system that can be easy on an admin with a low edit count but who is obviously active, and be harsh on an admin who made 1,000 edits to user page essays or something in the past 5 years and nothing else. If you disagree that's fine, but that's different from claiming that the standard was unclear. It's not unclear, it's just that the standard isn't 100% down to raw edit count. The exact same issue comes up with gaming extended confirmed status via pointless edits. It's not controversial that not all 500 edits are created alike, and the solution to accounts gaming the extended-confirmed requirements is not to increase the threshold to 1000 edits, but to have Actual Humans look at those 500 edits and say "hey, 497 of these were to a Sandbox page." SnowFire (talk) 17:08, 28 May 2025 (UTC)[reply]
Inactivity has always been a matter of human judgment except that is not what our admin inactivity policy says. I'm saying that the inactivity policy should match the community's expectations about inactivity. The recent recall demonstrate that there is currently a mismatch between what (some) members of the community expect and what the policy expects. That is the contradiction I do not wish to see continue: Either we change the inactivity policy to match the expectations or we change the expectations to match the policy. Thryduulf (talk) 20:26, 28 May 2025 (UTC)[reply]
By "our admin inactivity policy", do you mean the automatic desysopping threshold? Because that is not the "admin inactivity policy" (see the various analogies to 3RR vs. the policy on edit warring). To go back to my question - are you saying that you'd be satisfied by some sort of footnote on the 100/5 rule saying "this is the threshold that triggers automatic desysopping, it is not the sole expectation on admin activity, WP:Gaming the system applies to admins too"? This doesn't think very highly of admins if so that they need such a disclaimer... and as noted elsewhere the inactivity templates already encourage either a handing in of tools or a genuine return to activity rather than pro forma edits.... but maybe I'm misreading you. SnowFire (talk) 20:47, 28 May 2025 (UTC)[reply]
Once again meeting the explicit requirements in the policy and gaming are not the same thing and I will not be happy until they stop being incorrectly conflated. Thryduulf (talk) 20:51, 28 May 2025 (UTC)[reply]
I once again ask: What would it take to convince you that you're wrong? That the community does not see the 100/5 threshold as synonymous with "the policy" and that the GAMING criteria is intended to apply to admins just as much as EC-gamers? Because if this is impossible, then no "clarification" is required, that's just you refusing to understand the reality of the situation. (And I will again say that disagreeing with the community is fine, I have my own areas I think the community is Big Wrong on. But just admit that you disagree with the community then, rather than saying the matter is unclear.) SnowFire (talk) 22:34, 28 May 2025 (UTC)[reply]
What it would take to convince me that the written rules are the actual rules is to get consensus for changing the written rules.
For example, if you can get INACTIVITY changed to say something like "Admins can be desysopped for inactivity based on the subjective and even arbitrary view of whoever is doing the desysopping. If it gets so bad that they don't make even 1 edit per year, then the desysopping will be automatic, but noticeably higher activities are explicitly not a protection against desysopping for inactivity", then I'll agree that this view is the community's consensus, and not the work of a tiny percentage of editors trying to GAME their way around the written policy. WhatamIdoing (talk) 18:42, 30 May 2025 (UTC)[reply]
Yes. @SarekOfVulcan debating what the requirements should be is a lot more productive than trying to argue that we should be upholding requirements in excess of the ones that have consensus because some people think the ones with consensus aren't strict enough. Thryduulf (talk) 16:38, 28 May 2025 (UTC)[reply]
Firstly it's not a straw man, and I'm far from the only person who disagrees with you about whether following the rules as written is or is not gaming those rules. Please stop trying to characterise it otherwise. Thryduulf (talk) 16:48, 28 May 2025 (UTC)[reply]
"because some people think the ones with consensus aren't strict enough." is a strawman though. People aren't starting recalls for every admin who just exceeded those minimum requirements, only for those who actually game things by e.g. making false promises which result in a positive crat chat. We have a panic among some people after nearly every recall procedure it seems, but so far none of the succesful recalls have been shown to have been done incorrectly (recalling an admin who still had the support of the community, or a recall done by some coordinated cabal). Neither the inactivity requirements nor the recall requirements need adjusting, or at least for neither has such a need been demonstrated. Fram (talk) 17:19, 28 May 2025 (UTC)[reply]
To Fram's point, while you've made it quite clear that you think the inactivity requirements can't be meaningfully gamed, here are 25 to 50 users that disagree with you. Writ Keeper⚇♔17:23, 28 May 2025 (UTC)[reply]
And so what? We don't know if they gamed requirements, we don't know if it was something they faced in real life - they are just going to leave and that's it. There is literally no net benefit apart from removing admins who we think to a reasonable degree have probably gamed our inactivity guidelines. In terms of community effort and time consumed, it's literally a net negative. --qedk (t愛c)18:19, 28 May 2025 (UTC)[reply]
If it looks like a duck, acts like a duck, quacks like a duck, and makes blocks well outside of community norms less than an hour before being desysopped with the effect of evading the 5-year rule like a duck, I think it's more than reasonable to give the community a chance to call it a duck through the recall process, as they did. I still don't see the problem. Writ Keeper⚇♔19:50, 28 May 2025 (UTC)[reply]
We almost never know when it comes to gaming... Yet we have a strong understanding that removing editors who engage in consistent or egregious gaming is a net positive for the project and I don't see how it would be any different when the editor doing the gaming was an admin. The gaming admin is lucky to only get a recall and not a community ban for gaming (if they will game that system what system won't they game?) Horse Eye's Back (talk) 15:49, 29 May 2025 (UTC)[reply]
Recall that past discussions on setting activity standards had difficulty in setting them higher because there wasn't a consensus among the participants that admins must be continuously active to continue to be trusted to hold administrative privileges. I don't agree with some of the sentiments expressed that admins must be sufficiently aware that community sentiment has shifted. First, without a broader RfC, discussion is limited to a very narrow, self-selected segment of the editing population, which typically is more likely to have participants who have issues with the status quo. Second, I don't think it's reasonable to expect all admins to be assiduously tracking all discussions across the many forums where people like to discuss these matters.
I understand why some editors think ongoing activity is important for admins (connection to the community, ongoing exposure to current best practices, guidance, and norms, monitoring for accounts being accessed by others, and so forth). But past consensus has also felt that the volunteer aspect of the role must be balanced against this. I think it would be best for the community to definitively establish in a request for comments discussion if there has been a change in how the community weighs the tradeoffs. isaacl (talk) 17:38, 28 May 2025 (UTC)[reply]
The proposal of the OP is to exclude admins from following WP:GAMING. Changing inactivity thresholds does not affect this proposal, as gaming can happen for any set of guidelines. CMD (talk) 17:42, 28 May 2025 (UTC)[reply]
The proposal of the OP is not that important, the goal is to workshop ideas. I agree that gaming can apply to any guideline, I disagree with the supposition that inactivity guidelines being gamed is a concern and posit that admins should have the right to clearly understand what the community expects of them instead of being subjected to arbitrary recalls. The primary problem is that accusing anyone of gaming is an accusation of bad faith and there is no reasonable separation between someone who has gamed and someone who has simply failed to meet community expectations. That's the crux of the matter. --qedk (t愛c)18:19, 28 May 2025 (UTC)[reply]
If "accusing anyone of gaming is an accusation of bad faith", why seek to carve out an exemption specifically for admins instead of seeking a change that will affect everyone? CMD (talk) 18:31, 28 May 2025 (UTC)[reply]
What kind of a strawman is this? How is it at all a carve-out for admins? I'm explicitly stating (asking for, in fact) that community expectations should be codified into our policy. I'm literally advocating for more stringent expectations - so that - admins have clear expectations of their tenure, it's literally that easy. The reason that accusing someone of "gaming" is an accusation of bad faith is that any accusation of something negative is an accusation of bad faith, it's like if I right now, posited that you have vandalized the wiki - until proven, it's an accusation that is of bad faith. That is the key difference, you cannot prove that someone has gamed by simply being inactive. There is no way to tell the difference between admins making enough edits with the intent keep their rights and admins with the intent of improving the wiki but who have not been able to put in as much effort as they would like. --qedk (t愛c)18:49, 28 May 2025 (UTC)[reply]
Tamzin explained how in the very first reply of this thread. The first bullet point is an explicit carve out. It's very strange for you to call it a strawman so far down the thread. As for the rest, that still doesn't explain why such lenience should be applied to admins but not others. CMD (talk) 19:54, 28 May 2025 (UTC)[reply]
Just because someone disagrees with you does not make their argument a strawman. Just because a couple of people think something is a strawman does not necessarily make it so. QEDK has repeatedly engaged in good faith with those who disagree with them, it would be good if you could extend them the same courtesy. Thryduulf (talk) 20:28, 28 May 2025 (UTC)[reply]
@Thryduulf why are you directing this at me? QEKD is the one who called my observation a strawman. What courtesy have I not extended, and does that apply to what I said as well? CMD (talk) 02:25, 29 May 2025 (UTC)[reply]
Thryduulf just following up on your statement regarding courtesy. If it is relevant, the first use of "strawman" is in the third comment of the thread. CMD (talk) 01:16, 30 May 2025 (UTC)[reply]
Surely you cannot change the premise of the question and not expect me try to bring it to actually pertinent points of discussion - such that this process remains constructive. --qedk (t愛c)08:50, 29 May 2025 (UTC)[reply]
I am not sure what this is replying to, or what premise I am supposedly changing. The proposal is clearly written "Exclude gaming inactivity or inactivity as a valid criterion". As Tamzin said, this would "exempt violations of a policy we routinely block non-admins for violating". CMD (talk) 09:04, 29 May 2025 (UTC)[reply]
Fine, let's clarify how then. The initial premise I set was to ask the community for opinions on how we can avoid the recall process being used for determining subjective interpretations of gaming and align community expectations with actual policy such that the recall process does not need to be utilized at all. Your first comment mentioned that any guideline can be gamed and I agreed to some degree and explained exactly why particularly applying gaming here is a pointless and altogether a net negative for the wiki. You then proceeded to pick exactly one statement I made, changed the context and replied with why should our policy have a carve-out for admins when clearly that is not at all what was ever being suggested (which again I proceeded to explain in detail how not). Your third reply again goes to ignore what I've tried to convey, refers me to Tamzin's comment (who also I have engaged with extensively), does not answer any of the questions I've raised and just refers to it as a carve-out again. This is not constructive and I will respectfully disengage. --qedk (t愛c)09:21, 29 May 2025 (UTC)[reply]
I have not changed any context. Your explanations have all referred to gaming in general, which is why it is odd that they translate specifically into excluding the application to admin activity. (It also doesn't detail with the specific aspects of both cases at hand, which in different ways demonstrated quite clear issues.) I'm not sure what questions you have raised, but if you want the proposal to not be a carve-out, you should probably propose a new option that does not in plain text create an explicit carve-out. CMD (talk) 09:35, 29 May 2025 (UTC)[reply]
I mean, yes, but also admins are volunteers, so if the community's pleasure becomes too onerous, the outcome will be that we won't have admins (or worse, the only admins we'll have will be the ones who delight in endlessly arcane bureaucracy). -- LWGtalk20:48, 28 May 2025 (UTC)[reply]
This is hardly an onerous condition... So trotting out that truism just feels like misdirection. Any admin who would walk over this very reasonable requirement is an admin I'm happy to lose. Horse Eye's Back (talk) 15:53, 29 May 2025 (UTC)[reply]
It is not onerous to have a codified expectation of an admin but not an actual one that reflects the community viewpoint correctly - allowing for a recall process that subverts policy? --qedk (t愛c)12:15, 30 May 2025 (UTC)[reply]
Any hard rule (on any topic, not just in Wikipedia) with clear lines is subject to gaming. Every well functioning rule system has clear lines and then some judgement-based system to make decisions in gray areas. The particular case of administrator activity on Wikipedia is not special or interesting in this regard. 173.79.19.248 (talk) 15:02, 30 May 2025 (UTC)[reply]
Not an admin, and this discussion definitely doesn't incline me towards pursuing "the bit" but I try to stay up to date on community norms here and I'm struggling to comprehend what is the harm either side is trying to prevent here. As far as I can tell:
Long ago, the community established activity thresholds below which admins automatically get de-admined.
Some admins responded to this by a pattern of editing just enough to remain above the activity threshold.
Recently, the community established an recall process by which admins whose conduct is questioned by a sufficient number of users can be required to repeat the RFA or election process again to retain their bit.
On two recent occasions, this recall process was used to accuse admins like those mentioned in (2) of gaming the system, leading to their removal as admins.
???
I understand the benefit of timing out enhanced privileges in cases where we can't be confident the account is still under control of the original trusted user to reduce our attack surface from compromised accounts. In the case of the admins above, I fail to see how their retention or removal affects the project at all. It seems like any possible benefit in either direction has already been counteracted by the amount of wasted bytes in this discussion that could have gone towards content creation. We already expect admins (and experienced editors) to understand an incredibly complex set of norms and cultural context, and we already have fewer admins (and fewer editors) than would be good for the health of the project.
TLDR: the questions burning in my mind are:
How is the Wiki better now that the bit has been removed from those marginally-active editors?
How would the Wiki be better if those editors had retained the bit?
From what I've seen so far, it seems like initiating recalls on low-activity admins and trying to construct ungameable activity thresholds are both a huge waste of time, whose most tangible effect is likely to be a reduction in the willingness of people to consider taking up the admin mantle. -- LWGtalk20:48, 28 May 2025 (UTC)[reply]
These are very good points. An admin can only harm the project by taking actions. An inactive admin is not taking actions. Thryduulf (talk) 20:55, 28 May 2025 (UTC)[reply]
Moreover, if the object of the policy is to avoid hijacking of inactive accounts and admins out of touch with current policies, then the admin who does the minimum to retain the bit ("gaming") is no threat either. Hawkeye7(discuss)23:02, 28 May 2025 (UTC)[reply]
I don't know that it would help with the problems that some participants here are describing, but we could add a footnote to the inactivity section that notes that some admins have been recalled for activity that just barely exceeds the threshold of procedural desysopping. We could just state that fact and let readers take from it what they will, or we could explicitly say something like what we already say in the inactivity notice templates ("Inactive administrators are encouraged to rejoin the project in earnest rather than to make token edits to avoid loss of administrative permissions"). I'm hoping a footnote is a decent compromise between those who want admins to have more of a heads up and those who think there is no problem here. In general, as we start to rack up more recalls, I do think it's worthwhile to review our policies and procedures to harmonize them with community expectation. I don't think we should base major changes on a sample size as small as the one we have now, but tweaks/adjustments/footnotes/clarifications might be appropriate. Firefangledfeathers (talk / contribs) 22:24, 28 May 2025 (UTC)[reply]
I think I could get behind that change. "Sure, you can make one action per year if you want, but if you get a recall petition filed on you, don't be surprised." --SarekOfVulcan (talk)13:03, 29 May 2025 (UTC)[reply]
I think there is some consensus (from this discussion here) that gaming is a valid criterion and as such we should codify it into WP:RECALL and WP:INACTIVITY as a valid criterion (the first one being the community can recall you and the second one being crats can refuse to give your rights back). At the very least, it will disincentivize admins from attempting to game the system - and on the flipside, make them learn how to game better, which is an unfortunate outcome. --qedk (t愛c)12:15, 30 May 2025 (UTC)[reply]
Admins having to learn to game better is a better outcome than exclud[ing] gaming inactivity or inactivity as a valid criterion for using the newly established recall process. One of them improves behavior, the other lets misbehavior slide. ScottishFinnishRadish (talk) 12:28, 30 May 2025 (UTC)[reply]
How so? I thought this entire exercise was to prevent them from gaming the system, which we think is very wrong. --qedk (t愛c)12:30, 30 May 2025 (UTC)[reply]
Now that's just absurd, because that is exactly what I (and a few others) were proposing to fix by codifying community expectations into policy instead of doing it the other way around. --qedk (t愛c)12:36, 30 May 2025 (UTC)[reply]
(edit conflict) @ScottishFinnishRadish Do you really believe that incentivising gaming that is harder to detect is a good outcome? That that is a better outcome than eliminating the mismatch between the explicit requirements and community expectations such that gaming is no longer a thing at all? I certainly don't. Thryduulf (talk) 12:33, 30 May 2025 (UTC)[reply]
This whole discussion exists because what some community members define as minimally-acceptable activity and what policies define as minimally-acceptable activity do not match. The way to fix that is to find what the community consensus regarding minimally-acceptable activity actually is (which may or may not be what some particularly vocal individuals want it to be) and then change the policies to match that consensus and to prohibit recalling administrators for meeting those requirements but not unwritten ones that don't have consensus. The way to fix the disconnect is not to replace it with a different disconnect between written and unwritten rules. Thryduulf (talk) 12:46, 30 May 2025 (UTC)[reply]
Your perception that “you will be de-sysopped if you do not maintain activity above level X” is a definition of a minimum acceptable activity level is wrong. It is a definition of a maximum unambiguously unacceptable activity level (where “unambiguous” means “can be enforced automatically, without a further consensus-based process.”)
Almost certainly there is no true consensus about what a minimum acceptable activity level that could be expressed as an automatically enforceable rule; moreover, any attempt to clearly write down such a thing would *also* be subject to gaming. 173.79.19.248 (talk) 11:38, 31 May 2025 (UTC)[reply]
I don't mind your proposed language, but I'd slightly prefer not to explicitly use the word "gaming", since there's debate here over whether bare-minimum activity box-checking is gaming or not. My preference is based on likelihood in getting consensus here, not on which language might be better. Firefangledfeathers (talk / contribs) 15:44, 30 May 2025 (UTC)[reply]
I can understand that people are worried about a slippery slope here, but the two who have been recalled were both called out for the gaming well in advance of the recall petitions. I don't think it's fair to summarize this as "we tell admins there's a rule, and then desysop them anyway when they adhere to it". I'd be alarmed if that's what was happening. But it hasn't been. -- asilvering (talk) 14:59, 30 May 2025 (UTC)[reply]
I would support adding a piece about gaming to the inactivity requirements, per SFR. We don't need higher requirements - we need admins to abide by the spirit of the rule, rather than the letter, as with all policies. We block editors who make a fourth revert after 24 hours and 1 minute. We pull the EC flag from editors who make 500 rapid-fire sandbox edits. This is no different, and talk of secret unwritten rules is off the mark. Vanamonde93 (talk) 16:28, 30 May 2025 (UTC)[reply]
Yes, but in the case of the 24:01 fourth revert, it's the second revert that started the edit war, not the fourth. You were already 'guilty' before you reached the fourth revert. And EC is supposed to make 500 'real' edits, not run an unapproved bot for 500 edits. Everything the edit warrior and the sandbox bot were doing is wrong.
In contrast, "the spirit of the rule" for INACTIVITY doesn't say that admins are doing anything wrong by averaging one edit every 2.5 weeks (i.e., 100 edits/5 years), even if those edits tend to be bursty (e.g., 100 edits this year, 1 edit next year).
I do think there is value in retaining old admins merely because they're from an older time period. I think there are times when we need someone to remind us of our older standards, or to be the last person who remembers why a bot was configured a particular way, or to be disconnected from internal politics. But what irritates me here is that we haven't been able to get consensus to say in INACTIVITY that this is all vague and subjective and following the written standard is a de-sysop-worthy violation of the gaming guideline, and yet we still have a minority enforcing the rule that they can't (yet) get adopted as real. WhatamIdoing (talk) 18:58, 30 May 2025 (UTC)[reply]
Can ex-admins not remind us of our older standards, or be the last person who remembers why a bot was configured a particular way? Assuming there's no Men in Black-style memory erasure with the desysop that I'm unaware of. REAL_MOUSE_IRLtalk22:56, 30 May 2025 (UTC)[reply]
Can ex-admins not remind us of our older standards... not when you've bullied them all off the project for following the rules. Thryduulf (talk) 23:03, 30 May 2025 (UTC)[reply]
That's basically the problem. We could enforce an unwritten rule on "accounts", but that doesn't mean that the humans will continue feeling good will towards the project afterwards.
Imagine that you're having a horrible real-life situation. Like "family member dying of cancer" or "deployed to a war zone" bad. Imagine that it's long.
Do you think that when you finally have time for Wikipedia again, that you'll be feeling welcomed and supported by a community that says "How dare you only make a couple of edits each year for a couple of years in a row! They're obviously just trying to exploit our systems for their own benefit. ('Cause you know that being an admin here is a really valuable benefit to the user.) Let's de-sysop them while they're not looking!"?
I don't think people would return under those circumstances. Do you?
If we wanted to do something like this, then a statement that compliance with the rules isn't enough really needs to be in the written rules, and it needs to be there long enough for admins to notice its existence (e.g., two years, based on my experience with other policy and guideline work). WhatamIdoing (talk) 01:55, 31 May 2025 (UTC)[reply]
Nobody is asking for any kind of new enforcement. What I believe is that we should not restrict the community's ability to use the recall process. That's pretty much it. If the community wants to initiate recalls against admins that appear to be gaming the inactivity criteria, that's their prerogative. Writ Keeper⚇♔03:37, 31 May 2025 (UTC)[reply]
I really think we should acknowledge more that low activity and "legacy" admins are (a) humans who have put years of their life into this project and (b) potentially helpful. Too much of the narrative is that they are a problem that needs to be managed. —Kusma (talk) 07:50, 31 May 2025 (UTC)[reply]
That narrative exists because there have been numerous kerfuffles that occur when an admin not familiar with community standards takes an action that proves significantly controversial. Inactivity policies help lesson the chances of that, and those kerfuffles have actually occurred and have caused way more poor feelings than the hypotheticals imagined above. Further on the narrative, this focus on two recalls does not help it. There have been successful requests for readminship following deadminship due to inactivity. I don't have the numbers but I assume more than 2 didn't lead to a later recall, and that should be a considered part of the discussion around inactivity guidelines and policy. CMD (talk) 08:01, 31 May 2025 (UTC)[reply]
That is not at all pertinent to our current discussion. If this is a serious point you are trying to make, you should clarify how many of these kerfuffles were due to admins who were apparently gaming our inactivity policy. Otherwise, it simply does not apply to the matter at hand. qedk (t愛c)08:15, 31 May 2025 (UTC)[reply]
As you have done repeatedly, you have changed the premise of the situation itself to suit your point. That is the opposite of pertinent. How does your arbitrary kerfuffles that literally does not concern our discussion of admin inactivity criterion factor in? You seem to be saying that it's primarily caused by admins out of touch with community expectations who remained in power by gaming the system; and yet you have offered zero evidence to back that view up. qedk (t愛c)13:57, 31 May 2025 (UTC)[reply]
How do issues that arise following long periods of inactivity have nothing to do with inactivity? Please don't say I'm changing a premise and then make up an odd view and attribute it to me. CMD (talk) 15:59, 31 May 2025 (UTC)[reply]
What odd view? You have given nothing to substantiate your argument - the onus of your claim is on you and no one else. You're also doing the exact same thing in the thread below with Thryduulf, which is just incredibly unhelpful. You have a fundamental misunderstanding as to where primarily the disputes on this wiki stem from and if you think they're due to semi-active or inactive admins, you're gravely mistaken. If you're not willing to discuss this constructively, then I have no interest in engaging any further, sorry. qedk (t愛c)00:33, 1 June 2025 (UTC)[reply]
The odd view you directly wrote in the comment above. Plenty of people have engaged with you constructively throughout this thread, you have called their comments strawmen, something that Thryduulf noted was somewhat incivil above. Now you claim "You have a fundamental misunderstanding as to where primarily the disputes on this wiki stem", which, I have no idea how such a grand claim can even be extrapolated from this quite topic-limited discussion, nor how that can come in the same comment as a straight faced request "to discuss this constructively". CMD (talk) 17:02, 1 June 2025 (UTC)[reply]
That narrative exists because there have been numerous kerfuffles that occur when an admin not familiar with community standards takes an action that proves significantly controversial. So the problem is admins who take actions, not admins who don't.
The problem is admins who take actions after a long period of not taking actions, yes. The evidence is therefore in that very situation which has happened multiple times. CMD (talk) 16:00, 31 May 2025 (UTC)[reply]
Most likely helpful enough to still be a net positive to the wiki. What are the negatives to letting them continue to minimally contribute? CMD has pointed to the issue of out-of-touch admins who, when they finally return to active editing, take actions that are controversial, but can we not simply start a recall on admins who do problematic things due to being out of touch on the basis that they did problematic things and are out of touch? -- LWGtalk16:50, 31 May 2025 (UTC)[reply]
"can we not simply start a recall on admins who do problematic things due to being out of touch on the basis that they did problematic things and are out of touch?", that's what has happened, and yet here we are. CMD (talk) 16:49, 1 June 2025 (UTC)[reply]
we need admins to abide by the spirit of the rule, rather than the letter given that active administrators actively engaged with this discussion do not agree what the spirit of the rule is, how do you expect someone who is less engaged to know that the spirit is different to the letter, let alone what it actually is? Things like edit warring/3RR and similar make it explicit what the spirit is and how that relates to the letter. The inactivity policy does not do that. Thryduulf (talk) 01:27, 31 May 2025 (UTC)[reply]
The problem with spirit of the rule is that it's arbitrary. The inactivity policy has not been arbitrary, expecting semi-active / inactive admins to acquiesce the two is an unreasonable ask. At the very least, they need to be made aware of changed community expectations in some regard. qedk (t愛c)20:57, 5 June 2025 (UTC)[reply]
I've had some more time to think about this and I think the reason inactivity-based recalls for admins who appear to be deliberately editing just above the minimum threshold rub me the wrong way is that it seems to violate the principle that sanctions should be preventative, not punitive. I still don't feel like I've heard a solid case for what harm is prevented by recalling a minimally-active but otherwise unproblematic admin. Some might say "they aren't otherwise unproblematic if they are WP:GAMING the activity rules!" But WP:GAMING starts with the sentence Gaming the system means deliberately misusing Wikipedia policy or process for personal advantage at the expense of other editors or the Wikipedia community (my emphasis). I fail to see what "personal advantage" an admin who pops in once a year to make a few constructive edits is getting, and I definitely fail to see how that is "at the expense of other editors or the Wikipedia community". If an admin's minimal contributions aren't constructive, recall them for unconstructive editing, not for inactivity. I echo Thryduulf's sentiment that an admin can only harm the project by taking actions, and should be recalled on the basis of harmful actions they have actually taken. I don't see how edits that would otherwise be constructive become unconstructive in small quantities (assuming the minimum threshold of activity has been passed to keep us from being concerned about account compromise). On the other hand, a typical RFA consumes an amount of editor attention and time equivalent to years of contributions at the activity level community consensus apparently considers acceptable for an admin. So basically, my take: if an admin's edits are below the minimum threshold set by the community, they can be procedurally de-sysopped. If an admin's edits are unconstructive, they can be recalled for unconstructive editing, with no need to appeal to WP:GAMING. If an admin's edits are constructive, and above the minimum threshold set by the community, then it's not WP:GAMING, and a recall petition is a waste of time. In all cases WP:GAMING of activity thresholds is not an appropriate grounds for a recall petition. If people think that constructive editing above the minimum threshold is still grounds for de-sysopping, then they should seek community consensus to raise the minimum threshold. -- LWGtalk17:24, 31 May 2025 (UTC)[reply]
@LWG, this is a perfectly acceptable statement as far as I'm concerned, but it's still missing the point in the way that so much of this discussion has - the two admins who were recalled for gaming had been talked to about it already, over a protracted period of time and had not changed their approach. To my knowledge, this does not at all apply to the vast majority of low-activity admins. The philosophical discussion about admin activity is a real red herring here when what we're looking at is two specific cases of admins demonstrating specific behaviours, and not inactivity more broadly. -- asilvering (talk) 17:55, 31 May 2025 (UTC)[reply]
What have is examples of a few vocal editors who have a problem with activity levels the community has deemed minimally acceptable. We have no evidence that there was a consensus this was a problem, because neither of the administrators concerned stood at RFA - indeed in both recall petitions there were editors expressing opposition to recalling, despite that explicitly being irrelevant. If you think those specific behaviours are problematic then get a consensus that those behaviours are problematic. Thryduulf (talk) 19:09, 31 May 2025 (UTC)[reply]
If we're just talking about those two cases specifically, then I agree most of this discussion is missing the point. I'm replying to the discussion that seems to be happening, not the discussion that ought to be happening. I don't know all the context of those two cases, but from glancing through the recall discussions it seems there were other concerns about their conduct (i.e. the problem wasn't the low level of contribution, it was the low quality of contribution). I still feel that if the only objection to their conduct was a long pattern of editing just above the threshold, then they shouldn't have been recalled. -- LWGtalk19:30, 31 May 2025 (UTC)[reply]
Yes, there were other concerns. That's why various editors here are talking about how this is filling up with strawman arguments. It's true that there are some editors who believe our inactivity standards are too low; whether they'd be able to get community consensus to raise them is an open question. (I personally would argue against it - if someone gets the inactivity reminder, goes "aw crap, I didn't realize it had been so long" and logs back in to handle a bunch of reports at WP:AIV, that's a bunch of reports no one else had to handle and I'm perfectly happy with that. I don't think you need to be terribly plugged-in to the community to know that replacing a bunch of text with "I'M A BANANA" is vandalism.) But both of the recalls so far have been for highly inactive admins who were dicks about it. Talking about this like it's about inactivity in general is inventing a problem that hasn't actually occurred. -- asilvering (talk) 20:12, 31 May 2025 (UTC)[reply]
I think the last statement is an unfair reduction. The core issue has to be that the inactivity policy is inadequate because otherwise the question of gaming does not arise. That is to say, if we had a significantly higher threshold, no one would care about gaming because the admins are already doing what the community expects. Also see SFR's reduction above about where gaming better is essentially admins adhering to community expectations better, which is a perspective I'm somewhat aligned with (not necessarily agreeable to it). It's not that simple. qedk (t愛c)00:38, 1 June 2025 (UTC)[reply]
Doesn't the gaming issue still arise if people are perceived to have a pattern of making edits that barely meet the threshold without meaningfully contributing? When we accuse people of gaming EC the issue isn't that community expectations exceed the EC requirements, it's that the community expects people to meet the EC requirements through meaningful contribution rather than trivial tinkering. -- LWGtalk16:28, 1 June 2025 (UTC)[reply]
You are not wrong, I was merely pointing out SFR's point above - which is to say that at a certain point the difference between token editing and constructive editing disappears; although imo, the difference is already thin and I had reiterated earlier that attributing an intent to inactivity in terms of gaming is a slippery slope and I also disagree with it for purely philosophical reasons alone (see WhatamIdoing's reply a few paragraphs above, who explains it in more coherent terms). qedk (t愛c)17:48, 1 June 2025 (UTC)[reply]
Having read most of the above discussion, I'd like to add a perspective here from an admin who appears on the list of 307 'semi-active' admins that was linked above by Dekimasu (I had not been aware of this list previously, despite it being around since 2007). Like others whose activity has decreased, much of my editing activity was in the first 10 years after creating my account. It has been less since then, and my admin actions have never been that high. Despite the reservations some have (and will doubtless still have) about this aspect of my history, I did do two stints on the Arbitration Committee from 2009 to 2010 and 2013 to 2014.
I also recognise names here and there (among both those admins still active, those who are less active, and those who recently handed in the admin bit or who have had the bit procedurally removed). Most of those people made their own choices about their changing levels of activity. For my part, when the activity requirements first came in, I made a conscious choice, as various other parts of my life began to take priority, to set my own activity levels to check in at least once a month and to create at least one article a year (alongside other edits). That may seem low to some, but I wanted to remain engaged with and abreast of at least the major developments with Wikipedia (if not the detail) and aspects of the editing and administrating community. Most of my other activity (not logged) has involved reading news and noticeboards around en-Wikipedia.
I have observed, with a semi-detached level of interest, the steady changes and discussions around logged activity requirements, at times trying to work out whether I was still 'active' enough! This was all against a background of one day aiming to return to higher levels of activity, still drawn to Wikipedia because of the emotional, intellectual and social investment made in this project over the years. I agree with what others have said above about the human element. Many may have stories similar to that related here.
If you really want to find out what is going on with semi-active admins and what might (time permitting) make them more active or engaged again, I would suggest talking to them. Invite them to a centralised discussion and see how many turn up (you may have to allow some lag time for them to see the invite). Not all will be willing to participate, or want to go into any level of detail, but you may get a better idea of how to approach this from a more human perspective and find out why some people make the choice to keep the tools through periods of inactivity rather than handing them back in and asking for them back later (I have my own theories about this, but would not want to prejudice any discussion). Carcharoth (talk) 14:04, 2 June 2025 (UTC)[reply]
I appreciate your perspective, I would enjoy your thoughts on the discussion because the basic principle of conversations like these is to disagree - it's not prejudicial at all if it helps other editors on this wiki understand where you're coming from and what you think. I for one, think specifically your perspective as a "semi-active" admin is quite valuable here. qedk (t愛c)16:53, 2 June 2025 (UTC)[reply]
The insights are not very groundbreaking, just thoughts on how some people might see having the admin bit as them still being a "part" of the community, and that the act of giving it up (even voluntarily and with the option of taking it back up again later) would feel like them stepping further away when they might not want to do that (some people find it better to take a real break and come back refreshed). Some of the people who are inactive are so because they have better things to do, some will be because they don't have a choice, and they would love to come back more often but cannot. Psychology is a funny thing. Most of those who are less active appreciate what it is like (and the investment of time that it takes) to be very active. Those who have only ever been very active might have less appreciation of what it is like to be less active. The final point, that I forgot to make earlier, is that it would be nice to have some stability, rather than shifting goalposts. I know that is a function of the community's inability to reach a stable consensus, but is worth considering. Set some standards, and then leave it alone for a few years. I know that is rarely possible on Wikipedia, but there are times when I remember it being done like that. Carcharoth (talk) 09:11, 3 June 2025 (UTC)[reply]
In theory, I should know that, maybe? If you are right that they have not changed since 2022, I apologise. I got the impression that they had changed a lot since they first came in, but maybe I am remembering the many discussions attempting to change them. This reminds me of a short-lived attempt to impose moratoriums (moratoria?) on discussions to help encourage productivity (or discourage endless circular discussions). It never seemed to work, though it was a formal ArbCom remedy in the Macedonia naming case IIRC (or maybe the Ireland naming one). I digress. Is the progression in activity requirements over time laid out? No reason it should be. The status of a policy/guideline/essay used to be an indicator of its stability. How stable is this aspect of WP:ADMIN? Carcharoth (talk) 18:17, 3 June 2025 (UTC)[reply]
fwiw, I read "shifting goalposts" in your original post more as "please don't change the inactivity rules, since shifting goalposts is frustrating" rather than "please don't change the inactivity rules, since shifting goalposts again would be frustrating", and I think it works just as well that way. -- asilvering (talk) 18:26, 3 June 2025 (UTC)[reply]
I'm in the same boat as you, Car: I'm not entirely sure how often inactivity requirements have changed. From memory, I only recall the 2022 change (during the time I've been editing, since late 2018), but if they have changed often, then I'd agree the instability could be a challenge for admins. Levivich (talk) 19:50, 3 June 2025 (UTC)[reply]
I don't believe that's clear from this discussion, or relevant to it. I don't equate minimum requirements communicated in policy with editors expectations, and I would expect expectations to differ from minimum requirements, both then and now. And even if some editors' expectations have changed between then and now, that is to be expected. In fact, expectations changing over time is one of the reasons we have minimum activity requirements. Levivich (talk) 22:21, 3 June 2025 (UTC)[reply]
I think there's a massive difference between community expectations in situ and applying, or rather enforcing said community expectation via a procedural process that was never intended to apply to this particular usage. In fact, the second part is the more pertinent point of discussion here that we are proposing to amend to some extent, a part of which is figuring out the correct way to align community expectations in some regard such that a semi-active admin can understand what exactly is expected of them in the first place, otherwise it's just putting the cart before horse, no? qedk (t愛c)20:55, 5 June 2025 (UTC)[reply]
Redirects in native script
Do we have a policy about redirects in native script? I refer to יוסף אשרמן as an example of what I mean. Given the vast number of articles we have about people and places whose native name is not written in Roman letters, this practice could get seriously out of hand. However, I don't find this as one of the criteria for speedy deletion. The closest I can find is in WP:TITLE: "Names not originally in a Latin alphabet, such as Greek, Chinese, or Russian names, must be romanized", but can we assume this applies to redirect names? I believe it does, but before I start deleting things I'd like more opinions. Zerotalk01:51, 1 June 2025 (UTC)[reply]
It's worth noting that this essay (commonly referred to by its many shortcuts - WP:RLOTE, WP:RFOREIGN, WP:FORRED, WP:RFFL, WP:RLANG) is one of (possibly even the) most strongly supported rationales at RfD. Whether there is affinity between a language and subject is very often subjective, but I can't recall I've ever seen the deletion of a redirect from an unambiguous official or most common name in the subjects native language. At the other end of the scale, redirects with (almost) no connection between the language and subject are almost always deleted - for example while בִּנְיָמִין נְתַנְיָהוּ → Benjamin Netanyahu would definitely be kept, ג'ו ביידן → Joe Biden would be deleted. Another good rule of thumb is that if the term is mentioned in the lead of the article then it is very likely to be kept if nominated, especially if it's bolded and/or in the fist sentence. Thryduulf (talk) 02:35, 1 June 2025 (UTC)[reply]
Presumably someone who was reading a website that wrote the name with nikud and used the highlight>right click>search flow on a browser with Wikipedia set as a search engine. -- LWGtalk13:30, 1 June 2025 (UTC)[reply]
Yes it could happen, but very few web sites write it with nikud (less than one in a thousand if Google counts can be trusted). Zerotalk06:27, 2 June 2025 (UTC)[reply]
Hello. I came here after @Zero0000told me on my talk page to, "Please stop creating redirects in Hebrew script. We don't do that and I've request more input about it from the community." Though I asked, "If you can point to a policy or guideline that prohibits this practice I will gladly abide by it."
After reading the relevant policy and guidelines, it would seem that there was no policy supporting Zero0000's ask other than that he does not like it. If my understanding is correct, then I will continue to make these constructive additions when I create "a redirect from an unambiguous official or most common name in the subjects native language"... To be sure. An Israeli, may for example have a redirect of their Hebrew language equivalent, if I understand the above correctly, though to add a Russian language foreign language equivalent, would not make sense or be valid unless it was, for example, a Russian-Israeli subject for the article in question? Iljhgtn (talk) 03:07, 1 June 2025 (UTC)[reply]
@Thryduulf "Another good rule of thumb is that if the term is mentioned in the lead of the article then it is very likely to be kept if nominated, especially if it's bolded and/or in the fist sentence." I often will add the directly related foreign language equivalent in the lead using the Langx template, and then following that I will create the redirect, if it is an Israeli and they do not already have that redirect, but I always follow only if it is the most directly and commonly related language, for example with your Benjamin Netanyahu example. I do not believe that there is any prohibition on this type of edit and I believe these to be constructive edits and I am often thanked for them. Iljhgtn (talk) 03:11, 1 June 2025 (UTC)[reply]
A good recent example might be Henry Foner (chemist). Also, I was helped a while back in terms of which template to use with guidance from User:Harrz who first suggested to use R to transliteration Rcat instead of the R from alternative language template for these redirects. Iljhgtn (talk) 04:18, 1 June 2025 (UTC)[reply]
Based on my very limited understanding of Hewbrew, either or both depending on which are commonly used in relation to the subject. Thryduulf (talk) 20:56, 3 June 2025 (UTC)[reply]
My opinion is that the policy that article titles must be romanized applies equally well to redirect titles. This is also in line with decades of practice and exceptions are like hens teeth. There is also no purpose. Anyone who comes to the English wikipedia looking for יוסף אשרמן knows how to spell it in roman letters and in any case can find it with a simple search. Are we going to have a redirect in Chinese characters for every Chinese person or place, a redirect in Japanese characters for every Japanese person or place, and then there are multiple Indian scripts, Cyrillic, Arabic, Greek, Korean, Thai, and on and on. what about redirects in hieroglyphics for ancient Egyptians? If this is going to become a standard practice it will be a fundamental change to the outward facing image of the encyclopedia. Maybe that would be a good thing, but we should at least establish a definite policy on it. Zerotalk04:45, 1 June 2025 (UTC)[reply]
I have read through that archived discussion. The main risk, concerns, or opposition was centered around people inserting invalid or vandalism type foreign language equivalent redirects into Wikipedia, and that there would not be enough labor to help identify and correct for these acts of vandalism. Given that you are citing a discussion that happened 14.5 years ago, I think it is likely fair to say that there is a more robust editor base than before. Regardless, there was no clear opposition of the valid inclusion of non-vandalism type foreign character redirects, even in the archive you cited from. Iljhgtn (talk) 05:11, 1 June 2025 (UTC)[reply]
I was not familiar with the "hens teeth" line, but when I googled it, it said, "Extremely rare, unattainable or non-existent". If that is the meaning, then that could not simply be any further from the truth.
Since you first mentioned Chinese characters. Let's see what we can find, shall we?
Or how about Laos, type in ສາທາລະນະລັດ ປະຊາທິປະໄຕ ປະຊາຊົນລາວ.
"Hen's teeth"? If that meant "extremely common to the point of being near ubiquitous" then I would agree.
Lastly, "If this is going to become a standard practice it will be a fundamental change to the outward facing image of the encyclopedia". This is false on every level. The "outward facing" aspect of Wikipedia does not change at ALL with foreign language equivalent REDIRECTS precisely because they are REDIRECTS and not main space titles! If we were talking about titles of regular main space pages, I would agree, but this is in fact one of the core, common, and regularly valid uses of redirects from foreign language character equivalents! Iljhgtn (talk) 05:05, 1 June 2025 (UTC)[reply]
You show me a handful of examples out of countless thousands of articles? That doesn't disprove "hen's teeth". Exceedingly few such redirects exist compared to the number of articles which in principle could have them. Zerotalk05:11, 1 June 2025 (UTC)[reply]
I showed you that in mere seconds. If you want, I'll carve out a few hours and give you thousands of examples. Would that satisfy your hens teeth? Iljhgtn (talk) 05:13, 1 June 2025 (UTC)[reply]
It is a well established principle that the fact that other stuff exists is not a reason for it to continue to exist. Please address the issue raised above: should each article have a redirect in Hebrew, another in Chinese, another in Japanese, etc.? Clearly that would be ridiculous per the principles at WP:NOTDIRECTORY: Wikipedia should not list everything. Johnuniq (talk) 05:48, 1 June 2025 (UTC)[reply]
No one is advocating that. If there is a direct tie, e.g. a movie's original release title, or a political figure from a country that uses that scripts. We wouldn't have a Hebrew title for an American president or vice versa or a Chinese redirect to a Russian man. That is what WP:FORRED is for. We have 80,000+ r from lang redirects, several tens of thousands of which are non-Latin. PARAKANYAA (talk) 08:08, 1 June 2025 (UTC)[reply]
@PARAKANYAA is exactly correct. It only makes sense to have a foreign language redirect for a subject where the foreign language is most directly tied to that subject. Also, I will mention that r from transliteration is a big one that I was encouraged by @Harrz to use recently and he might have more to say on that, but I think there are many more templates that use this type of redirect than just R from alternative language. Iljhgtn (talk) 13:41, 1 June 2025 (UTC)[reply]
It's easy to type a non-roman character into the search box and get lots of hits. It's not so easy to judge how common it is. For that you also need to know how many articles don't have such redirects but could. For example, I looked the 40-ish cities and city municipalties in Thailand and found 4 redirects in Thai. (That's more than I expected.) When I looked at Israeli authors, I found that most had redirects in Hebrew but only because you (Iljhgtn) added them in the past 6 months. (Previously there were a few added in 2011.) Look, I'm not mortally opposed to this practice, I just think that somewhere in the policy pages the issue should be provided with guidelines. If the community thinks it's a good thing we should recommend it. Zerotalk06:35, 1 June 2025 (UTC)[reply]
I actually fully agree that mostly policy and guidelines should fully and explicitly either prohibit or permit (and even recommend) one thing or another. I have often encountered and found myself engaged in discussions of the past where other editors actually like the ambiguity and gray zone. I do not. I prefer clear "do this" or "do not do this" policy guidance, and so I am in agreement with you on that @Zero0000. Iljhgtn (talk) 13:43, 1 June 2025 (UTC)[reply]
By actual measurement (woolly due to the imprecise meaning of "roman script") there are 45,000 transclusions of {{R from alternative language}} with non-roman script. This is 0.6% of articles, which is more than I would have guessed. Zerotalk09:15, 1 June 2025 (UTC)[reply]
What about also {{R from transliteration}}? There are MANY, many more templates that use redirects of a foreign language equivalent! Iljhgtn (talk) 13:44, 1 June 2025 (UTC)[reply]
Like Johnuniq above, I am not seeing what a redirect page brings here. If an en.wiki article carries the name in a non-English main language, then the standard search does a decent job of presenting the relevant article, for example Duncan Livingstone / Donnchadh MacDhun and Hu Bo / 胡波. (My 1st example was going to be Sun Tailor, an indy musician I tagged for notability many years ago, but I see there is now also a redirect page at ארנון נאור.) So we have on-wiki search, we have inter-wiki article links at each article page top via Wikidata (which also has a table of per-language labels and descriptions); I don't see the need for an extra interlanguage redirect layer. AllyD (talk) 07:24, 1 June 2025 (UTC)[reply]
What is the scale of the issue here? Would there be a reason why it needs to be dealt with via speedy instead of RfD (i.e., is this another Neelix-sized case, in which case we'd probably create a temporary X-criterion instead of a permanent R-criterion). If relatively few foreign language redirects are problematic they can probably be dealt with on a case-by-case basis with whatever consensus arises at RfD instead. Alpha3031 (t • c) 07:28, 1 June 2025 (UTC)[reply]
The purpose is quite clear in that anglicizations are often very inconsistent and if one is basing an article off of non-English sources, the native-language term would be the most efficient way to find the article. How much to anglicize is also unclear, e.g. should we delete Türkiye? such redirects have saved me time repeatedly, standard search does a poor job of this kind of thing when there can be dozens of different anglicizations of someone's name. It getting out of hand is not a concern as long as WP:FORRED is kept to, e.g. it should only be done for topics where there is a clear relationship, like a film's original release title or the native language name of someone from that country. I also don't see why we're discussing script rather than language. PARAKANYAA (talk) 08:01, 1 June 2025 (UTC)[reply]
However, this advantage is minimized if the name is given in native script in the article lead or infobox, which is much more common and something we encourage. Zerotalk09:19, 1 June 2025 (UTC)[reply]
I say this is a "Why not both" approach. Also, if that is not in the lead, but then someone adds that to the lead, would they not then immediately be able to add the foreign language redirect immediately following that addition to the lead? That is common practice and it is one of the many edits that I routinely make. Several years in that one particular edit has only ever been viewed as constructive, though I've had suggestions over the years on how to improve it. For example, I used to only ever use Rcat {{R from alternative language}} and now I use that paired with {{R to transliteration}} most often, making the distinction of when a subject title is a transliteration or a translation. Iljhgtn (talk) 13:48, 1 June 2025 (UTC)[reply]
It still has a quite large benefit by 1) showing in the searchbar, saving a lot of time 2) not being easy to remove in cases like vandalism/article cleaning 3) foreign-script variations that are commonly used in sources but not in the article. Also, it really isn't in there as much as you think, particularly older or less well-maintained articles. Often I would just have the Russian name to search, it wouldn't be in the article, and the transliteration was inconsistent so it took me ages to even figure out if we had an article. Would not have happened if such a redirect existed.
I just don't see what the problem with it is. It provides me and several other readers with a large benefit, for what cost? It's not like we have some sort of Latin script purity in redirects language aside. We have redirects from Unicode. Emojis. Should we start deleting redirects from original, non-English supported diacritic cases? PARAKANYAA (talk) 15:15, 1 June 2025 (UTC)[reply]
No, at least a few of these are terms you might reasonably encounter (without a further explanation) in English language texts, e.g. the maths symbols and the micrometre. Helping people who find something unfamiliar and unexplained inside English texts is a basic use of a redirect on enwiki. But there are no English language texts which will e.g. put Mao's or Netanyahu's name in the original script and not in Latin script, so no readers of English texts will need these redirects to understand the text. Please don't use such hyperbolic strawmen by comparing apples and پرتقال . Fram (talk) 12:11, 2 June 2025 (UTC)[reply]
Redirects are cheap, so my default is to say if Iljhgtn is willing to put in the work great, go for it, unless I can see some sort of tangible harm it does. Possible forms of harm, in descending order of seriousness in my view:
Verifiability of alternate names. This is why we generally don't accept redirects from languages with no clear connection to the subject. But for cases like official names of persons/entities that are widely used in sources, this is not an issue.
??? Those two things are basically the only possible harms I can see from adding foreign-language redirects.
On the other hand, like PARAKANYAA I also personally benefit greatly from that kind of redirect since I frequently read non-English sources and it is helpful to be able to quickly copy/paste native-script names without having to figure out how to romanize them first (often that's how I find the correct romanization for further research). If this kind of thing is helpful for people like me and PARAKANYAA, and doesn't hurt anyone else, and Iljhgtn is willing to volunteer the work, why wouldn't we accept it? -- LWGtalk15:59, 1 June 2025 (UTC)[reply]
To be clear. I also add these for other languages. Though Hebrew is a favorite for me. I also add for Palestinian language pages (with Arabic) and Russian, and Yiddish (though admittedly to a lesser degree). I am glad that others see this activity for the constructive edit that it is, and I welcome as many more to join in and participate as might be interested and have the time to do so! Iljhgtn (talk) 22:43, 1 June 2025 (UTC)[reply]
This is not perhaps precisely the same issue, but I have serious concerns around Iljhgtn's editing concerning Hebrew names. Here he took an article with two foreign-language names and elevated only Hebrew to the infobox. Here he added a "native name" with no sourcing for a person who was born in the US and lived there for at least half of his life. The edits here are similar; I can see no evidence that Gaitsgory has a "native name" in Hebrew (why not in Tajik, Romanian, or Russian?). These are merely edits I happened to have noticed because articles were on my watchlist, but overall this project seems to me to be probably full of errors. --JBL (talk) 00:04, 2 June 2025 (UTC)[reply]
Restricting to just those with the most direct connection to Hebrew does seem to make sense. I can take special care to do that moving forward. Iljhgtn (talk) 00:22, 2 June 2025 (UTC)[reply]
@Iljhgtn I don't mean to pile on here, but please try not to translate names without a reliable source. We've had problems with Korean names written with Chinese characters being wrong, because people simply invent translations (see MOS:HANJASOURCE). We can avoid situations like this by relying on reliable sources for translations/transliterations. Toadspike[Talk]20:00, 3 June 2025 (UTC)[reply]
When you say This is not perhaps precisely the same issue you are partly correct, it is at most tangentially relevant to whether redirects from non-Latin scripts are wanted. If you think it warrants discussion, then you should initiate one in an appropriate venue. If you feel that any individual redirect does not meet the guidance at WP:FORRED then you should discuss that with the creator and/or nominate them for discussion at RfD. Thryduulf (talk) 00:22, 2 June 2025 (UTC)[reply]
I'd like to clarify how this sentence from WP:MPN should be interpreted: "Older names should be used in appropriate historical contexts when a substantial majority of reliable modern sources do the same"
Am I understanding this correctly that when we decide which name to use in a historical context, we should do so based on what current sources say when referring to that historical period, not what contemporary sources from that historical period say?
What brought me here is that on the Volodymyr Zelenskyy and Olena Zelenska articles, some editors have changed the spelling of their birthplace from Kryvyi Rih to Krivoy Rog in the infobox, on the grounds that Russian spellings were used in the Soviet Union in 1978 when they were both born. I understand this argument; however, if I'm understanding WP:MPN correctly, what matters is not what English romanisation was used when they were born, but what romanisation is currently used today to refer to Kryvyi Rih in 1978. Is this understanding correct?
I think my understanding is correct because WP:MPN also says "Names have changed both because cities have been formally renamed and because cities have been taken from one state by another; in both cases, however, we are interested in what reliable English-language sources now use." (emphasis mine) However, I'd like to find out if there's community consensus on this.
Your interpretation matches the way I've always understood it. Explicit note of the old name can be added if it will aid understanding or is important for context (e.g. "... born in Kryvyi Rih (then known as Krivoy Rog)") but that isn't always necessary or useful. More often helpful is noting the modern name/spelling when quoting old sources, but again that isn't required on every use. Thryduulf (talk) 13:05, 5 June 2025 (UTC)[reply]
Datawikiperson, it's used as a proxy for editing experience, familiarity with the rules, maturity, something like that. It is not a good proxy for editing experience. Unless someone comes up with a better idea, I guess it is here to stay. (I like the notion of true WP:CLUEness. If only we knew how to measure it). Sean.hoyland (talk) 16:03, 5 June 2025 (UTC)[reply]
There is also the idea that an edit count threshold is a barrier that people who do not think WP:SOCK applies to them have to cross. There is a hope/belief/assumption that the barrier might reduce the amount of sockpuppetry in contentious topic areas. It's possible that it does the opposite, by preferentially selecting for the most dedicated and persistent partisan editors and concentrating them in contentious topic areas. A solution that is often proposed is to lower the barrier. Then neutral, sensible editors will flow into the topic areas and dilute the partisan nonsense. This is a fantasy, in my view. Those people are not out there. They presumably have better things to do. You can see who's out there, thousands of potential editors, by looking at partisan media reporting and social media commentary about articles in contentious topic areas in Wikipedia. Yikes! Sean.hoyland (talk) 16:34, 5 June 2025 (UTC)[reply]
As the person who started that RFC, I'm doubtful that there's a significant difference between 300 edits and 500 edits. People who make 1 edits might not manage 10, but people who make 300 edits are fairly likely to make 500 eventually. I do think there's a difference between someone who makes 500 edits in 30 days vs 500 edits spread over multiple months.
For the people who actually achieve 500 edits (which is a very small number), it usually takes a year or longer to get to that point. The OP here appears to be on track for the median experience. WhatamIdoing (talk) 05:52, 6 June 2025 (UTC)[reply]
See, to me it's not about eventually, but more the level of experience already acquired that 500 edits very roughly demonstrates. Remsense 🌈 论05:54, 6 June 2025 (UTC)[reply]
This protection only applies to ~7800 of over 7 million articles (~1/10 of 1%) - which have been magnets for disruption. There is a backlog in the ECP Edit Request queue, an area I'd love to see more editor participation in. — xaosfluxTalk17:09, 5 June 2025 (UTC)[reply]
The number of edits is arbitrary. A person may achieve something in one edit that another takes 10 edits to do. However, as Sean says, it's the best system we've got for protecting contentious articles without putting too much power in the hands of administrators. I note that the OP has made 282 edits, which would clearly be on the right side of their proposal but is on the wrong side of current practice. Phil Bridger (talk) 19:28, 5 June 2025 (UTC)[reply]
The barrier to socks is worth preserving, imperfect though it is. It's true that some seriously good editors are dissuaded but we haven't found a better way to reduce the number of seriously bad editors. Since EC was introduced, the experience in contentious topics and the quality of articles (I'm most familiar with PIA) has increased enormously. It has been the most (maybe only) successful innovation since 3RR was cut to 1RR. Zerotalk06:50, 6 June 2025 (UTC)[reply]
So I'll start by saying I've never really liked ECP, well maybe in its earliest form as 1RR light applied to one specific page, but I digress, and I was very skeptical of broadening its application beyond topics covered by discretionary sanctions. However it really is the least bad way we've found to rate limit disruption so far. In practice many of the pages it's applied to are not ones we would want new users to cut their teeth on anyway since pages that warrant ECP are also the ones that tend to be less pleasant to edit for most people and place newcomers on a steep learning curve well steeper than usual anyway in an environment that is very much sink or swim.Even with the 500 edit threshold, SPAs and sockmasters manage to become EC as a matter of routine but for many though be no means all of them it results in some combination of increased chance of being spotted and increased time investment necessary to cause their preferred form of disruption, hence the rate limiting. It is by no means perfect, and it has a lot of collateral, and I'm the first to advocate for keeping this place as open as possible, but we really are in a situation where there are no good options, only some slightly less bad ones. 184.152.65.118 (talk) 01:21, 8 June 2025 (UTC)[reply]
Not quite, in fact you're seven years off and it was EdJohnston who got the ball rolling. It originated as a bespoke remedy in one specific ARBAA AE case where it did in fact function as a softer 1RR, was subsequently expanded under ARBGG, and WP:ECP2016, long before ARPIA3 more rigorously formalized its application. And now you too can propagate institutional knowledge along because I certainly don't have time to do it on anything like a regular basis anymore.What's most amusing to me is that many of the issues discussed in that original AE request still keep coming up again to this very day. But that's Wikipedia for you, chasing our tails since 2001. 184.152.65.118 (talk) 02:24, 8 June 2025 (UTC)[reply]
I support an increase in the number, not a reduction, to weed out vandals and incompetents. I do not know if there is a restriction on creating AfDs, but if not, there should be a similar one. Xxanthippe (talk) 04:32, 8 June 2025 (UTC).[reply]
Discussion about WP:DIALECT
There is an ongoing discussion about the future of the WP:DIALECT naming convention, that is, the naming of articles about dialects and language varieties. We invite fellow Wikipedians to join the discussion and provide their valuable feedback! – Aca (talk) 08:44, 8 June 2025 (UTC)[reply]
Technical
Edit Source (MiniEdit)
Currently, you can edit the entire article only .
I suggest making a mechanism that will track individual paragraphs and display a PENCIL "Edit Source" on the right.
You can see something similar in many web-mails (gmail.com).
Of course, the question immediately becomes what to consider a paragraph. This is not so important, you can combine several paragraphs to a large one.
Yes, that's exactly what I'm talking about. It often happens that the user does not see some scripts on the page. I've disabled everything I can. And on Chromium 136, I don't see this pencil. Like 99% of Wiki users Seregadu (talk) 04:56, 29 May 2025 (UTC)[reply]
I'm not exactly sure what issue you're having, but this is a script you need to add! I don't think you've done that, at least not to User:Seregadu/common.js, which is where you would only have to copy one line to enable MiniEdit. If you need more help, don't hesitate to ask. Remsense ‥ 论04:59, 29 May 2025 (UTC)[reply]
I'm going to try adding a script now, but why not do it for everyone?
Glad if I could help! Honestly, it's always worth considering that most people aren't "power users" like you and I, and maybe you can imagine little symbols showing up all the time being confusing or stressful for someone's grandma or a young child. Remsense ‥ 论05:03, 29 May 2025 (UTC)[reply]
Because the mechanism used to edit something is the section, not the paragraph. When you click an edit button next to a paragraph and get the whole section, your user will be like "what happened?!"
No! Exactly every paragraph ! After all, the pencil is already there and it works well. In this conversation, I can edit only the first 5 lines. Let's wait for your opinion when this conversation grows to 4 screens. Seregadu (talk) 05:14, 29 May 2025 (UTC)[reply]
2 problem that , that I found right now! And where is the community see ? I'm not just adding empty lines, I'm testing the script. I see that it requires updating the browser cache after each text change. It's not normal.
it's as if adding text removes the script from the browser cache. Seregadu (talk) 05:20, 29 May 2025 (UTC)[reply]
I finally tried this script now, I wanted to edit my message. The script prompts me to edit the entire header of this page, not my message. This script doesn't work for me. Neither at the 0 level of names, nor at 1, nor at 2. Seregadu (talk) 19:10, 29 May 2025 (UTC)[reply]
I couldn't find a link to my common.js page, and link to all the scripts useful to the user. You don't admit the idea that I should write them myself, do you? The obvious place: "Special pages" -- there is nothing.
Yes, I wasn't paying attention. I searched in the top menu, in the side menu, but not in my profile. I was no right. Yes, the script works for editing articles, but not discussions. And that's good too. Although it's strange for a Wiki to invent different text formats.
But you still haven't answered the question: "Why a simple user, even without knowledge of JS, doesn't see a link to a library of useful scripts or styles? It is a pity if it exists, but there is no link to it. Seregadu (talk) 16:51, 2 June 2025 (UTC)[reply]
So, unfortunately, I was logged out of my account, and whenever I try to log in, the following text message appears: “There seems to be a problem with your login session; this action has been canceled as a precaution against session hijacking.” It also further mentions that it may be due to my cookie settings. Well, I can’t access that due to this exact problem. If anyone could help me, I’d be very thankful. BTW, my account is “Long-live-ALOPUS”. This may have something to do with my account completing one year, but, I’m able to log in in other devices, not my iPad. Could it be a problem from my side? I don’t think I forgot my password. Please help. 2405:201:550B:B035:B588:DBDC:3F72:E094 (talk) 11:21, 31 May 2025 (UTC)[reply]
Try opening an incognito window (that's on Chrome; I think Safari and Firefox call it private browsing) and try to login there. If that works, that's a pretty good indication that you've still got some stale cookies that need removing. RoySmith(talk)18:04, 1 June 2025 (UTC)[reply]
That's a 12 year old machine (from when it was introduced). The newest version of iOS it should support is iOS 12. iOS 12 comes with Safari 12, which most definitely has "Private browsing". It is not unlikely that there is some sort of incompatibility with iOS 12 devices and the recent changes to the login methodology as it was likely never tested. Have you tested other language wikipedias ? What about https://en.wikivoyage.org ? —TheDJ (talk • contribs) 09:27, 2 June 2025 (UTC)[reply]
Well, I don’t have that private browsing feature; I think there’s a content filter, that’s why. Also, yes, I’m able to log in to my Arabic and Hindi Wikipedia accounts (which are the same name as my English one), but not Wikivoyage. Also, I’m able to log in from other, non-permanent devices, so this is a problem in my iPad. 2405:201:550B:B035:CD9E:1317:5009:A39B (talk) 12:57, 2 June 2025 (UTC)[reply]
Request: example of markup for tickable checkboxes
(Context) I would like to add a section to an article talk page which contains a list of checkboxes which I can tick and then save the section. Short of using 'pre' tag with '[ ]' and '[X]', is there a civilized way to do it? Gryllida (talk, e-mail) 12:50, 31 May 2025 (UTC)[reply]
So, I have written a Python code that takes a file, does some operations on the text, and replaces the old text with new text. Now, Wikipedia:AutoWikiBrowser/User manual#Tools allows external scripts, but I don't understand how to pass the article through the Python code. What additional code is needed for it? —CX Zoom[he/him](let's talk • {C•X})22:50, 31 May 2025 (UTC)[reply]
(When you do, I suggest showing the code that you used to do so, or at the very least whether you use pywikibot or handjammed things.) Izno (talk) 20:39, 1 June 2025 (UTC)[reply]
CX Zoom, to my understanding, you have a python script read the content from a file, and then write the changed content back to the file. So you could set the "Program or script" field to the python executable, then pass the path to the python script as an argument, then you'd have the script with something like:
@Qwerfjkl: The structure of script is similar. I understood the "Program or script" field also. But I don't understand the "Arguments/Parameters" field. Do we enter the same value in both fields? —CX Zoom[he/him](let's talk • {C•X})18:22, 2 June 2025 (UTC)[reply]
I am only guessing (and you need to ask this at AWB), the Arguments/Parameters would be something to specify the name of the file to be processed (variable "filename" in above code). If any other arguments were required by the Python program, they would also be given, similar to how you would run a program from a command line. Johnuniq (talk) 05:43, 3 June 2025 (UTC)[reply]
CX Zoom, as I said, you can put the path to the python executable (python.exe) in the Program or script field, and the path to the python script under "Arguments/Parameters". Equivalent to running python script.py in the terminal. — Qwerfjkltalk15:11, 3 June 2025 (UTC)[reply]
Is "Related changes" working properly? (example: Category:Use Malaysian English)
Category:Use Malaysian English transcludes {{Parent monthly clean-up category}}. That template was modified on 31 May 2025, but when I click on "Related changes" in the sidebar of Category:Use Malaysian English, the resulting page says No changes during the given period match these criteria. I have been having a feeling that "Related changes" has not been working properly for a few months, but this is the first time that I have been able to find a concrete example. Am I misunderstanding what "Related changes" is supposed to show? I use it to try to figure out why a page that has not been modified in a while is suddenly showing a change of some kind (e.g. a new category or syntax error). – Jonesey95 (talk) 14:27, 2 June 2025 (UTC)[reply]
That is a helpful link. I see an explicit statement there: Changes to transcluded pages like templates are not listed, unless there is also a link to or from the page. Maybe it has just been coincidence that clicking on "Related changes" has often worked for me in these situations. I guess my question is, then, if a page that has not been modified in a while is suddenly showing a change of some kind (e.g. a new category or syntax error), what is a good way to figure out what has caused the change? I seem to remember a script that sorted "Pages transcluded onto the current version of this page" by modified date, which would probably work, but I found it difficult to live with because if I was looking for a specific template, I could never find the template in the long list because it was not alphabetized. – Jonesey95 (talk) 20:06, 2 June 2025 (UTC)[reply]
The script is User:Anomie/previewtemplatelastmod but I also found it difficult to live with. I gave up using it because both the order and added information was unwanted most of the time and made it harder to find templates of interest. @Anomie: It's a great script when I do want the changes it makes. I would love to reinstall it if I had to click something on an edit page to activate it. PrimeHunter (talk) 21:17, 2 June 2025 (UTC)[reply]
I don't think this is true in the "to" direction. If you do related changes on a template and select changes linked to the selected, all the pages that include that template are usually included. Bawolff (talk) 00:06, 4 June 2025 (UTC)[reply]
Simple summaries: editor survey and 2-week mobile study
Hi everyone! I'm writing on behalf of the Web Team. Over the past year, the team has been exploring ways to make the wikis more accessible to readers globally through different projects around content discovery. One of the ideas we’ve been discussing is the presentation of machine-generated, but editor moderated, simple summaries for readers. These summaries take existing Wikipedia text, and simplify it for interested readers. Readers will show interest by opting into the feature and clicking to open the summary on pages where it is available. As part of our exploration into this idea, in the next two weeks we will be launching:
1. An editor survey on English, Spanish, French, and Japanese Wikipedias. This survey will ask editors on their preferences for generating, editing, and moderating summaries, as well as their thoughts on the project overall. We will use the data from this survey to propose the initial moderation workflows for a future version of a summary feature.
2. A two-week experiment on the mobile website. This experiment will allow a small set (10%) of readers to opt into and open pre-generated summaries on a set of articles for two weeks. After two weeks, we will turn the experiment off and use the data collected to determine whether users are interested in summaries and open them frequently, as well as whether summaries aid the overall experience.
After the completion of these two steps, we’ll be publishing our results on the project page and reaching out to discuss whether to proceed with building this feature and provide some options for its associated workflows for editors. You are welcome to leave questions around the project here or on the project talk page. EBlackorby-WMF (talk) 18:20, 2 June 2025 (UTC)[reply]
@EBlackorby-WMF But seriously. I'm grinning with horror. Just because Google has rolled out its AI summaries doesn't mean we need to one-up them.
I sincerely beg you not to test this, on mobile or anywhere else. This would do immediate and irreversible harm to our readers and to our reputation as a decently trustworthy and serious source. Wikipedia has in some ways become a byword for sober boringness, which is excellent. Let's not insult our readers' intelligence and join the stampede to roll out flashy AI summaries. Which is what these are, although here the word "machine-generated" is used instead
You also say this has been "discussed" which is thoroughly laughable as the "discussion" you link to has exactly one participant, the original poster, who is another WMF employee. Cremastra (u — c) 22:04, 2 June 2025 (UTC)[reply]
What a coincidence! I had just read this article (https://www.theverge.com/news/676933/gmail-ai-summaries-workspace-android-ios) a day ago and wondered if there would be a similar feature on Wikipedia. As long as this machine/AI-generated summary feature is opt-in, I don't see any downsides to having it available for interested readers. The attention spans of the younger generations are shrinking, and some would rather read a short summary of the World War II article than a 13,033-word long article; this feature would be useful and beneficial for them. Some1 (talk) 22:43, 2 June 2025 (UTC)[reply]
All right, they're a reasonably short summary. In any case, even in articles with longer leads like Romeo and Juliet it is possible to skim over or ignore the parts that disinterest me and still extract valuable information. Cremastra (u — c) 22:51, 2 June 2025 (UTC)[reply]
AI-generated simple summary of Dopamine The lead of Romeo and Juliet isn't as long as the lead of World War II, which I'd linked. It seems like these AI-generated simple summaries are ~5 sentences long, which is much shorter (and more digestible) than the average leads of (non-stub) articles. Some1 (talk) 02:28, 3 June 2025 (UTC)[reply]
Also, concerns about this feature should focus on the "This summary has not been checked for verifiable accuracy" part, not because "it's AI". Some1 (talk) 02:39, 3 June 2025 (UTC)[reply]
The first paragraph is generally the digestible summary of the summary. This is enforced technologically in mobile views, which is where most of the view of the above-maligned younger generations are going to be coming from, as only the first paragraph is shown before the infobox. For World War II, that is six sentences. CMD (talk) 04:58, 3 June 2025 (UTC)[reply]
@Some1 I only have experience with the beautifully named c4ai-aya-expanse-32b but I'd describe it as almost "on the level of OpenAI". Which is where a lot of companies are at. It refuses to tell me that I am wrong, even when I am intentionally saying stuff that is clearly incorrect. It says things like You're right; the poem I generated does indeed draw inspiration from the well-known and beloved "duck poetry" genre. Polygnotus (talk) 03:10, 4 June 2025 (UTC)[reply]
Some1, summarizing contentious articles and how that will almost certainly be exploited and weaponized by partisan actors is something that interests me too. For interest, see this recent query from a reader, where they appear to either a) assume that we control Google knowledge panels and/or b) that we should amend the wording to ensure the part they regard as important fits into the summary. It is the first time that I have seen something like this. Sean.hoyland (talk) 07:54, 4 June 2025 (UTC)[reply]
@EBlackorby-WMF Hi! As you can tell, your proposal does not align with what the community actually wants.
As you may or may not be aware, the WMF and the Wikipedia community have a very difficult and tense relationship.
It sounds like you guys already did a lot of work, without getting input from the community.
You link to this with the text we’ve been discussing but that must've been an internal WMF discussion because no one responded to that post.
Perhaps the Movement Communications team forgot to actually communicate with the movement?
I recommend stopping, and in the future asking for feedback at a far far earlier stage (but of course I know you won't).
There are many people here who are happy to help you by saying why we dislike certain ideas. But you need to involve those people at an early stage (during brainstorming), otherwise it is difficult to change course and you've wasted a lot of time and energy.
The WMF as a whole makes this same mistake over and over and over again. If you want to hear all the downsides and problems with a proposal, you can ask me on my talkpage. Polygnotus (talk) 05:15, 3 June 2025 (UTC)[reply]
Did a lot of work even go into this? It takes all of 5 minutes to set up the world's 327482th ChatGPT wrapper claiming to be a brand new feature. It feels slapdash and easy for them to throw up and it's such an insult to the community. 🌸wasianpower🌸 (talk • contribs) 04:20, 4 June 2025 (UTC)[reply]
The replies above may be missing the point. Imagine you were a WMF staffer. Would you want to fix boring bugs or would you want to work on AI for your CV? Johnuniq (talk) 05:49, 3 June 2025 (UTC)[reply]
Imagine you were a WMF staffer. Would you want to fix boring bugs? Hell yes I would. Have you seen my contributions here on en.WP? All I do is fix boring bugs so that our readers and editors get the pages, links, text, and images that they expect, with a minimum of errors. The WMF needs more gnome developers. – Jonesey95 (talk) 12:56, 3 June 2025 (UTC)[reply]
@Polygnotus: The joke in my reply is that I did work for the WMF from 2012 to 2020, and fixing boring bugs and working on the Action API are things I did. I also worked on Scribunto, TemplateSandbox, TemplateStyles, Special:ApiSandbox, and a bunch of other stuff. But eventually I wound up with a manager who seemed primarily interested in trying to climb the management ladder (yay kiss up kick down), and in general office politics became a bigger and bigger requirement, and eventually they fired me, no real reason given. Even if they'd be willing to rehire me, I hear the office politics have continued to get worse since so I still might not fit in anymore. Anomie⚔00:03, 4 June 2025 (UTC)[reply]
I would want to fix longstanding bugs too, and while as a volunteer I'm probably not as dedicated as Jonesey95 I actually did apply for a job with the Wikimedia Foundation and got an interview but was turned down. * Pppery *it has begun...15:31, 3 June 2025 (UTC)[reply]
"While we were impressed with your qualifications and experience, we have decided to proceed with other candidates". No other detail, and I didn't ask. I don't think "by whom" is a useful question to ask; the email I got was from a member of the recruiting team but I'm sure she wasn't the one actually making the decision. * Pppery *it has begun...15:37, 3 June 2025 (UTC)[reply]
Cui bono? Is there some financial incentive to make this decision which, from our point of view, doesn’t make any sense? I mean for the foundation as a whole, not any individual working there. I’m trying to understand where the pressure to do this is coming from. 3df (talk) 02:45, 4 June 2025 (UTC)[reply]
@3df, believe it or not, there are people out there who think this kind of thing is useful, and a great many of them work in development. No ulterior or secret motive is necessary to explain it. -- asilvering (talk) 02:47, 4 June 2025 (UTC)[reply]
@Asilvering Agreed. Although it would be very very beneficial for the AI company to have people correcting the output of their AI for free. They normally have to hire people to do that job. Polygnotus (talk) 02:50, 4 June 2025 (UTC)[reply]
Nope, I don't want an additional floating window of content for editors to argue over. Not helpful or better than a simple article lead. ꧁Zanahary꧂06:36, 4 June 2025 (UTC)[reply]
Keep AI out of Wikipedia. That is all. WMF staffers looking to pad their resumes with AI-related projects need to be looking for new employers. Carrite (talk) 16:01, 3 June 2025 (UTC)[reply]
I'm glad that WMF is thinking about a solution of a key problem on Wikipedia: most of our technical articles are way too difficult. My experience with AI summaries on Wikiwand is that it is useful, but too often produces misinformation not present in the article it "summarises". Any information shown to readers should be greenlit by editors in advance, for each individual article. Maybe we can use it as inspiration for writing articles appropriate for our broad audience. —Femke 🐦 (talk) 16:30, 3 June 2025 (UTC)[reply]
But 99% of the AI consumers knowingly interact with is trained on Wikipedia, so they don't need wikipedia.org for that. So the WMF is proposing making a shittier version of something that already exists. Polygnotus (talk) 16:49, 3 June 2025 (UTC)[reply]
It would be good if we had our own version of it, where we could control what is shown and how it is shown, instead of having a for-profit company modify our content as they please with no way for anyone to do anything about it, and no free and open alternative. Matma Rextalk17:39, 3 June 2025 (UTC)[reply]
That appears to be based on a bunch of incorrect assumptions. It is not like a nuke, we don't need to have it just because others do.
we could control what is shown and how it is shown Being able to set a system prompt is not control, you'd have to train your own model, which means either copyright violations on a massive scale or training on model exclusively on Wikipedia data, meaning it would be completely inferior to what is available.
instead of having a for-profit company modify our content as they please with no way for anyone to do anything about it Have you read WP:REUSE? This is what you signed up for.
and no free and open alternative What are you talking about? Anyone can download ollama. https://ollama.com/ The WMF does not have the money and brainpower required to develop a serious alternative to the existing models, and if they try that is a clear indication that they don't understand their role. But the screenshot says that the name of the model is Aya. Aya is a family of models by Cohere Labs. https://cohere.com/research/aya Which is a for profit company. Polygnotus (talk) 18:10, 3 June 2025 (UTC)[reply]
@Polygnotus Your comparison to nuclear bombs seems out of proportion.
Being able to set a system prompt is not control I don't mean a system prompt, I mean the user interface around the summary (see the mockup earlier in the thread, with ample warnings and notes, and compare it to the summary in Google or whatever else) and I mean the editorial control to hide or override these summaries if they're egregiously wrong, which I hope will be available if this experiment becomes a real feature.
Have you read WP:REUSE I think it's a bit rude of you to imply I don't know what I'm talking about. Anyway, have you seen how the content is actually presented by the various LLM companies? They don't generally cite content as they should (and not just from Wikipedia), and as far as I can tell no one yet has managed to force them to do it.
What are you talking about? Anyone can download ollama Famously, everyone on the planet has a computer able to run large language models, and will not mind waiting several seconds or minutes for the results to come out. Oh, wait. Local models are only a viable alternative for a small group of people.
I don't think you replied to what I said, only to things you imagined I said. I'm happy to argue for a bit, but please slow down. Matma Rextalk21:01, 3 June 2025 (UTC)[reply]
They don't generally cite content as they should (and not just from Wikipedia), and as far as I can tell no one yet has managed to force them to do it. DuckDuckGo does these days. Izno (talk) 21:06, 3 June 2025 (UTC)[reply]
I mean the user interface around the summary (see the mockup earlier in the thread, with ample warnings and notes, and compare it to the summary in Google or whatever else) and I mean the editorial control to hide or override these summaries if they're egregiously wrong, which I hope will be available if this experiment becomes a real feature. People do not read banners and warnings, see Banner blindness. You can never make a banner big enough to force people to read it. override these summaries if they're egregiously wrong Even the example they provided is already egregiously wrong, of course they will be. Having humans override the after the fact is not a reasonable solution to a giant problem.
I don't think WP:REUSE is a very popular page, and there are tons of people who don't realize that basically anyone can copy anything from Wikipedia, and no one does anything about it, even if they do not follow the terms of the license.
have you seen how the content is actually presented by the various LLM companies? They don't generally cite content as they should (and not just from Wikipedia), and as far as I can tell no one yet has managed to force them to do it. Yes, I have, which is why my opinion is what it is.
Local models are only a viable alternative for a small group of people. agreed. You talked about no free and open alternative which is why I mentioned Ollama.
please slow down I mean if they really do this I think we've lost the war and I'll just leave Wikipedia. Or set up an alternative and then leave. Polygnotus (talk) 21:13, 3 June 2025 (UTC)[reply]
What war? Whose against whom? And what does MAD has to do with this discussion? Do you think we're building Skynet here or something? I am baffled and at a loss as to how to reply to this. Matma Rextalk21:18, 3 June 2025 (UTC)[reply]
You wrote what does MAD has to do with this discussion? in response to me writing The nuke thing is a famous example of game theory, see Mutually Assured Destruction for more. which was my reponse to Your comparison to nuclear bombs seems out of proportion in response to me writing It is not like a nuke, we don't need to have it just because others do.
One of the reasons many prefer chatGPT to Wikipedia is that too large a share of our technical articles are way way too difficult for the intended audience. And we need those readers, so they can become future editors. Ideally, we would fix this ourselves, but my impression is that we usually make articles more difficult, not easier, when they go through GAN and FAC. As a second-best solution, we might try this as long as we have good safeguards in place. —Femke 🐦 (talk) 18:32, 3 June 2025 (UTC)[reply]
@Femke You seem to ignore this comment where I explained that the WMF can't compete with AI companies whose core business is to develop AI models, the fact that a model trained exclusively on Wikipedia data would be far inferior to a model trained on a far far larger dataset, and the fact that they are using Aya. as long as we have good safeguards in place What do you mean? Polygnotus (talk) 18:37, 3 June 2025 (UTC)[reply]
As in: moderation before something is put to readers, rather than after the fact. Which would in practice restrict the feature to high-priority technical articles, given that we have limited editor time for this. I don't know enough about the specifics of Aya to comment intelligently there. —Femke 🐦 (talk) 18:42, 3 June 2025 (UTC)[reply]
@Femke I think you know that is not what the WMF is proposing. So your comments make no sense. we might try this They are not proposing that we try anything. They are proposing giving the most important screen real estate we have (the WP:LEAD) of every article to a for-profit company.Polygnotus (talk) 18:45, 3 June 2025 (UTC)[reply]
In the comment above, they say that the moderator workflow is still to be determined. You're probably right they don't have a 'check first' workflow in mind, but if there is consensus to implement this (and it seems from this discussion so far that there probably isn't), I imagine the community would only be okay with this with extremely strong moderation in place. Like, the CMD example below is something that needs to be avoided at all costs.
Perhaps, it's time to start a Wikiproject and some type of contest to fix the problem identified and ensure we write articles that people can actually understand. My Challenges seem not to work as an encouragement. —Femke 🐦 (talk) 18:52, 3 June 2025 (UTC)[reply]
You think people are lining up to check the work of an AI model? Especially when summarizing complicated technical topics most people don't even understand? Polygnotus (talk) 18:58, 3 June 2025 (UTC)[reply]
Just to be clear, I oppose the test of unverified AI summaries as is slated for next week to 10% of mobile editors (phab:T393940). The foundation cannot dictate content. —Femke 🐦 (talk) 06:49, 4 June 2025 (UTC)[reply]
A truly ghastly idea. In other words: Yuck. Since all WMF proposals steamroller on despite what the actual community says, I hope I will at least see the survey and that—unlike some WMF surveys—it includes one or more options to answer "NO". Yngvadottir (talk) 17:02, 3 June 2025 (UTC)[reply]
It sure looks like they are planning to ask casual readers who use the mobile app. And if you ask them, their answer would probably be "yes". But that doesn't mean that it is a good idea. And introducing AI summaries would probably lead to a fork and an exodus. I would honestly be shocked if AI is not the final straw in the relationship between the WMF and the community. Polygnotus (talk) 17:17, 3 June 2025 (UTC)[reply]
The survey linked below was much as I expected: almost nowhere to express disapproval of the whole putrid idea. Bonus: video without closed captions. Of text. On YouTube. Classy and inclusive. Yngvadottir (talk) 23:24, 3 June 2025 (UTC)[reply]
@Yngvadottir I really enjoyed the question about a An AI-powered dashboard that shows the quality and metrics for summaries for my wiki.
What is an AI-powered dashboard??? This was clearly written with someone who is unfamiliar with the capabilities and limitations of AI technology.
Also my wiki shows that they want to dump this trash on multiple wikis, despite the fact that everyone who speaks languages other than English and English knows how much worse the experience in another language is, compared to English. Polygnotus (talk) 01:57, 4 June 2025 (UTC)[reply]
Yea I saw that too. The survey that I did had nowhere for me to say that it was a bad thing. In fact there were even worse ideas listed there too, such as edits to summaries might not even be listed anywhere unlike edits to normal pages. 2007GabrielT (talk) 12:17, 4 June 2025 (UTC)[reply]
Laudable goal, but if it is to go through, it should be only if established editors, i.e. extended confirmed editors, decide if the generated summary can supercede the current lead, or decide that the generated content requires modifications before using. – robertsky (talk) 19:03, 3 June 2025 (UTC)[reply]
@Robertskyif the generated summary can supercede the current lead That is not what they are proposing at all... if established editors, i.e. extended confirmed editors, decide that is also not what they are proposing decide that the generated content requires modifications before using that is also not what they are proposing. Polygnotus (talk) 19:06, 3 June 2025 (UTC)[reply]
@Polygnotus, The lead is supposed to be the summary of the article. Why have another machine generated summary if the lead is doing the job? editor moderated is what they are proposing, and they asked for editors' preferences for generating, editing, and moderating summaries. So I am suggesting as such. – robertsky (talk) 19:17, 3 June 2025 (UTC)[reply]
@RobertskyWhy have another machine generated summary if the lead is doing the job? Are you asking me that? That is the WMFs proposal, and I am saying it is a bad idea...
Look at the screenshot. It shows both the current lead and the AI summary that contains multiple errors.
My brother in Zeus, Cohere Labs is worth billions. Do you want Wikipedia volunteers to work for them for free??? You do realize that AI companies hire people to do the work you seem to think should be done by unpaid volunteers?
A note that the WMF has begun requesting responses to surveys via the QuickSurveys extension, so some (like me) should get a prompt inviting you to the survey if enabled. Some of the questions... aren't great if I'm honest. – Isochrone (talk) 20:45, 3 June 2025 (UTC)[reply]
Since the WMF is willing to be this sneaky, I don't think we should feel guilty if we fill in the survey a couple hundred times. Polygnotus (talk) 21:04, 3 June 2025 (UTC)[reply]
Let's intentionally skew the results! The WMF intentionally skewed it by picking who to show it to; the community should skew the results to tell the WMF to stop trying to put AI in Wikipedia! Polygnotus (talk) 21:14, 3 June 2025 (UTC)[reply]
And then the legitimate consensus among the people who took the survey will probably be thrown out, requiring us to rely even further on RfCs and other community headaches. ⫷doozy (talk▮contribs)⫸23:20, 3 June 2025 (UTC)[reply]
If this were to actually happen, some or many readers would just glance at the summary instead of reading the article. Since the summary will form the glancers' entire impression of the subject, it needs to be extremely accurate. I suspect it is often not. Even if editor moderation helps this problem, you may as well just go to Simple English Wikipedia and get the same thing but actually made by humans. ⫷doozy (talk▮contribs)⫸20:54, 3 June 2025 (UTC)[reply]
Haven’t we been getting good press for being a more reliable alternative to AI summaries in search engines? If they’re getting the wrong answers, let’s not copy their homework. 3df (talk) 21:16, 3 June 2025 (UTC)[reply]
Oppose. We already have summaries of our encyclopedia articles: the lead sections of our encyclopedia articles are the summaries of the article. Also, Wikipedia is already a massive collection of great summaries, because writing an encyclopedia (tertiary source) is the skill of summarizing secondary sources such as newspapers and books. Also, our leads (summaries) are so good that Google and other search engines use them in their knowledge panels. Wikipedia and AI are in the same business (summarizing) and we humans at Wikipedia are better at it than AI. I see little good that can come from mixing in hallucinated AI summaries next to our high quality summaries, when we can just have our high quality summaries by themselves. –Novem Linguae (talk) 22:12, 3 June 2025 (UTC)[reply]
Thanks! So a planned deployment to 1% of readers on Monday 9 June, and then expanding to 10% of readers on Tuesday 10 June, and a possible further expansion on Monday 16 June. CMD (talk) 04:35, 4 June 2025 (UTC)[reply]
@Novem Linguae Do you happen to have access to that stuff hosted on Google?
Are we for real?? Just last week I noted to staff that any rollout of LLM content would be unacceptable to the community, and now we're suggesting integrating it into a core aspect of content? Leads are already a shortened version of a page. The best leads have been carefully crafted by dozens of editors and represent some of the best content in the world. Using LLMs to generate what is effectively a worse lead will only amplify problems like at Sambhaji (angry readers read a lead but not the body). Devs, please realize that we are not going to accept integrated LLMs, and stop wasting time on such boondoggles. I will strongly oppose the integration of this feature into EnWP or any other Wiki. Our reputation is on the line here. CaptainEekEdits Ho Cap'n!⚓23:09, 3 June 2025 (UTC)[reply]
Oh, and to be clear: I absolutely, categorically, totally oppose the 2-week testing period. I support removing it via site CSS, or just blacking out the site. Or better yet, the Foundation can back down from this foolish course of action. CaptainEekEdits Ho Cap'n!⚓23:22, 3 June 2025 (UTC)[reply]
I feel like people seriously underestimate the brand risk this sort of thing has. Wikipedia's brand is reliability, traceability of changes and "anyone can fix it". AI is the opposite of these things. Public sentiment (among some corners) is reacting against the AI trend quite harshly. Projects like this threaten the brand good-will that Wikipedia has based on its unique strengths. The current climate gives Wikipedia a unique opportunity to be the answer to the AI-ification of everything. Why are we throwing that away? Bawolff (talk) 00:17, 4 June 2025 (UTC)[reply]
I am going to join the chorus of editors saying that this is a uniquely bad idea. But I'll focus on one thing from the survey: generic readers should not be the ones who decide whether the AI summary is "helpful". If I come to Wikipedia because I want to know who founded the Roman Empire, and AI tells me it was Tiberius, I would be eternally grateful... until I find out that it was Augustus. I don't doubt that this was created with the best of intentions, but I really hope that the WMF spends its resources elsewhere (for example, fixing the remaining mobile communication bugs). HouseBlaster (talk • he/they)01:10, 4 June 2025 (UTC)[reply]
The use of AI today comes with a caveat that the "AI can be wrong" and "AI should not be trusted 100%". I am not saying that Wikipedia is 100% right, but Wikipedia should remain to be more reliable than whatever Grok or ChatGPT can write up. If we use AI, we would go down into their level of reliability, which I didn't think to be the best way to go. We have seen many people, both with good and bad intentions, have criticized the reliability of Wikipedia. Going down the AI route will only reduce our "perceived reliability" even more. ✠ SunDawn ✠Hail Me!01:20, 4 June 2025 (UTC)[reply]
Copying my comment from Village pump (WMF), I believe it is better here:I feel like Simple Article Summaries (SAS) are contrary to a lot of things readers want in an encyclopedia. Readers come to the site trusting that we can give them all the information they want, while (crucially!) substantiating everything we say with sourcing and adhering to NPOV. While other readers could feel differently than I when I decided to join this community, without these two things, Wikipedia would be just another site.I've experimented with using AI on an encyclopedia. I've had it review my writing. I've asked it to write, with the intention to find shortcomings in my own ideas (if I forgot to say something). Just today, I delt with a user who has made over a thousand edits who cited sources that have never existed, at what appears to be the direction of a LLM. There is absolutely no evidence I've seen, either lived or in my line of work at an AI company, which would lead me to believe that an LLM can stick to the facts. Even the output in your survey is fraught with hallucinations.Likewise, using LLMs in my line of work, I've noticed the personality fluctuate in dramatic ways with model updates. I've tried my very hardest to correct it with a custom prompt, instructing it to use prose and maintain a neutral, skeptical perspective, but even this has not worked. There is absolutely no evidence I've seen, either lived or in my line of work at an AI company, which would lead me to believe an LLM can write neutrally. The most obvious example is WP:NOTCENSORED, whereas LLMs very much are.Yes, human editors can introduce reliabilty and NPOV issues. But as a collective mass, it evens out into a beautiful corpus. With Simple Article Summaries, you propose giving one singular editor with known reliabilty and NPOV issues a platform at the very top of any given article, whist giving zero editorial control to others. It reenforces the idea that Wikipedia cannot be relied on, destroying a decade of policy work. It reenforces the belief that unsourced, charged content can be added, because this platforms it. I don't think I would feel comfortable contributing to an encyclopedia like this. No other community has masterered collaboration to such a wonderous extent, and this would throw that away. Scaledish! Talkish? Statish.01:44, 4 June 2025 (UTC)[reply]
Every article on Wikipedia has a WP:LEDE which summarizes the article. We do not need another summary to summarize that summary above the summary. This is a solution looking for a problem. I won't necessarily disagree that some article ledes are overly technical, but the solution to that is to address it among the communities of editors which oversee those articles. Furthermore, if a possible Wikipedia reader is daunted by the language in a lede and is too incurious or thoughtful to try and understand the language presented, they can always use an AI tool on their own time to summarize it. Adding our own AI summary only serves as a barrier to understanding, and is not an improvement in any way. I cannot state strongly enough how much I oppose any implementation of generative AI on Wikipedia. A Cynical Idealist (talk) 02:01, 4 June 2025 (UTC)[reply]
Oh god no. What a horrible way to damage Wikipedia's brand image right when we need to be emphasizing it the most. Think of the signal you'd be sending to everyone on the internet who is currently thinking "at least Wikipedia is still written by humans". -- asilvering (talk) 02:12, 4 June 2025 (UTC)[reply]
Count me as a "yuck". I've been experimenting quite a lot with useful applications of LLMs in my professional work, and naturally also tried some Wikipedia-themed experiments. I've even specifically tried to generate leads for my GAs. The AI-generated leads are terrible and I have never used a word of one! Even if they were of acceptable quality, I agree with others that any use of AI to generate user-visitor content will torpedo Wikipedia's current reputation as the last bastion of actual facts on the internet. Leads are already supposed to provide an accessible, brief overview of the article. If the WMF feels they too rarely achieve that goal, they could fund an editathon with prizes like the World Destubathon. ~ L 🌸 (talk) 02:27, 4 June 2025 (UTC)[reply]
Another crucial consideration: this cannot be treated as "just" a test. Wikipedia will become the "main character" of social media for a day, as a villain. Thousands of people will hear about the feature, not examine it for themselves, conclude that Wikipedia doesn't care about fact-checking any more, and never learn that the test ended. Anything that is implemented as user-facing on English Wikipedia must be treated as a fully complete feature that en-wiki fully endorses. (Also, apologies for so many instances of "staircase wit" -- it just keeps seeming worse the more I think about it.) ~ L 🌸 (talk) 02:46, 4 June 2025 (UTC)[reply]
Going to expand on my early "yuck" a bit, since I'm a bit dumbfounded nobody's brought this up yet. The limiting factor on the English Wikipedia - which is the Foundation's primary revenue source - is the time of good-faith volunteer editors. This is extremely reminiscient of short descriptions: generate simplified summaries of articles by some automated off-wiki process, find out they're inevitably terrible, foist them off on the "infinite supply of volunteers" to fix. This was, I'm not even sure when, sometime before March 2017 at the very least, and we're only now starting to catch up. At least then, someone, somewhere, thought the descriptions would be usable as-is. You don't have that excuse this time, and we're not going to put up with it again. —Cryptic03:14, 4 June 2025 (UTC)[reply]
Gross. If this happens on Wikipedia, I'm done. What makes Wikipedia unique in 2025 is we don't accept unedited AI garbage. If a non-wiki-editable process is responsible for showing content on Wikipedia, you have successfully killed the website. Its "Wiki"pedia for goodness sake. JackFromWisconsin (talk | contribs) 03:34, 4 June 2025 (UTC)[reply]
@JackFromWisconsin, fwiw, they do appear to be planning on allowing editors to edit it. In my opinion, this is even worse, because then they're generating a huge and completely unnecessary cleanup problem for volunteers to handle, but there you are. -- asilvering (talk) 03:36, 4 June 2025 (UTC)[reply]
I saw that on the survey. Just a completely unnecessary use of AI. Our backlogs are log enough as is. We don't need a "check AI summaries" backlog too. If a new gadget were to be developed to show human-made summaries, that'd okay. (But arguably unnecessary, that's what the LEAD is for!) But any moment AI gets involved, it will completely ruin the process. There are only so much volunteer hours. JackFromWisconsin (talk | contribs) 03:40, 4 June 2025 (UTC)[reply]
@JackFromWisconsin Think of the poor multi-billion dollar AI company who now has to pay up to 2 dollars an hour for people to correct the output of their model! They really deserve our help, for free. Polygnotus (talk) 03:42, 4 June 2025 (UTC)[reply]
One of the options on the survey said that these edits might not even be listed (so no edit history). Do we want it to be easer for people vandalize something already likely to be a false AI hallucination? 2007GabrielT (talk) 12:21, 4 June 2025 (UTC)[reply]
I'm curious about what Thryduulf and WhatamIdoing's thoughts are on all this. They've been advocates for AI in past Village Pump discussions, so it'd be interesting to hear from a different perspective. Some1 (talk) 03:54, 4 June 2025 (UTC)[reply]
I don't advocate for AI. I advocate against creating unenforceable policies and guidelines about AI, and I advocate against editors making unproveable accusations that others are wrongly using AI, especially when those people are not native English speakers.
For myself, I'd never enable something like this. In fact, I turn it off at every opportunity. If anyone reading this happens to have a contact at DuckDuckGo, please tell them that I'd like a way to turn off their AI that persists even in a private/incognito window. WhatamIdoing (talk) 04:30, 4 June 2025 (UTC)[reply]
@Some1 just as you did with WAID you have misstated my position: I do not advocate for AI, I advocate against policies and guidelines related to AI that are based on hypoerbole, misinformation and assumptions rather than facts and evidence. I advocate against allowing (let alone encouraging) personal attacks on editors based on unprovable (and frequently incorrect) assumptions.
As for the actual subject of this discussion, the idea of a non-technical ~5 sentence summary of a long article is a good one, iff that summary is always both accurate and neutral. Based on the evidence presented in this discussion, the current implementation of this idea does not consistently meet those requirements. Given that some of our articles are tagged as having disputed accuracy and/or disputed neutrality, I am not sure that it is possible to meet both requirements. Thryduulf (talk) 10:35, 4 June 2025 (UTC)[reply]
While we are on this subject I should thank you for this erstwhile thankless task — lately I have been disturbed by the apparent willingness of many people to just say stuff about this subject, seemingly with no concern whatsoever for whether it is true or false, on the general idea that it owns the libs/cons/bros/sises/etc. jp×g🗯️13:33, 5 June 2025 (UTC)[reply]
I received the invitation to take the survey and was quite displeased when I saw what it was about. I have major concerns regarding the reliability of LLM-generated summaries, the extra workload maintaining their accuracy would create for human editors, and the emissions/environmental impact of LLMs. I don't think any of the potential benefits outweigh the costs here and would urge any WMF staff reading this to reconsider this idea. Ethmostigmus 🌿 (talk | contribs) 04:09, 4 June 2025 (UTC)[reply]
The view of the Wikimedia Foundation on Wikipedia is evident in the framing of this survey. The first two suggestions for adding "simple summaries"—indeed, an obfuscation of the significant role that artificial intelligence wields in this process—suppose that administrators should be responsible for managing simple summaries. At best, that is a dangerously negligent perspective; at worst, it is woefully scornful of a community that has persisted for nearly a quarter century without the idea that administrators should supercede content. What has been proposed is a box that is invisible to many editors who have not opted to use Vector 2022 and which appears to be difficult to edit. elijahpepe@wikipedia (he/him)04:39, 4 June 2025 (UTC)[reply]
Good point, I also found the proposals that admins could be responsible for the AI tasks to be alarming and almost shocking. "Admin effort" is one of our most precious resources, and it shows a real lack of understanding about en-wiki's needs and priorities to propose inventing a new task for admins to deal with, let alone one so spirit-killing as AI cleanup. ~ L 🌸 (talk) 04:55, 4 June 2025 (UTC)[reply]
I just got the survey, responded to it (I hate the idea with a burning passion and made sure to share my opinion in the survey) and immediately searched for the discussion because I knew there'd be one. There are so many problems with this whole idea, and they all boil down to "AI that we as editors of the website can't directly control". Of course, directly controlling an AI to output a specific summary defeats the purpose of using an AI. Also, from MOS:INTRO: The lead section should briefly summarize the most important points covered in an article, in such a way that it can stand on its own as a concise version of the article. So we already have a "simple summary", and it's one that we can directly edit, thus maintaining both the quality of the encyclopedia and the trust those who use Wikipedia have in us. Why do we need a second one? Side note: When I did the survey, the order of responses, which ranged from "Good" on the left to "Bad" on the right for the first few pages, got switched so "Bad" was on the left and "Good" was on the right on the last page. I'm glad I happened to glance (without even really meaning to) at those responses or I wouldn't have even noticed the (accidental?) switcheroo.—Gestrid (talk) 05:44, 4 June 2025 (UTC)[reply]
LLMs are notoriously bad at summarising. Abusing vulnerable people (mobile visitors) as guinea pigs for an experiment which is unlikely to collect any useful information is, at best, rude. The WMF should stick to its better ideas about LLMs, which are about using them for anything but prose generation. For example, instead of presenting a summary of the article as if it were true, you could pick some sentences from the article and quote them verbatim, possibly ask some questions about them. Nemo06:08, 4 June 2025 (UTC)[reply]
'Opppose in the strongest of all possible ways. Are y'all (by that, I mean WMF) trying to kill Wikipedia? Because this is a good step in that way. We're trying to keep AI out of Wikipedia, not have the powers that be force it on us and tell us we like it. - The BushrangerOne ping only06:05, 4 June 2025 (UTC)[reply]
I can't help feeling that what this would create is a duplicate lead that editors would not just have to verify but also moderate and curate. The lead of some articles is the result of potentially long-winded discussion, this risks requiring all that work again. These would also require oversight to ensure they are not targeted by vandals or POV pushers, as they would be highly visible. The leads if many articles should be shorter and less cluttered, but something that would in effect duplicate the lead (and the work required to maintain the lead) doesn't seem like the greatest idea. -- LCU ActivelyDisinterested«@» °∆t°06:21, 4 June 2025 (UTC)[reply]
These kind of discussions are common inside and outside of contentious topic areas. Even seemingly simple articles may have had weeks of discussion on how to correctly summarise the article in the lead. -- LCU ActivelyDisinterested«@» °∆t°10:15, 4 June 2025 (UTC)[reply]
Absolutely not, all of the work that countless people put into these articles being thrown away in favour of LLMs we don't even really understand. Besides that, we have simple for a reason. Weirdguyz (talk) 06:30, 4 June 2025 (UTC)[reply]
Absolutely not This duplicates the existing summary function of our article leads. If readers find that an article lead poorly summarizes its content, that is one of many avenues by which we hope to recruit them into editors improving the content they care about. As HouseBlaster notes, when other LLMs ask for thumbs up/down feedback, they are assessing whether you liked the response, not whether you double-checked its accuracy. To implement that here will train models to reinforce reader preconceptions, rather than accurately summarize our articles. As CMD demonstrates below, even the dopamine example demonstrates hallucinations that will severely diminish our reliability, so even a mobile trial is untenable. ViridianPenguin🐧 (💬) 06:52, 4 June 2025 (UTC)[reply]
Very bad idea. First, LLMs have inherent reliabilty issues (as demonstrated above, the summary in the demo video used to promote the idea is wrong). The effort to correct summaries would need people willing to check the article in detail; it would swallow up editor time that could better be spent on improving article leads. Second, it would do a lot of damage to Wikipedia's brand. On social media, people are praising the existence of WP as something that has not turned into AI slop. Even if AI were only used for small summaries, it would raise suspicions and upset people.OsFish (talk) 07:26, 4 June 2025 (UTC)[reply]
So in a world where Wikipedia is one of the only respected bastions against hallucinated bullshit information by LLMs, our response is to implement them onto the project??? Not a hope in hell. ser!(chat to me - see my edits)07:53, 4 June 2025 (UTC)[reply]
I have my doubts that trying to duplicate Google's work (or "work") or the efforts editors writing leads engage in is worthwhile. Having AIs that can read an article and write a WP:LEAD compliant lead would be something actually useful, as it can be fairly difficult for people. Or AIs that you feed sources to and write or expand articles with them, that would be even better. One should avoid the tendency to develop AIs in imitation/inspiration of existing efforts, because chances are you are duplicating existing work/reinventing the wheel for no good reason. Jo-Jo Eumerus (talk) 08:34, 4 June 2025 (UTC)[reply]
In my opinion, this would be a gross overstep of the bounds we typically expect the Foundation to adhere to. We are not paid, obviously, but if this is implemented over the objection of the community, the Foundation would effectively be signalling intent for Wikipedia to become one more publication that has fired their editors, in part or in whole, in order to put out AI slop. Alpha3031 (t • c) 10:49, 4 June 2025 (UTC)[reply]
Oppose - the lead exists for a reason. AI summaries are extremely unreliable (as this thread constantly mentions), and it would ruin Wikipedia's reliability. VERIFIABILITY is one of our core policies - AI just hallucinates, leaves stuff out, and makes shit up. This is proof that the WMF does not care about the community of volunteers that work this website. PhoenixCaelestis (Talk · Contributions) 11:25, 4 June 2025 (UTC)[reply]
Strong oppose, including the trial. This is utter disrespect to both readers and editors, and dangerous to the point where we risk losing plenty of both. AI generated stuff is not only inaccurate and unreliable, it is also cheap and therefore almost worthless (since you can get it everywhere nowadays). Even the trial is highly problematic as it sends the wrong signal to the users (namely that Wikipedia became enshittified), and can therefore irreversibly damage Wikipedia's reputation. Let's keep Wikipedia AI-free – that's a strength, not a weakness. --Jens Lallensack (talk) 11:37, 4 June 2025 (UTC)[reply]
Oppose - Making AI generated summaries is exactly none of our business. Google are already on top of that with their AI Overview nonsense -- let's leave that stuff to them. DJ-Aomand (talk) 11:55, 4 June 2025 (UTC)[reply]
I don't understand the point. A piece of text is generated, which in best-case scenarios is duplicating already existing text, then editors review it and edit for quality? If they're going to be manually edited afterwards anyway, what's the purpose of automatically generating them? 207.11.240.2 (talk) 12:22, 4 June 2025 (UTC)[reply]
I'm very uncomfortable with both this proposal and with the direction of travel it suggests. This is either going to wastefully duplicate what's already there, or require scarce editor time to fix it up. Even if this is not affecting the underlying article content, it is generative AI material being presented to a reader under our name, and that is a line we should not cross. Andrew Gray (talk) 12:53, 4 June 2025 (UTC)[reply]
Oppose any movement towards the integration of generative AI on Wikipedia. This is a volunteer project based on community effort, always has been. We're the last best place on the internet because we're built on love, not automation. Don't ruin our reputation by falling victim to the craze for dumbing down everything to the lowest possible attention span - and then add insult to injury by doing it with generative AI. ♠PMC♠ (talk)14:02, 4 June 2025 (UTC)[reply]
Volunteers have spent tremendous amounts of time both crafting the lead sections of articles, and trying to keep chatbot-generated junk out of articles in general. Now, here's this proposal, to flip a middle finger at both efforts, and say "Hey, we'll put some chatbot-generated junk above the actual leads the volunteers worked so hard on building consensus for!". I do not believe I have the words to express how disgusted I am at this proposal. SeraphimbladeTalk to me14:07, 4 June 2025 (UTC)[reply]
Very strongly opposed to this. LLMs are nothing but unethical, mindless plagiarism-machines built with the stolen work of actual humans. Keep this techbro bubble out of Wikipedia. -- kazerniel (talk | contribs) 15:31, 4 June 2025 (UTC)[reply]
What the hell? No, absolutely not. Not in any form or shape. Not on any device. Not on any version. I don't even know where to begin with everything that is wrong with this mindless PR hype stunt. — HELLKNOWZ∣TALK15:59, 4 June 2025 (UTC)[reply]
No, no, no This will destroy whatever reputation for accuracy we currently have. People aren't going to read past the AI fluff to see what we really meant. --SarekOfVulcan (talk)17:14, 4 June 2025 (UTC)[reply]
Validation issues An experiment seems reasonable as our articles can often seem inpenetrable. And it's good to develop expertise and experience with AI tech as it is becoming omnipresent. But the idea of human validation may be difficult. One issue is that our articles may change frequently and so the summary and validation would need to be redone frequently too. Another issue is that every page has a disclaimer saying that our content is not guaranteed to be valid and so an assertion of validity would be sending a mixed message. Andrew🐉(talk) 18:17, 4 June 2025 (UTC)[reply]
To say publicly what I wrote in the survey: from a structural standpoint, an AI-generated summary seems pointless. The one paragraph summary of the article is the lead paragraph. The multi-paragraph summary is the entire lead. If AI can write a better one-paragraph summary than the lead paragraph, then that paragraph should just be the lead paragraph. Why have two summaries at the top of an article, especially if one is worse than the other?
A better deployment for AI here would be to have AI write a summary of the article and then compare its summary to the existing lead, and post the differences/analysis on the article's talk page, essentially an AI edit suggestion. Human editors can then review the suggestion and implement it (or not) as appropriate. AI could do this not just for the lead but for entire articles. Of course, this hinges on an AI that has sufficient accuracy to the point where it's suggestions are actually useful.
A next-level deployment would be for AI to read the sources of the article, summarize those, and then compare its summary to the written article, and post suggestions for changes on the talk page.
A next-next-level deployment would be for AI to suggest new sources for the articles, or to read and summarize sources that aren't in the article, and then post edit suggestions to the talk page. AFAIK AI isn't ready for this level yet, but the first two suggestions above could probably be done today with reasonable accuracy using large and small language models.
+1. AI that helps editors address problems with Wikipedia is welcome (if it works). We already use it, in various places, to varying degrees of success, and to relatively little pushback. -- asilvering (talk) 19:25, 4 June 2025 (UTC)[reply]
I would not be in support of large AI-suggested edits. To properly evaluate what an AI writes takes a lot of brainpower. In my opinion it takes the same or more brainpower as just reading the sources/article yourself and writing it without AI. I think an AI that posts suggested edits on talk pages would just distract editors or get ignored, and reminds me of Microsoft trying to have AI write patches and post them on GitHub. There is a thread on Reddit called "My new hobby: watching AI slowly drive Microsoft employees insane" making fun of how terrible AI has been at writing software patches (7,000 upvotes in r/ExperiencedDevs). It would be sad if Wikipedia got into a similar situation. –Novem Linguae (talk) 20:08, 4 June 2025 (UTC)[reply]
I think Of course, this hinges on an AI that has sufficient accuracy to the point where it's suggestions are actually useful. covers that already. That's a big ask. -- asilvering (talk) 20:13, 4 June 2025 (UTC)[reply]
The problem is that many people do think that LLM is useful and it can be good for certain low-hanging fruit but it can also be dangerously wrong with no way to know. Andre🚐21:42, 4 June 2025 (UTC)[reply]
Why does the WMF development process engage with the community after development?
Can you confirm that this has no links to Knowledge/Google? The Google AI summary is receiving criticism because the summaries are poor. By having editors check the output then that accuracy could increase. To improve this and other LLMs, AI companies are paying people to provide feedback. The concern would be that we are doing work for Alphabet
Would it reduce people clicking through to Wikipedia, and a small percentage becoming editors?
How many articles are we talking about? Is this only in en? The concern is how much editor time would be needed.
Concern is whether it a good time with the DC attorney general issue. Even if he is not approved, then the next one will ask the same questions
WMF has been concerned that enWP editor's white male and American. As LLMs have a cultural bias do you see this as increasing WMF's perception of a white male American bias? My big concern is that it takes the fun part out of editing, and creates a Readers Digest Condensed book of the lede , which is our summary of the article, which is a summary of others peoples summaries. But if there was an editor toolbar that allowed editors to create a lede as part of their process, or to use the AI in an integrated way (create a table based on these paragraphs), or to check a page for errors, then you might get traction
it takes the fun part out of editing. Indeed, and not only that: having to correct the output of an AI that makes the same mistakes again and again may be the quickest way to burnout. Yes, the most important thing, in the end, is to have fun. It's not about maximising clicks, which is what the WMF seems to be interested in. If it were, much more of us would spend much more time on core content rather than our highly specialised pet topics. Introducing AI to Wikipedia looks like an attempt to "optimise" us or our work to get more clicks – even though that's not even the principal goal for most of us personally. Interacting with AI is quite the antithesis of "having fun". I am here because I want to collaborate with humans to build something great together, and to help others becoming better writers. That is meaningful to me and makes it worthwhile – interacting with AIs is just not. --Jens Lallensack (talk) 17:30, 7 June 2025 (UTC)[reply]
Well, it's easy enough to test, so I asked AI to summarize a Wikipedia article in one paragraph and then to compare its summary with Wikipedia's summary, and to tell me the differences between the two summaries. I did this for Today's Feature Article, 1880 Republican National Convention, using the TFA blurb as the example of Wikipedia's one-paragraph summary (although one could just as easily use the lead paragraph, or entire lead). I figure TFA is a good proxy for top-quality one-paragraph article summary written by Wikipedia volunteers. I asked ChatGPT and Gemini to "summarize https://en.wikipedia.org/wiki/1880_Republican_National_Convention in one paragraph", and then to "compare these two paragraphs and tell me what's different between them". Here are their responses:
TFA one-paragraph summary
The 1880 Republican National Convention (June 2 to 8, 1880, Chicago) resulted in the nominations of James A. Garfield of Ohio and Chester A. Arthur of New York as the Republican Party candidates for U.S. president and vice president. Leaders in the early balloting at the convention, which deadlocked for several days, were former president Ulysses S. Grant, Senator James G. Blaine of Maine, and John Sherman, the treasury secretary. After the 35th ballot, Blaine and Sherman switched their support to a new "dark horse", Garfield, a congressman from Ohio, who had nominated Sherman. On the 36th ballot, Garfield won the nomination. After Arthur won the vice presidential nomination on the first ballot, the longest-ever Republican National Convention adjourned. The Garfield–Arthur Republican ticket narrowly defeated Democrats Winfield Scott Hancock and William H. English in the 1880 presidential election.
ChatGPT's one-paragraph summary
The 1880 Republican National Convention, held from June 2 to 8 in Chicago, was marked by intense factionalism and a prolonged deadlock. The leading contenders were former President Ulysses S. Grant, backed by the Stalwart faction favoring patronage; Senator James G. Blaine, supported by the Half-Breeds advocating civil service reform; and Treasury Secretary John Sherman, representing a more moderate stance. After 35 ballots failed to produce a nominee, a compromise emerged when Blaine and Sherman shifted their support to James A. Garfield, a congressman from Ohio not initially in the running. Garfield secured the nomination on the 36th ballot. To balance the ticket and appease the Stalwarts, Chester A. Arthur of New York was nominated for vice president. The Garfield-Arthur ticket narrowly defeated Democrats Winfield Scott Hancock and William Hayden English in the 1880 presidential election. Tragically, Garfield was assassinated in 1881, leading to Arthur's succession to the presidency.
ChatGPT's comparison of its summary ("Paragraph 1") with the TFA blurb ("Paragraph 2")
Here are the key differences between the two paragraphs:
Tone and Style:
Paragraph 1 is more narrative and descriptive, using phrases like “marked by intense factionalism” and “a compromise emerged.”
Paragraph 2 is more concise and encyclopedic, structured more like a historical summary.
Emphasis on Factions:
Paragraph 1 details the factions backing each candidate (Stalwarts, Half-Breeds, etc.).
Paragraph 2 omits faction names and focuses on the individuals.
Garfield’s Role:
Paragraph 1 mentions Garfield was “not initially in the running.”
Paragraph 2 notes Garfield “had nominated Sherman,” subtly emphasizing his presence at the convention before his surprise nomination.
Vice Presidential Nomination:
Paragraph 1 explains Arthur’s nomination as a move to “appease the Stalwarts.”
Paragraph 2 simply states Arthur won on the first ballot, omitting strategic context.
Convention Description:
Paragraph 1 highlights the prolonged deadlock with rich detail.
Paragraph 2 mentions it was the “longest-ever Republican National Convention” but without elaboration.
Garfield’s Assassination:
Paragraph 1 includes it and its consequence (Arthur’s presidency).
Paragraph 2 omits it entirely.
In summary, Paragraph 1 is more detailed and interpretive; Paragraph 2 is more formal and fact-focused.
Gemini's one-paragraph summary
The 1880 Republican National Convention, held in Chicago, Illinois from June 2 to June 8, 1880, saw the nomination of James A. Garfield of Ohio for president and Chester A. Arthur of New York for vice president. Despite Ulysses S. Grant, James G. Blaine, and John Sherman being strong contenders, Garfield ultimately secured the nomination after multiple ballots, with Arthur as his running mate. The Garfield–Arthur ticket went on to narrowly win the 1880 presidential election against Democrats Winfield Scott Hancock and William Hayden English.
Gemini's comparison of its summary ("Paragraph 1") with the TFA blurb ("Paragraph 2")
The two paragraphs describe the 1880 Republican National Convention, but Paragraph 2 provides more specific details and additional information compared to Paragraph 1.
Here are the key differences:
Format of Dates and Location: Paragraph 1 states "held in Chicago, Illinois from June 2 to June 8, 1880," while Paragraph 2 uses a more concise parenthetical format: "(June 2 to 8, 1880, Chicago)".
Detailed Nomination Process:
Paragraph 1 generally states, "Garfield ultimately secured the nomination after multiple ballots, with Arthur as his running mate."
Paragraph 2 offers much more detail, mentioning "Leaders in the early balloting at the convention, which deadlocked for several days," and specifies the "35th ballot," how "Blaine and Sherman switched their support to a new 'dark horse', Garfield," and that Garfield "had nominated Sherman." It also mentions "On the 36th ballot, Garfield won the nomination."
Arthur's Vice Presidential Nomination:
Paragraph 1 briefly notes "with Arthur as his running mate."
Paragraph 2 adds that "After Arthur won the vice presidential nomination on the first ballot."
Convention Duration/Length: Paragraph 2 explicitly states that "the longest-ever Republican National Convention adjourned," a detail not present in Paragraph 1.
Full Name of Democratic Vice Presidential Candidate: Paragraph 1 refers to "William Hayden English," while Paragraph 2 shortens it to "William H. English."
Helpful? I think so. It would probably be better if the prompt were improved to instruct it write an encyclopedia-style summary, or even a Wikipedia-style lead. Novem's probably right that posting these on talk pages, particularly in volume, could be overwhelming, but it would be easy to create a toolforge-hosted python script that uses the AI APIs to perform these two steps for any given article, and thus generate "AI suggestions for improvement" on-demand for any given article... as long as somebody pays the API credits. But WMF has hundreds of millions of dollars and could afford to foot that bill, at least up to some reasonable cap. Levivich (talk) 21:51, 4 June 2025 (UTC)[reply]
If we're just going to ask the AI to write in the style of a Wikipedia lead, what's the use in having the AI? Wikipedia-style leads are already present.The Morrison Man (talk) 22:05, 4 June 2025 (UTC)[reply]
@The Morrison Man: The use of the AI is that the AI may have good suggestions for improvement. For example, ChatGPT's comparison above identifies the following possibilities for improving the TFA blurb:
name the factions backing each candidate (Stalwarts, Half-Breeds, etc.)
explicitly state that Garfield was not initially in the running
explicitly state that Arthur's nomination was a move to appease the Stalwarts
mention that Garfield was assassinated the following year, making Arthur president
Editors can debate whether any of these changes are, in fact, improvements to the TFA blurb, but it seems to me to be a pretty helpful list of things to consider when thinking about how to improve the TFA blurb. And it took less than one minute -- way less time than it would have taken me to read the article and the TFA blurb and figure out suggestions for improvement. That's what AI can do, today. Levivich (talk) 22:26, 4 June 2025 (UTC)[reply]
Well first, that's flat not true. The lead doesn't have the third or fourth bullet points. Second, none of it is in the lead paragraph. Third, duh, reading the 4-paragraph lead would give more info than the 1-paragraph TFA blurb, and reading the article would certainly have all that info, but this demonstration is about improving the 1-paragraph TFA blurb, so pointing out that some of this info is in the lead isn't really relevant. Levivich (talk) 22:39, 4 June 2025 (UTC)[reply]
I also tested it with a few articles I know well, and if asked to keep the summary short it generally did well. Longer "summaries" meant more hallucinations, though. Cremastra (u — c) 21:55, 4 June 2025 (UTC)[reply]
An informal test does not prove the absence of hallucinations. They are insidious and they may appear in unpredictable places. Andre🚐22:40, 4 June 2025 (UTC)[reply]
This is a bad idea. While AI generated summaries of Wikipedia content are potentially useful and, given our free licensing, ultimately inevitable, there is no reason for the Foundation to be generating or hosting them. The primary role of the Foundation should be assisting volunteers in the creation and curation of content. Since it's free delivery in digestible packets mostly takes care of itself. Eluchil404 (talk) 00:05, 5 June 2025 (UTC)[reply]
I see below that the WMF has already decided to pause the idea. However, I really think it should just be scrapped altogether rather than "reformatted", and I believe that any attempts by the WMF to push through with it in any capacity, despite community opposition, will not end well. Generative AI is already very fond of hallucinating, even when trained on proper data, and promoting technology that encourages such things would only hurt the project's reputation. I get the idea, I understand that there are good intentions behind it, and I do think that AI has its use cases (not on-wiki though). But now is not the right time, and until AI gets past its hallucinations, I don't think it ever will. Narutolovehinata5 (talk · contributions) 01:59, 5 June 2025 (UTC)[reply]
? A question about accessibility. When I watched the demo video, it looks like the default position for the "simple summary" was collapsed. For our visually impaired readers and editors who use screen readers to access Wikipedia, would this summary be available to them/us. Because in order to view and/or hear the summary, it requires interaction (clicking on it to open it), which obviously screen readers are not capable of. And per our guidelines at MOS:COLLAPSE, content in an article (if this summary is to be considered content), should never be collapsed by default. So how would this feature be beneficial to our visually impaired readers/editors if it is not accessible? We have alternative text for images, so has there been any consideration given by the develpers for alt text for this feature if it is to remained collapsed by default?Isaidnoway(talk)07:47, 5 June 2025 (UTC)[reply]
As is the survey, but I would still like to hear their response. Wikipedia already has enough problems with accessibility issues, so adding another one is not ideal.Isaidnoway(talk)08:39, 5 June 2025 (UTC)[reply]
@Isaidnoway Regarding your first question. Screen readers are capable of interacting with collapsed interface elements, as long as it's implemented correctly, e.g. that button elements are marked as interactive and respond to keyboard actions and not just mouse clicks. For example, if you're using the "Reply" button to reply in this conversation, the reply tool has an "Advanced" button following the comment box, which should be fully compatible with your screen reader, and which should reveal some additional options when used. In MediaWiki development we use libraries called Codex and OOUI, which make this easy to do or even do it automatically, so I would expect any new features to be accessible by default. Matma Rextalk15:35, 5 June 2025 (UTC)[reply]
I think this would be a quite bad idea for a first step towards integrating a new technology — especially one that many people passionately hate (whether for intelligent reasons or nonsensical/false/superstitious ones). Essentially, the pitch here is the lead: essentially to supplant the single most important, visible, sensitive and contentious part of the entire article! Surely, if a surgeon comes up with a new parkour move, you don't want them trying it out for the first time on your aorta. Can't we, like, try this on something that doesn't instantly kill us in the event of an error? jp×g🗯️13:16, 5 June 2025 (UTC)[reply]
No. Just no. – Every reason why this would be a catastrophic decision has already been said above, based on the fact that it is just a conceptually terrible idea. We need help from the WMF regarding LLM-generated content, but to fight it back, not to include it in the most prominent spot of every article. Choucas0 🐦⬛⋅💬⋅📋08:37, 6 June 2025 (UTC)[reply]
Strong oppose. AI-generated content does not have any place in articlespace and I am coming around to the idea that it doesn't have any place in project discussions either. LLMs are not reliable sources, and so this is as clear a WP:5P2 violation as it gets. It is also very likely to plant a seed for legal questions (is this going to be on BLPs? edit 6/7 -- articles on BLPs seem to have been filtered out, but not articles that contain statements about them) and almost certain to result in immediate and massive public backlash when the media gets wind of it. I also have reservations about the experiment from which this terrible idea sprung. This is based on the opinion of eight (8) people. Are those eight people in the room with us right now? There seems to be a strong and near-unanimous consensus against this from far more than eight people. It seems to also be based on this presentation at Wikimania 2024, the quality of which is unclear because no one bothered to upload the slides despite it being almost a year. Gnomingstuff (talk) 17:56, 6 June 2025 (UTC)[reply]
Hey everyone! This is Olga, the product manager who is working on the summary feature at WMF. I just wanted to let you all know that we’re following the conversation here closely and will be getting back to you with some thoughts and next steps we can discuss later today. OVasileva (WMF) (talk) 07:37, 4 June 2025 (UTC)[reply]
Please abandon this idea, Olga. The community doesn't want to integrate AI into Wikipedia, and in future our AI-skepticism will become an ethical anchor for everything we do -- and also a major selling point for Wikipedia.—S MarshallT/C07:35, 5 June 2025 (UTC)[reply]
Dopamine is a neurotransmitter, a chemical messenger that carries signals between brain cells. It plays a vital role in several brain functions, including emotion, motivation, and movement. When we experience something enjoyable or receive a reward, our brain releases dopamine, creating a sense of pleasure and reinforcement. This neurotransmitter also helps us focus and stay motivated by influencing our behavior and thoughts. Dopamine imbalance has been associated with various disorders, such as depression and Parkinson's disease, highlighting its importance in maintaining overall brain health and function.
The first sentence is in the article. However, the second sentence mentions "emotion", a word that while in a couple of reference titles isn't in the article at all. The third sentence says "creating a sense of pleasure", but the article says "In popular culture and media, dopamine is often portrayed as the main chemical of pleasure, but the current opinion in pharmacology is that dopamine instead confers motivational salience", a contradiction. "This neurotransmitter also helps us focus and stay motivated by influencing our behavior and thoughts". Where is this even from? Focus isn't mentioned in the article at all, nor is influencing thoughts. As for the final sentence, depression is mentioned a single time in the article in what is almost an extended aside, and any summary would surely have picked some of the examples of disorders prominent enough to be actually in the lead.
So that's one of five sentences supported by the article. Perhaps the AI is hallucinating, or perhaps it's drawing from other sources like any widespread llm. What it definitely doesn't seem to be doing is taking existing article text and simplifying it. CMD (talk) 18:43, 3 June 2025 (UTC)[reply]
As someone who has tested a lot of AI models; no AI technology that is currently available to the public is reliably able to make an accurate summary of a complicated article. We may get there at some point, but we aren't there yet. Polygnotus (talk) 18:47, 3 June 2025 (UTC)[reply]
CMD makes some good points but maybe the WMF is not using a good AI. I tried asking Gemini 2.5 Pro to summarise the article "in one paragraph using English suitable for a general readership." The result was as follows:
Dopamine is a chemical messenger that plays several vital roles in the body. In the brain, it acts as a neurotransmitter, sending signals between nerve cells, and is particularly known for its role in the brain's reward system, with levels increasing in anticipation of rewards. Many addictive drugs affect dopamine pathways. Beyond the brain, dopamine also functions as a local messenger. Imbalances in the dopamine system are linked to several significant nervous system diseases, such as Parkinson's disease and schizophrenia, and many medications for these conditions work by influencing dopamine's effects.
This seems a reasonable summary as all the points it makes appear in the article's lead and so there's no hallucination. Note that Gemini lists its sources and it only lists the Wikipedia article so it presumably was just working from that. The language is still not easy as you have to understand concepts like "pathways" but it seems reasonably free of the technical jargon which makes the article's lead quite difficult. Andrew🐉(talk) 18:39, 4 June 2025 (UTC)[reply]
@Andrew Davidson Yeah but now do it a thousand times. Or ten thousand. The hallucinations will creep in. Note that Gemini lists its sources and it only lists the Wikipedia article so it presumably was just working from that. That is not how that works. The language is still not easy as you have to understand concepts like "pathways" but it seems reasonably free of the technical jargon which makes the article's lead quite difficult. If the problem is that the leads of the articles are difficult to understand, one solution could be direct people to simple.wiki. Another idea is to set up a taskforce/wikiproject whatever. Another idea is to use available Readability-tools (via some API):
Average Reading Level Consensus
Automated Readability Index
Flesch Reading Ease
Gunning Fog Index
Flesch-Kincaid Grade Level
Coleman-Liau Readability Index
SMOG Index
Original Linsear Write Formula
Linsear Write Grade Level Formula
FORCAST Readability Formula
Combine that with the pageview data (pageviews.wmcloud or the dump) and then check which are the hardest and try to improve those. There are thousands of ways to deal with this perceived problem ethically and uncontroversially. Polygnotus (talk) 18:51, 4 June 2025 (UTC)[reply]
Running things ten thousand times would be a significant experiment and that's what the WMF are proposing. The results are unlikely to be perfect but the starting point here is that the current human-generated article leads are far from perfect. It would be good to gather statistics on just how bad the current situation is using readability tools and other consistency checks. We'd then have a baseline for assessing potential improvements. Andrew🐉(talk) 20:09, 4 June 2025 (UTC)[reply]
maybe the WMF is not using a good AI I share this concern as well. The WMF is using Aya, and while I understand the choice of using an open-source multilingual LLM, I question whether Aya's accuracy is good enough, and whether it's better than ChatGPT, Gemini, or other LLMs. If the accuracy is worse, why would we use it? Why we re-create what is already available? The only way this makes sense is if the LLM used produced a better summary than what Google is already showing users with Gemini. I question whether any LLM on the market today has sufficient accuracy. Levivich (talk) 19:09, 4 June 2025 (UTC)[reply]
I question whether any LLM on the market today has sufficient accuracy. No need to question that, there is no sufficiently accurate AI for this task. Polygnotus (talk) 19:13, 4 June 2025 (UTC)[reply]
maybe the WMF is not using a good AI is not really the problem with hallucination. LLMs are inherently stochastic and will hallucinate sometimes if you run the model enough times. Just because you got better results with a test run of one model doesn't imply you'll always get that. Dan Leonard (talk • contribs)19:16, 4 June 2025 (UTC)[reply]
I don’t like that it’s not in wikivoice, either. Or that it’s loaded with AI words to watch. Seriously disheartening, and disrespects all of the amazing work that AICLEAN users have been doing to keep these issues out of articles. This is exactly the kind of text we are searching for to remove.
How do we clean this? Do we need to plan ahead with templates like, “the above AI summary contains the following errors”? What if these summaries appear on top of meticulously planned CTOP leads like Donald Trump, which are built on dozens of established and coded consensuses, down to the precise words chosen? 3df (talk) 01:15, 4 June 2025 (UTC)[reply]
I had to draftify a pretty ridiculous percentage of new articles as AI-generated articles during the recent WP:NPP backlog drive. To have this now shoved onto Wikipedia anyway is incredibly disheartening, and if it went through, I'd genuinely consider quitting editing altogether. 🌸wasianpower🌸 (talk • contribs) 04:18, 4 June 2025 (UTC)[reply]
I had the opportunity to see a generated summary for the dopamine article, shown by another editor since I am not part of the roll-out myself. It was not quite the same, but equally if not even more dreadful to read. The very first words called it a "special molecule" and I almost lost it then and there. Let's put and end to this madness early. Choucas0 🐦⬛⋅💬⋅📋09:00, 6 June 2025 (UTC)[reply]
Dopamine is a special chemical in our bodies, like a messenger between brain cells. It's mostly known for making us feel good when we do something fun, but it's also about motivation and wanting rewards. It helps us move, focus, and even controls some hormones.
In the brain, dopamine is like a traffic light, directing how cells communicate. When we expect something good, dopamine levels rise. Drugs that affect dopamine can change how we feel and act, which is why some are used to treat health issues like Parkinson's disease or ADHD.
A two-week experiment on the mobile website seems to be the most immediate hazard; such an experiment would harm readers and negatively affect our reputation as a fairly reliable, non-AI source of information. Instead of freaking out, we should come up with some plan to persuade the WMF that this not a good idea and to stop them from rolling this out at any level.
Should the Wikipedia community do something to prevent or protest this "experiment", and if yes, what can/should we do? Cremastra (u — c) 21:25, 3 June 2025 (UTC)[reply]
@Cremastra We should blast this survey link to everyone and anyone, and have them fill it out. Start an RFC with it. Spread it on Discord and IRC and post it on Village Pumps et cetera.
I already filled out the survey through the usual method. People are welcome to fill out the survey but I don't think we should submit multiple responses each. Something like an open letter to the WMF would be more effective than screwing around with their data. Also, if in reality the survey is an overwhelming "no", intentionally skewing the results would compromise their legitimacy. Cremastra (u — c) 21:30, 3 June 2025 (UTC)[reply]
@Cremastra The legitimacy the survey had was already zero, because they are intentionally choosing not to actually ask the community about it. Because we don't use surveys on Wikipedia, we use talkpages and RfCs and Village Pump discussions and the like. So the fact that they are intentionally evading our consensus building mechanisms makes that survey null and void already. Polygnotus (talk) 21:33, 3 June 2025 (UTC)[reply]
@Scaledish No, the survey results are hidden. So unless you hack their account or the Qualtrics database you have to trust them when they report the results. But the fact that they use an external survey service instead of the normal ways to get consensus on Wikipedia, and that I had to search through their JavaScript to find the link, shows that they did not want us to voice an opinion and did not want me to share this link... Polygnotus (talk) 02:00, 4 June 2025 (UTC)[reply]
@Polygnotus Thank you for finding the link. I tried for a good 10 minutes to be presented with the survey that is being given to editors and I was never given it. A/Bing that survey is gross. Scaledish! Talkish? Statish.02:02, 4 June 2025 (UTC)[reply]
@Scaledish Yeah if this survey was above board and an honest way to gauge consensus, why hide the link? Why not invite everyone to voice their opinion? I am no conspiracy theorist, but this seems fishy. Polygnotus (talk) 02:06, 4 June 2025 (UTC)[reply]
I mean, there's nothing wrong with that policy-wise, if they did actually insist on it, but it might be a tad extreme. Cremastra (u — c) 21:37, 3 June 2025 (UTC)[reply]
If some random user implemented this – adding an AI summary to every article – after this discussion made it clear there was no consensus to do that, that user would be cbanned even if the summaries were accurate. 3df (talk) 23:27, 3 June 2025 (UTC)[reply]
In the world of community-WMF squabbling, our standard playbook includes an open letter (e.g. WP:OPENLETTER2024), an RfC with community consensus against whatever the WMF wants to do (e.g. WP:FR2022RFC) or in theory some kind of drastic protest like a unilateral blackout (proposed in 2024) or an editor strike. My preference in this case is an RfC to stop the silliness. If the WMF then explicitly overrides what is very clear community consensus, we're in new territory, but I think they're unlikely to go that far. Cremastra (u — c) 21:36, 3 June 2025 (UTC)[reply]
@Cremastra Maybe you can start an RfC on a very visible place? Something like:
The WMF has started a survey to ask if we want to put an AI summary in every article's lead section.
I took the survey. Its questions are confusing, and watch out for the last question: the good-bad, agree-disagree direction for the response buttons is REVERSED. Sloppy survey design. – Jonesey95 (talk) 21:40, 3 June 2025 (UTC)[reply]
I just hit this survey in the wild so to speak, so I did fill it out due to seeing it there. That last question switcheroo totally threw me, I don't think those results will be usable. CMD (talk) 02:54, 4 June 2025 (UTC)[reply]
I noticed that too. I'm not convinced it wasn't on purpose. In any case, I wouldn't trust the results of that last part. DJ-Aomand (talk) 11:39, 4 June 2025 (UTC)[reply]
As I said at the top, I think our immediate concern should be the actual proposed experimentation, not the survey.
I was thinking something along the lines of
The WMF has proposed testing AI-generated summaries appended in front of article leads (example). Does the community approve of this use of AI, or is this inappropriate and contrary to Wikipedia's mission? Cremastra (u — c) 21:42, 3 June 2025 (UTC)[reply]
They will use the survey as a weapon and pretend it gives them free reign to do whatever they want. A lot of people here will simply leave the second they see such an implementation of AI on a Wikipedia page, because that goes against everything we stand for. Getting those people back will be near impossible. Polygnotus (talk) 21:44, 3 June 2025 (UTC)[reply]
If the WMF feels like acting with impunity, they'll do so. There has been little to no response from the WMF on this page, which suggests to me they're just going to roll ahead with their fingers in their ears. Which as thebiguglyalien points out above, may remind you of a certain guideline. Cremastra (u — c) 21:46, 3 June 2025 (UTC)[reply]
I am certain @EBlackorby-WMF: is not doing this because they are evil, I honestly believe these are goodfaith people who do not understand what they are saying, and what the consequences of their words are.
If I say things like They are proposing giving the most important screen real estate we have (the WP:LEAD) of every article to a for-profit company. they haven't looked at it that way, because that is not how they think.
I do not think they should be banned/blocked, I think they should be educated. But we must stop them from doing more damage, one way or the other. Polygnotus (talk) 21:51, 3 June 2025 (UTC)[reply]
No one here thinks the WMF or any of their employees are "evil"; that is a ludicrous word to be using. If the WMF would respond to the feedback on this page (which is overwhelmingly against the proposal), it would reasssure me and many others. The present state of silence is what worries me. Cremastra (u — c) 21:53, 3 June 2025 (UTC)[reply]
Yes, some people here honestly think the WMF is evil. Seriously. I even had to defend them in the context of the ANI vs WMF courtcase thing. They were falsely accusing the WMF of throwing those editors under the bus and abandoning them. Complete nonsense of course. But yeah some people do harbor an irrational hatred against the WMF. Polygnotus (talk) 21:56, 3 June 2025 (UTC)[reply]
Y'all, please take a look at Special:Log/newusers/EBlackorby-WMF and do the math. She's been around for three (3) weeks. She very likely has no input into the design of any of this. You could make her job easier by just filling out the survey and encouraging everyone else to do the same.
That said, we need to keep in mind that "what readers think" and "what readers want" has very little overlap with what editors want. For example: We write complex texts that take half an hour or more to read; readers usually spend less than 10 seconds on the page. We provide dozens or even hundreds of inline citations; readers don't click on any of them for 299 out of 300 page views, and on the 1/300th case, they only click through to one (1) source. We usually have zero or one images in an article; readers would like a dozen or more. We (well, some of us) worry about Wikipedia's reputation; a surprising percentage of readers don't actually remember that they're reading Wikipedia. In other words, it's entirely possible that many readers would be completely happy with this, even though the core community will hate it. WhatamIdoing (talk) 04:41, 4 June 2025 (UTC)[reply]
@WhatamIdoingYou could make her job easier by just filling out the survey and encouraging everyone else to do the same. If they wanted us to fill in the survey, why didn't they post the link?
it's entirely possible that many readers would be completely happy with this Good news for them, most search engines already include AI fluff that you explicitly have to opt-out of, so they can get their AI hallucination fix on any topic faster (and more conveniently) than they can reach Wikipedia. Polygnotus (talk) 04:45, 4 June 2025 (UTC)[reply]
And perhaps one based solely on the Wikipedia article, instead of Wikipedia plus who knows what else, would actually be an improvement for these readers. It doesn't interest me, but I'm not going to tell other people what they're allowed to read. WhatamIdoing (talk) 05:00, 4 June 2025 (UTC)[reply]
@Polygnotus, Matma said it nicely earlier. Let me say it a little less nicely: Tone it down, now. You are being needlessly antagonistic and on top of that bludgeoning this discussion. Find something else to do for a while. Izno (talk) 21:55, 3 June 2025 (UTC)[reply]
I was under the impression that discussion was broader and of the type that spends three months hammering out a wording. This is focused on a quick response to a specific issue. Cremastra (u — c) 21:43, 3 June 2025 (UTC)[reply]
Yes, I agree that's the impression, but I don't think that you can demonstrate consensus to do anything about this discussion without showing consensus in that discussion, without your own separate RFC. Izno (talk) 21:57, 3 June 2025 (UTC)[reply]
Even though (as mentioned above) that discussion is about AI development as a whole, a few WMF employees actually discuss Simple Summaries in a bit of detail over there, so it may be worth reading through. —Gestrid (talk) 06:26, 4 June 2025 (UTC)[reply]
If we can't, we will have to add a note that is displayed on every single article that tells readers to ignore the summary (and perhaps hide that note on desktop). —Kusma (talk) 10:58, 4 June 2025 (UTC)[reply]
I am just about the least qualified editor here, but I'd think spreading the survey and participating in the current AI development RfC should come before anything drastic. ⫷doozy (talk▮contribs)⫸21:52, 3 June 2025 (UTC)[reply]
I suggest starting an RfC at the VPProposals page with a simple question ("Should English Wikipedia articles offer AI-generated summaries?" or something like that) and a link to the mediawikiwiki:Reading/Web/Content Discovery Experiments/Simple Article Summaries project page. Keep it simple. I predict that 99% of the users will !vote to oppose the feature, but at least with an RfC, the WMF will know where the "community" stands on this specific project. Some1 (talk) 22:49, 3 June 2025 (UTC)[reply]
Interface administrators have access to gadgets, user scripts, and sitewide JavaScript and CSS, not extension installation and configuration. Extension installation and configuration is done by WMF folks using a different process (patches and deploys of the operations/mediawiki-config repo in Gerrit). –Novem Linguae (talk) 07:58, 4 June 2025 (UTC)[reply]
Likely they could add CSS or JS to remove or hide the box with the AI content. Remember WP:Superprotect? That was added back in 2014 when German Wikipedia was doing much the same to hide MediaViewer. I don't think they'd try to bring back superprotect to fight back if we did it, but they might do other things. Anomie⚔12:12, 4 June 2025 (UTC)[reply]
Nope. I was just making the point that interface administrators do not have direct control of MediaWiki extensions. As mentioned by some others, it's possible to break some things using hacks (in this case the hack would probably be an edit to MediaWiki:Mobile.css or MediaWiki:Common.css or similar). This would be similar to what Portuguese Wikipedia did to block IP addresses from editing. We should think very carefully before crossing that bridge though. That would be a major escalation with the WMF. –Novem Linguae (talk) 17:15, 4 June 2025 (UTC)[reply]
I will note that I've asked folks at the WMF to reconsider this decision. There probably needs to be a wider discussion (both internally and potentially onwiki) about the rules around what can and cannot be A/B tested (stuff like, "hey should we have a bigger donate button" doesn't require consensus, but this feels closer to a pseudo-deployment). I think it also might make sense to potentially spin this tool in a different direction, say as an LLM that highlights hard technical language text on the lede that the user can then fix. (I think the core problem here still definitely needs addressing) Sohom (talk) 13:10, 4 June 2025 (UTC)[reply]
I don't think we can begin to discuss spinning such a feature in the direction of highlighting "hard" or "technical" language without clearly defining what that threshold should be. What reading level are we aiming for across ENWiki? Grabbing a quote from the mediawiki page on the usability study for Simple Article Summaries:
"Most readers in the US can comfortably read at a grade 5 level,[CN] yet most Wikipedia articles are written in language that requires a grade 9 or higher reading level. Simple Summaries are meant to simplify and summarize a section of an article in order to make it more accessible to casual readers."
A grade 5 level would mean that all lede sections would need to be completely understandable for a 10-11 year old. I fear simplifying text to this degree will end up reducing the nuance present in articles (which, per its nature, is already reduced in the lede). The Morrison Man (talk) 13:23, 4 June 2025 (UTC)[reply]
I think it's fine for editor-facing tooling to be wrong at times, (assume a lower grade/have the grade be configurable) primarily cause editors have the ability to make judgement calls and not show parts of the text, something that readers can't. Sohom (talk) 14:30, 4 June 2025 (UTC)[reply]
I personally find it very problematic that we cannot do 2 week experiments. Experimentation is the basis of learning, of evolving of knowing where to go from where you are. If a two week experiment is this problematic, I think we should question the longevity of the project (on a generational scale). If people want to give input, they should give input, but that shouldn't block a 2 week experiment. —TheDJ (talk • contribs) 13:27, 4 June 2025 (UTC)[reply]
@TheDJ I think the problem here isn't so much experimentation (which imo is fine), but rather the fact that this "feels like a deployment". Peeps who would see such a experiment would assume that Wikipedia is going the AI way (when it is not in fact doing that and is actively discouraging people from using AI in their writing). If the experimentation had community buy-in, I think we would have a completely different story. Sohom (talk) 13:32, 4 June 2025 (UTC)[reply]
Experiments are fine, when they are conducted ethically. That is especially true of experiments involving human subjects. In this case, it was proposed that we present potentially misleading AI content to readers, who would not be aware of, nor had consented to being, test subjects. For things like minor UI changes, such unknowing A/B type testing may indeed be ethical, but not for some massive change like that. Readers to Wikipedia do not expect to receive AI-generated material; indeed, one of the things I love most about Wikipedia is that it's written by people, and does not use any "algorithm" or the like to try to shove something in anyone's face. You just get the article you pull up, and if from there you want a different one, you choose which one you read next. Now, if there were an opt-in process for people to consent to being part of such an experiment and provide feedback, that might be a different story. SeraphimbladeTalk to me16:48, 4 June 2025 (UTC)[reply]
@TheDJ Let's not pretend that the community reacts like this because it is a 2 week experiment. That is the mother of all strawmen.
The whole thing is clear proof that the WMF is completely out of touch, does not understand its own role, and has no respect for the volunteers, or the readers. Polygnotus (talk) 18:27, 4 June 2025 (UTC)[reply]
It's not "proof". It's not close to "proof". It doesn't resemble proof in any way. Maybe it is confirmation of something for some people, but confirmation is weak. Sean.hoyland (talk) 04:44, 7 June 2025 (UTC)[reply]
At the same time as this underhanded attempt to sneak AI slop into the content, they are also making a request on meta to run test donation banners more often exclusively on enwiki. Starting at the extreme so as to work backwards, I suggest revoking all donation banner permissions until such time as everyone employed by or elected to WMF and affiliate roles with generative AI COI or positive views towards the same are terminated and prohibited from holding elected office. Competence is required. Awareness of community norms is required for anyone holding an elevated role on enwiki. Hold WMF to the same standards as you hold admins and contributors. Recall the WMF. 216.80.78.194 (talk) 20:08, 4 June 2025 (UTC)[reply]
This is a prime reason I tried to formulate my statement on WP:VPWMF#Statement proposed by berchanhimez requesting that we be informed "early and often" of new developments. We shouldn't be finding out about this a week or two before a test, and we should have the opportunity to inform the WMF if we would approve such a test before they put their effort into making one happen. I think this is a clear example of needing to make a statement like that to the WMF that we do not approve of things being developed in virtual secret (having to go to Meta or MediaWikiWiki to find out about them) and we want to be informed sooner rather than later. I invite anyone who shares concerns over the timeline of this to review my (and others') statements there and contribute to them if they feel so inclined. I know the wording of mine is quite long and probably less than ideal - I have no problem if others make edits to the wording or flow of it to improve it.
Oh, and to be blunt, I do not support testing this publicly without significantly more editor input from the local wikis involved - whether that's an opt-in logged-in test for people who want it, or what. Regards, -bɜ:ʳkənhɪmez | me | talk to me!22:55, 3 June 2025 (UTC)[reply]
I mostly agreed with the thrust of your statement formulation before, but unfortunately this case makes it seem too weak. Bluntly, whether we are informed is somewhat of a moot point here. The issues with the example should have been caught internally, far before they made it to the craft-a-custom-youtube-video-for-a-survey phase, and far before they would need to inform communities. In the survey linked above, the tool blatantly and obviously fails on its own merits for its own purpose. To be at the two-week live test phase now, with the tool as it is? Informing us is not the issue. CMD (talk) 02:17, 4 June 2025 (UTC)[reply]
Another approach would be to no longer allow the WMF to monetize the work of Wikipedians, and instead run our own banners to collect money for a new war chest. The WMF will never take the community seriously as long as they are the only possible provider of what we need. If there is a viable alternative that will change. Polygnotus (talk) 02:26, 4 June 2025 (UTC)[reply]
Proposals to create an alternate WMF are not going to be helpful to this discussion. We are an existing community trying to work with the WMF, forking is a distraction. CMD (talk) 02:56, 4 June 2025 (UTC)[reply]
In the technical sense, we are capable of doing that as is. In practical and logistical senses, it would take moving some mountains which lie far outside the scope of this discussion. CMD (talk) 03:02, 4 June 2025 (UTC)[reply]
We may need to start another RfC that says something like: "The WMF is not allowed to use secret surveys and has to use the conventional Wikipedia consensus building methods (talkpages, RfCs, et cetera)." Polygnotus (talk) 02:19, 4 June 2025 (UTC)[reply]
Hm. Originally I thought this was some kind of A/B test and we should let the experiment play out without interference...for science! But now that I've seen the questions, this is not an A/B test. This is trying to gauge community support. It is trying to be an RfC. It should not have been hidden and doled out randomly. It should have been a public survey. Consider me suitably outraged. Toadspike[Talk]03:21, 4 June 2025 (UTC)[reply]
It might be more worrying that editors don't grasp the point of random sampling. Public surveys, and even quasi-private ones, tend to get a lot more responses from certain types of contributors (e.g., editors with >30K edits) than others. If you want to know what everyone thinks, then posting the link to a page where mostly highly active editors will see it (and only a tiny fraction of them – only 1 in 500 registered editors ever posts to the Village pumps, and even if you look only at WP:EXCON editors, it's just one in six of them) is not a way to go about it. Surveying a biased sample set is exactly the kind of bad behavior by survey operators that we see at Wikipedia:Fringe theories/Noticeboard all the time, so we shouldn't be advocating for using it here. WhatamIdoing (talk) 04:57, 4 June 2025 (UTC)[reply]
@WhatamIdoing As someone whose second-favourite book is about lying with statistics... any choice you make is wrong, and it is about choosing the lesser of a bunch of evils. This was a terrible choice. Polygnotus (talk) 05:01, 4 June 2025 (UTC)[reply]
If your goal is to get an accurate understanding of the sentiment in a given population, and you believe that 100% responses are unlikely, then proper random sampling is not "the lesser of a bunch of evils"; it is the right choice.
If your goal is to show off that you subscribe to some non-scientific human values (e.g., "transparency!" or "following our conventional consensus-building methods"), then of course you wouldn't want to do things in a statistically sound manner. Instead, you'd want to take a leaf from the marketing manuals. I could suggest a model that I believe would work, except that (a) I don't think marketing-led software development is the right approach for Wikipedia, and (b) I don't want to provide a manual on how to do it. WhatamIdoing (talk) 05:12, 4 June 2025 (UTC)[reply]
@WhatamIdoing You are invited to come read the book. It has an entire chapter that deals with problems such as this (and ethics more broadly).
The idea that this is, somehow, "science", and that therefore we can do all kinds of bad/unethical stuff has historically been proven to be a bad one. You most likely know a bunch of examples.
Who cares about a statistically sound manner of doing research when someone is proposing to give the best screen real estate we have, the lead sections of our articles, to some multi-billion dollar AI company, and to use the volunteers as free labour?
Sorry, I can't pretend that there is a discussion to be had about survey methodology instead of one about incompetence and disrespect for the volunteers. Polygnotus (talk) 05:21, 4 June 2025 (UTC)[reply]
Random sampling is neither "bad" nor "unethical". NB that I'm talking about your suggestion above that "The WMF is not allowed to use secret surveys and has to use the conventional Wikipedia consensus building methods (talkpages, RfCs, et cetera)." and not about whether AI is desirable in general, or this proposed use is desirable in practice. WhatamIdoing (talk) 20:29, 4 June 2025 (UTC)[reply]
It sure looks like you did: "The idea that this [random sampling and proper statistical standards] is, somehow, "science", and that therefore we can do all kinds of bad/unethical stuff". WhatamIdoing (talk) 20:35, 4 June 2025 (UTC)[reply]
I wrote: The idea that this is, somehow, "science", and that therefore we can do all kinds of bad/unethical stuff has historically been proven to be a bad one.
You wrote: It sure looks like you did: "The idea that this [random sampling and proper statistical standards] is, somehow, "science", and that therefore we can do all kinds of bad/unethical stuff".
Square brackets are a convention in the English language to identify words that have been added as a clarification by an editor. You might have run across that in academic sources in the past.
I am using this convention to tell you what I understood the Antecedent (grammar) of the pronoun "this" in your sentence to mean. A typical response to such a statement sounds like one of these two:
'I apologize for being unclear. When I wrote "The idea that this is somehow science...", I didn't mean statistics; I meant "The idea that [fill in the blank with, e.g., 'AI' or 'marketing' or whatever is somehow science..."', or
'Yes, you understood me correctly. I think it's wrong to consider random sampling and proper statistical standards to be any type of science. Instead, I think statistics should be considered a [fill in the blank with, e.g., 'non-science like fine artwork' or 'a pseudoscience like Time Cube']."
The idea that this is, somehow, "science", and that therefore we can do all kinds of bad/unethical stuffhashistoricallybeenproventobeabadone.
+
The idea that this [random sampling and proper statistical standards] is, somehow, "science", and that therefore we can do all kinds of bad/unethical stuff
A decade ago, work-me ran one of these surveys. We offered an on-wiki version and an off-wiki (Qualtrics) version. We got about 500 (yes, five hundred) responses in Qualtrics and just two (2) on wiki. People voted with their feet, and I've no reason to believe that it would be any different for any other survey. You might not approve of their choices (it's ever so much easier to argue with people who give the 'wrong' answer if it's on wiki, with their username right there...), but these are the choices people make, and I'd rather get 500 responses in Qualtrics than just two (or even ten) on wiki. WhatamIdoing (talk) 04:49, 4 June 2025 (UTC)[reply]
Speaking of evil, I noticed as I landed on the last page that the order of good and bad responses had been switched at one point during the survey. Can't help but feel like they did this intentionally. LilianaUwU(talk / contributions)05:19, 4 June 2025 (UTC)[reply]
There are indeed benefits to random sampling. Asking "do you like this new feature or not" is fine. But the survey asks several questions about who should moderate this new content which would certainly be subject to community approval later anyways, which is weird. Toadspike[Talk]10:19, 4 June 2025 (UTC)[reply]
I also was thrown off by the switch from "agree"/"disagree" to "unhelpful"/"helpful" and it almost caused me to vote in favor of AI usage. Whether from deception or incompetence, it renders the results of last set of questions completely useless as there's no way to know how many people voted incorrectly. Dan Leonard (talk • contribs)19:27, 4 June 2025 (UTC)[reply]
To answer the question asked in the section title. No.
Lets tone down the the witch hunt. (Also yes, the number of tasks mentioning AI might be more, but Tone Check and Simple Article Summaries are the only two WMF led ones planned for now). Sohom (talk) 11:48, 4 June 2025 (UTC)[reply]
@Sohom Datta @Polygnotus Similar to summaries, WMF already started experimenting pushing raw machine translaton as articles in non-Engllish languages. This is also labeled as experiment, targetted for smaller languages. So you won't hear much voice from those our small wikis. https://phabricator.wikimedia.org/T341196. As far as I can tell both these experiments are similar and unethical. MT output from ML models for smaller languages are unusable without human edits and attempts to replace editors in smaller wikis. 2405:201:F009:9906:F2EE:64D9:BD6F:E8FB (talk) 08:42, 5 June 2025 (UTC)[reply]
Unfortunately, I have to pick my battles. And I don't speak any of those languages so I have no clue how to judge the translations. I just know that when I talk to any AI in a language other than English the quality degrades substantially and noticably. Polygnotus (talk) 12:48, 5 June 2025 (UTC)[reply]
I'll take a look at this later, but to my understanding reading the related Phabricator tasks, the content that is auto-translated is fairly well marked as being a auto translation and the button is at the end (not at the start) of articles (and feature prominent call to actions to improve and add the translations to the Wikipedia articles). Given the state of many language editions I see this as a net positive for smaller wikis and not necessarily a attempt to "replace editors". Sohom (talk) 16:58, 6 June 2025 (UTC)[reply]
Hey everyone, this is Olga, the product manager for the summary feature again. Thank you all for engaging so deeply with this discussion and sharing your thoughts so far.
Reading through the comments, it’s clear we could have done a better job introducing this idea and opening up the conversation here on VPT back in March. As internet usage changes over time, we are trying to discover new ways to help new generations learn from Wikipedia to sustain our movement into the future. In consequence, we need to figure out how we can experiment in safe ways that are appropriate for readers and the Wikimedia community. Looking back, we realize the next step with this message should have been to provide more of that context for you all and to make the space for folks to engage further. With that in mind, we’d like to take a step back so we have more time to talk through things properly. We’re still in the very early stages of thinking about a feature like this, so this is actually a really good time for us to discuss here.
A few important things to start with:
Bringing generative AI into the Wikipedia reading experience is a serious set of decisions, with important implications, and we intend to treat it as such.
We do not have any plans for bringing a summary feature to the wikis without editor involvement. An editor moderation workflow is required under any circumstances, both for this idea, as well as any future idea around AI summarized or adapted content.
With all this in mind, we’ll pause the launch of the experiment so that we can focus on this discussion first and determine next steps together.
We’ve also started putting together some context around the main points brought up through the conversation so far, and will follow-up with that in separate messages so we can discuss further.
With all this in mind, we’ll pause the launch of the experiment so that we can focus on this discussion first and determine next steps together. Wonderful. Thank you very much. Cremastra (u — c) 13:36, 4 June 2025 (UTC)[reply]
Concurring with the other editors below. Thank you very much for pausing, but I think the next steps should be an agreement to not go forward with this at all. It doesn't take an admin to see that there is overwhelming consensus here against this proposal, and this website operates by consensus. This proposal should be treated as any other, from any editor, but in this case it has been clearly rejected by the community. Cremastra (u — c) 15:00, 4 June 2025 (UTC)[reply]
Thank you for listening to the community on this one - but may I suggest simply scrapping the whole idea? I fail to see any way it will ever be acceptable to the vast majority of editors. CoconutOctopustalk14:12, 4 June 2025 (UTC)[reply]
@CoconutOctopus I think there are valid ways of implementing this idea, perhaps as a stand-alone browser extension, or maybe even as a tool that highlights technically worded or hard to understand text for editors or for that matter, maybe a tool that popups up relevant related articles to look at for definitions of technical terms. I would not call for scraping this line of work, but I would definitely call for caution since it can be easy to accidentally erode trust with readers. Sohom (talk) 14:27, 4 June 2025 (UTC)[reply]
Glad to hear this. Please keep in mind that while it's true that editor involvement is essential, volunteer time is our most precious resource, and a lot of us are already spending a lot of that time cleaning up AI-generated messes. -- asilvering (talk) 14:17, 4 June 2025 (UTC)[reply]
Good reminder about the influx of AI garbage at AfC and NPP as a key context here. I think this proposal felt particularly misguided because it was actively counter to editors' most pressing needs re: AI, namely, anything that could help us spend fewer hours of our precious youth carefully reading content that no human took the time to write. ~ L 🌸 (talk) 17:16, 4 June 2025 (UTC)[reply]
Indeed. AI tools that help editors identify which articles are most likely to be most in need of a more simplified lead? That could be hugely useful. AI tools that give us more shit to shovel, while dealing possibly irreparable harm to our current image as "the last best place on the Internet"... I'll pass. -- asilvering (talk) 17:26, 4 June 2025 (UTC)[reply]
I think I'm with CoconutOctopus on this one. What you're seeing here isn't like the initial opposition to Visual Editor (where it wasn't yet fit for purpose, but one day might be, and indeed after more effort was put into it, it was and it was then pretty readily accepted). This is primarily opposition to the proposal altogether, that AI-generated material would ever be presented as article content. I do not see any way that such a thing could ever be acceptable, regardless of what was done with it. SeraphimbladeTalk to me14:30, 4 June 2025 (UTC)[reply]
Echoing the other editors. There is absolutely zero way in which I would ever be comfortable with presenting readers with AI generated content. Your step back is a little win, but I definitely don’t like the implication that you will return in the future. Scaledish! Talkish? Statish.14:54, 4 June 2025 (UTC)[reply]
Thank you very much for listening to the needs of the community! The idea did get me thinking: while there is strong opposition to AI-generated content, I haven't seen as much discussion about the other part of the idea, namely, bringing summaries to articles. While, in most articles, it would be redundant with the lead, a "simple summary" could be interesting to consider for articles with a long and technical lead. The infrastructure for this project can definitely be used to work on an implementation of volunteer-written summaries on technical articles, if the community and the WMF are both interested! Chaotic Enby (talk · contribs) 15:09, 4 June 2025 (UTC)[reply]
I'm realizing that it could be done with a template (maybe a reskin of a collapsible box) and would not necessarily need WMF involvement, although their help would still be welcome for some technical aspects like Visual Editor integration and for A/B testing variants of the format once the idea has community consensus (if that happens). Also thinking that, since these summaries would be user-editable, it might be neat to have a gadget to edit them directly (like Wikipedia:Shortdesc helper and the lead section edit link). Chaotic Enby (talk · contribs) 15:31, 4 June 2025 (UTC)[reply]
Indeed, and a tool that would help editors with these might be useful, as opposed to creating new layers of summaries. CMD (talk) 19:01, 4 June 2025 (UTC)[reply]
Infoboxes are yet another type of summary. And the proposed feature seems rather like Page Previews which are another existing type of article summary. Wikipedia has a problem of proliferating complexity -- see feature creep. Andrew🐉(talk) 22:16, 4 June 2025 (UTC)[reply]
Grateful for a) the editors that spoke up here, and b) WMF for recognizing community concerns and agreeing that this needed to be paused. Just adding my voice to say - with no ill will toward the teams that developed it - this seems like an extremely bad idea on its face. 19h00s (talk) 15:39, 4 June 2025 (UTC)[reply]
To reiterate what others have said, I do not see any scenario in which I support any readers or editors, ever, viewing AI-generated content on Wikipedia. This project is fundamentally against the Wikipedia ethos and should be done away with entirely. —Ganesha811 (talk) 16:44, 4 June 2025 (UTC)[reply]
@OVasileva (WMF): I hope the WMF will use randomly-selected surveys of editors and readers to gather feedback rather than self-selected surveys, because
self-selected surveys (like comments on wiki talk pages) will always result in skewed feedback. Those of us who want the WMF to keep iterating, experimenting, and testing may not be as vocal as others but we may be more numerous, who knows. Levivich (talk) 17:03, 4 June 2025 (UTC)[reply]
I think there are a lot of contexts where I would agree with this sentiment - that is the comments are a form of elite that are not representative of a bigger group. However, in this case where there is going to be an explicit need for editor moderation, a discussion with 85 participants probably does have some degree of representativeness of the kinds of people who would then do that moderation. Best, Barkeep49 (talk) 18:52, 4 June 2025 (UTC)[reply]
A bit late to this conversation, but I agree with the "Yuck" sentiments. I think that a pause on development on this feature is insufficient, and a cancellation is the minimum acceptable response here, and ideally should include better communication so wee don't ever get 2 weeks away from something like this again. Do we need a RFC now to give our interface admins preclearance to remove these summaries if the WMF ever does roll them out? Tazerdadog (talk) 20:34, 4 June 2025 (UTC)[reply]
I'll have to agree with everyone else: it shouldn't be a pause on development, it should be an outright cancellation. We're the last mainstream website without AI being continually rammed down our throats, and it should remain that way. LilianaUwU(talk / contributions)22:11, 4 June 2025 (UTC)[reply]
Hi all (ping @Polygnotus and @Geni). I’m Marshall Miller, working with Olga (but in a different timezone!) Thanks for noting this — the survey is still running. It’s too late in the day for the team to turn it off from a technical perspective — tomorrow is the soonest we can do it. And I understand your concern — we don’t want this survey to accidentally convey that we are definitely building/deploying this feature broadly. I’m hopeful that by the time we can turn it off, there will be enough data collected for us to be able to look at informative results together (staff and volunteers). MMiller (WMF) (talk) 02:10, 5 June 2025 (UTC)[reply]
I’m hopeful that by the time we can turn it off, there will be enough data collected for us to be able to look at informative results together (staff and volunteers). Note that the survey is incredibly flawed in a bunch of ways, so it is impossible to draw conclusions from it. Also note that surveys are not how we make decisions here, the Wikipedia community has discovered that our consensus-based model is superior to simple voting. It would be very good to have a retrospective where we can discuss what went wrong and how we can avoid making similar mistakes in the future. Also, I am pretty sure that the community wants assurances that something like this won't happen again. They are already drafting up ways to tell the WMF to stop doing this.
As a nerd I like AI stuff and I use AI every day, but as a Wikipedian I know how careful we gotta be if we want to use AI properly on Wikipedia. Polygnotus (talk) 02:25, 5 June 2025 (UTC)[reply]
Actually, I think the survey results could be very interesting. If they are based on the dopamine summary, how many people picked up on its flaws? Some would be quite obvious just reading the lead. If they did not, they that's an interesting signal of how much what we (Wikipedia) show people is trusted implicitly. There has been research that readers never view sources etc., perhaps that's because they believe we have vetted things. Maybe they assume the same for these summaries. CMD (talk) 04:22, 5 June 2025 (UTC)[reply]
Using AI to generate content should be a bright red line. One thing that might be helpful is a tool on talk pages that identifies useful sources for the article in question (excluding sources already in the article) Kowal2701 (talk) 09:32, 5 June 2025 (UTC)[reply]
I think you'd be hard-pressed to find anybody who would interpret interested wikis as anything but "wikis whose volunteer communities have expressed interest in taking part in the development of this project". It is technically not the case that this came completely out of the blue as some claim on this page (so I'd have some sympathy if you felt accused of things you didn't do), but if you took the lack of response to the thread as an indication not that enWP was not interested and the project was unwelcome, but that you could proceed with it without more consultation with the community, then I think that encapsulates the disconnect between WMF and the community expressed here really well. Nardog (talk) 13:02, 5 June 2025 (UTC)[reply]
I look forward to going over this conversation a decade hence and following up with all the people who said that this or that computer thing will a priori "never" be able to do this or that task — historically the record has not been great on these predictions. Does anyone remember a couple years ago when a bunch of people considered it a knock-down refutation to say Stable Diffusion couldn't draw fingers, and that it would never ever ever be possible for a computer to draw fingers? jp×g🗯️13:44, 5 June 2025 (UTC)[reply]
It's possible (and even likely) that AI will get better - and I tend to think that summarization of existing content is an AI strength, as opposed to creating new content, which is a definite weakness. But that misses the point. In a world which will increasingly be dominated by AI-generated content, from AI slop on up, Wikipedia can and should be different. We should lean into the fact that we are a human project, written and managed by volunteers. Wikipedia is already one of the last bastions of AI-free content online while the world turns into an echo chamber of LLMs regurgitating material at one another. —Ganesha811 (talk) 13:57, 5 June 2025 (UTC)[reply]
Whether or not LLMs are capable of becoming reliable sources in the future, they aren't reliable sources right now, and so they shouldn't be used to generate reader-facing content until and/or if that happens. Gnomingstuff (talk) 18:13, 6 June 2025 (UTC)[reply]
A proper step back?
I may be wrong, but it seems to me that the deployment of AI for article descriptions is a bit of a solution in search of a problem. It looks like people want to use AI and then think this is a good way. Can we think about what the problems are on Wikipedia and how to solve them instead? Perhaps the answers involve AI, perhaps they do not. In the case at hand:
Is it true that lead sections are often too technical?
If yes, is there a way to identify which lead sections are too technical?
If yes, how can we improve these lead sections?
AI could possibly help with these things, but not by replacing our human written leads with AI generated ones. That is what software companies do who do not have an army of highly intelligent and opinionated volunteers working for them for free. (Google or Facebook might do these things, because they are technology based, but there is absolutely no reason for a human-based place like Wikipedia to replace human output by machine output; it is antithetical to the way we work). Any deployment of AI on Wikipedia must be subordinate to the humans, not replace them. So anyway, could we do the process the right way around: first identify a problem that needs solving, then discuss how to approach the problem and what tools to best use for it. —Kusma (talk) 19:03, 4 June 2025 (UTC)[reply]
Well put! I'm not 100% against any interaction between AI tools and Wikipedia - but they must be deployed judiciously on the back end to solve specific problems, not suddenly rolled out to 10% of all mobile users in a "test" in order to replace the work of human editors. —Ganesha811 (talk) 21:52, 4 June 2025 (UTC)[reply]
Yes, thank you for this. I see the implementation of AI—at least right now—similarly to putting WiFi in toothbrushes. Is it "the latest tech-y thing"? Yes. Does it make our lives easier? No. Relativity ⚡️02:48, 5 June 2025 (UTC)[reply]
@Relativity As someone who is strongly against this proposal I should say that using AI can truly be beneficial. They completely missed the mark on the Five Ws and how to communicate and all that, but the technology in itself isn't uniformly bad. I am using AI when I edit Wikipedia in ways that are beneficial and non controversial.
For example, Claude just wrote a script for me that shows the currently active surveys on my userpage. So if the WMF has another bad idea I will know about it.
And I have also used AI for things like detecting typos, missing words and other small imperfections. Ultimately, I take the decision and the responsibility, and the AI sometimes says a bunch of nonsense, but it can be a useful tool, if you know how to work with it. Polygnotus (talk) 02:55, 5 June 2025 (UTC)[reply]
@Polygnotus: I'm not saying that AI can't be useful—it can be, and I've used it before for different things. I use AI-powered tools all the time for work. Perhaps I should have reworded my earlier comment—I'm saying that it would not make our lives easier in Wikipedia in what is being proposed to be done. The new proposal may be adding AI to our pages for the same reason we'd put WiFi in toothbrushes. Relativity ⚡️17:01, 5 June 2025 (UTC)[reply]
You use AI well to suggest edits, and commit those you agree are improvements. I also used tools in that way, though I'm not sure I'd call them AI. That's a wholesome and beneficial use of AI but, as you say, not all of its suggestions are helpful and it does need a human filter. Certes (talk) 21:06, 6 June 2025 (UTC)[reply]
Hi @Kusma, you raise a lot of important questions. We agree with you that discussing the problem itself should take precedence over any specific solution. Thank you for starting this topic. While this may not have been super clear in our previous communications, different teams at the Wikimedia Foundation have been doing research in this area for the last few years before we started exploring possible solutions. I wanted to share some of this earlier research that originally made us curious about this problem space in case it's helpful and so we can discuss further:
This work started with a wider initiative to address knowledge gaps by the Research team at the WMF. One of the things this initiative focused on was improving the readability (how easy it is to read and understand a written text) of articles (Multilingual Readability Research). Some of their findings were also published in this public journal article https://arxiv.org/abs/2406.01835
I also find the background research page really valuable since it includes lists of other research done on this topic from within and outside of the WMF and within a variety of different contexts and topics. It includes different studies of how readable, accessible, and understandable Wikipedia content is over time and in different scenarios.
In general, content simplification has also been an area that many editors have also been interested in. This led to the rise of projects like Simple English Wikipedia, as well as the Basque Txikipedia (Wikipedia for kids). These projects have been successful, but they are only available in a few languages and have been difficult to scale.(Meaning, reader traffic as well as editor activity on these pages is much lower compared to, respectively, English Wikipedia and Basque Wikipedia.) In addition, they ask editors to rewrite content that other editors have already written. Our thinking was that there might be a way to make some part of this process easier. I’d be curious to hear of other options around this as well that could streamline simplification-type initiatives.
I'm curious what do others here think about this research, and the questions you raised about the technicality of lead sections? Do you see this as a problem impacting readers? OVasileva (WMF) (talk) 09:58, 5 June 2025 (UTC)[reply]
@OVasileva (WMF) Above you wrote: We’re still in the very early stages of thinking about a feature like this, so this is actually a really good time for us to discuss here. and here you write different teams at the Wikimedia Foundation have been doing research in this area for the last few years before we started exploring possible solutions.
Which is it? Is this the result of years of work, or did you just start thinking about this? Neither is a good answer of course, but at least the situation would be easier to understand if this was a friday afternoon rushjob. If not, then the problem is more fundamental than we feared. Polygnotus (talk) 10:09, 5 June 2025 (UTC)[reply]
From what I understand, the second statement refers to more generic research before exploring possible solutions (in that case, the Simple Summaries feature). Chaotic Enby (talk · contribs) 10:16, 5 June 2025 (UTC)[reply]
@Chaotic Enby That seems likely. But a team which has done years of research should be able to identify that this idea and approach were, ehm, sub-optimal. And you wouldn't expect them to push such a halfbaked rushjob to prod. And what I don't see is evidence that they understand the problem, which would be helpful if we want to move forward. Polygnotus (talk) 10:19, 5 June 2025 (UTC)[reply]
Probably a bad idea to respond only to 1 comment, the only comment that is not critical but asks about the underlying stuff. We are kinda waiting for a response to the other stuff. Polygnotus (talk) 12:12, 5 June 2025 (UTC)[reply]
@OVasileva (WMF): Thank you for being willing to respond to community feedback. I would like to add my voice to the chorus of people strongly opposed to the idea of AI summaries. For the English Wikipedia specifically, one option to consider for readability would be to advertise the Simple English Wikipedia more prominently. However, AI is simply too unreliable and unpopular among editors to consider at this point in time. QuicoleJR (talk) 12:44, 5 June 2025 (UTC)[reply]
I agree with the 100+ other people categorically rejecting pursuing this idea (AI-generated summaries) in any form. I am also very confused why seemingly at no point was there any "research" done on the fundamentals of Wikipedia editing and its community processes? Is no one in the research team an active, regular editor? I just can't see how this got as far as c. 5 days from test deployment without anyone realizing:
How unbelievably poorly this would be received among editors; anyone who was even marginally involved in the en.WP editing community would have anticipated the overwhelming negative sentiment exhibited above and nixed this immediately.
Do different WMF research teams not talk to each other? Surely the backlash against a vaguer AI-focused WMF "strategy" was communicated among employees?
That any wikipedia article summary must summarize the text actually in the article rather than whatever is in the LLM corpus; as @Chipmunkdavis demonstrated, the "dopamine" summary is both egregiously incorrect in its facts and divorced from what the article actually says.
That this is exactly the type of "increase clicks over quality" enshittification WP has been robust to for two decades because it was never intended to be a money-making platform dependent on page visits in the first place. I don't buy for a second that this project is just being funded to address "knowledge gaps". The WMF sees the hysteria over the TikTok generation having a 10-second attention span and the mass adoption of ChatGPT for topic overviews as an existential threat to its bloated budget, none of which even goes toward the people making its singular product (except WikiLibrary, thank you for that). If there was actual interest in closing "knowledge gaps" the WMF would fund digitalization and permanent storage of offline media from underrepresented countries/languages so that editors could use them as sources.
That expanding administrative duties, as suggested in the survey, is an incredibly intrusive overreach and absolutely should not have been floated without input from admins.
That the WMF's apparent expectation (and the obvious necessity) that volunteers will ultimately have to fine-tune and correct any AI hallucinations in these summaries utterly eliminates the provided reason for using AI in the first place (efficiently scaling up simplification efforts and expanding them to other languages) as the bottleneck will still be editor time and competency. Except now, rather than leads created through a self-selected collaboration of editors who are generally knowledgeable on the topic, we'd have potentially millions of error-ridden summaries that not only have to be evaluated by a human, but require an editor with expertise in the topic to read the entire article to ensure summary fidelity. And the intent is to deploy this for the topics that are currently written "too technical", i.e. the topics that are so complex or niche that very few editors are capable of editing them. And this is supposed to be the first (read: majority of the time, only) content a reader will encounter on the topic.
Thank you, this is very well put. As a still relatively new editor who sometimes has trouble understanding the almost automatic skepticism about any WMF initiative, this kind of debacle is really not helping to prevent me going in this direction as well. Choucas0 🐦⬛⋅💬⋅📋09:20, 6 June 2025 (UTC)[reply]
- Do different WMF research teams not talk to each other? Surely the backlash against a vaguer AI-focused WMF "strategy" was communicated among employees? Product teams and the Wikimedia Research teams are typically different teams and do not have a lot of overlap outside of the planning process. In the case of research teams, it is often desirable to explicitly not have folks who are insiders in the community since having insider knowledge has the potential to introduce subtle biases in the research. (See also, Observer bias)
- If there was actual interest in closing "knowledge gaps" the WMF would fund digitalization and permanent storage of offline media from underrepresented countries/languages so that editors could use them as sources. There are efforts in this realm on Wikisource, particularly those Wikisource Loves Manuscripts and amongst various affiliates who are indirectly funded by the WMF through grants!
- That expanding administrative duties, as suggested in the survey, is an incredibly intrusive overreach and absolutely should not have been floated without input from admins. Floating a idea of administrative oversight and gathering feedback on the same idea does not typically require a consensus discussion to happen before the idea is floated. This is not a intrusive overreach in any sense since the intention was to have a discussion at a later date about moderation strategies (as outlined in their roadmap for the now paused feature) Sohom (talk) 10:21, 6 June 2025 (UTC)[reply]
I really appreciate your taking the time to inform us all on WMF procedure!How would having familiarity with Wikipedia processes introduce (harmful, measurable) bias? I would think it would be far better to have people who actually understand how WP works interpreting data; the research landscape is in fact cluttered with irredeemably poor articles about Wikipedia (like this one that somehow arrived at the exact opposite conclusion from what the data showed).I've been pointed toward that WikiSource manuscript effort before, but from what I've read it seems it is focused on digitizing primary manuscripts, which would have limited use in our articles? Regarding the admin thing, by "floated" I meant "got to the stage where a pilot study was run", which is pretty far along. Why not gauge the reception by the communities that will actually be implementing the proposal before funding pilot studies and mobile tests? JoelleJay (talk) 16:23, 6 June 2025 (UTC)[reply]
Yeah I saw that linked up above, but that seemingly came after their pilot study.We will come back to you over the next couple of weeks with specific questions and would appreciate your participation and help. Did this happen? JoelleJay (talk) 17:03, 6 June 2025 (UTC)[reply]
Just as WMF has performed research before that came to conclusions that support their point of view (without my opinionating on whether that was deliberate), so too could someone who is deep-in-the-know design research that supports a "Wikimedian" point of view a priori. It's not a concern (or at least, the framing here isn't about it) about the interpretation of data, it's about which data is looked for to begin with. Izno (talk) 16:57, 6 June 2025 (UTC)[reply]
I understand that over-familiarity could influence the choice in which research to pursue, which is why it would be best to have a team with a mix of insiders and outsiders. Or have insider consultants to evaluate proposals after an experimental design has been hashed out by outsiders. At the very least, they would have learned much much earlier that an LLM-based approach to this problem was absolutely out of the question and could have put their resources into something more productive. JoelleJay (talk) 17:09, 6 June 2025 (UTC)[reply]
@OVasileva (WMF) Have been doing some background reading of the pages that you mentioned, while I do see a fairly strong indication of the need for the simplification of article text in the research studies, I see almost no studies claiming that large language models are the correct approach to solving this problem. The closest thing I could find in relation to a AI/ML technique was in the most recent survey by Trokhymovych et al. where the authors proposed a machine-learning model based on previous work by Lee and Vajjala et al. to use a BERT model to detect and score the readability of Wikipedia articles. The article does not explicitly make any recommendations on how this problem could be fixed. (Honestly, I am sad to see that the tool built by the researchers was not advertised more widely!)
On the other hand there has been a fair amount of research into the text generation characteristics on LLMs, particularly pointing out that they are prone to hallucination (as shown by multiple pieces of research cited in the Wikipedia article about the topic) and are prone to becoming unaligned even when explicity trained to be aligned (Carlini 2023). Additionally, while there has some research into using a variety of grounding techniques, most papers still concede that their methods lower the rate of hallucinations but do not eliminate the risk of hallucinations completely. (Elaraby et al., Li et al. ) This makes them unsuitable for a reader-focused unmoderated test as you had proposed here. While theoretically, moderation tooling could have helped, the fact that a majority of the more complex technical articles receive very little viewership or editorship means that a lot of the articles would still be left unmoderated and prone to misinformation or false information, potentially exacerbating the knowledge gap for the person(s) that received the wrong information instead of closing it. (not to mention that it might cause the person to cultivate a distrust towards content on Wikipedia which would contrary to the goal here). Sohom (talk) 10:04, 6 June 2025 (UTC)[reply]
I am especially curious what their entailment score was for, e.g., the dopamine summary, given that it seemed to summarize material that was not mentioned or not emphasized in the original text. How did that happen? JoelleJay (talk) 17:12, 6 June 2025 (UTC)[reply]
The model's output will consist of: i) a readability score ranging from negative (easy to read) to positive (difficult to read), ii) a predicted grade level (i.e. roughly capturing the number of years of education generally required to understand this text).Polygnotus (talk) 17:32, 6 June 2025 (UTC)[reply]
I'm not sure if the tool is properly maintained at the moment to be very honest, but the idea of the tool would be nice to have, available working and free of major bugz. Sohom (talk) 21:59, 6 June 2025 (UTC)[reply]
I have tested a bunch of articles (chemistry articles vs US presidents) and it looks like this model simply thinks that a longer text is more difficult to read, and does not take into account factors like using chemistry jargon that people who know nothing about chemistry (like myself) have never heard of. Sure, I can guess what some of them mean, but I have no clue what enediol is, or furan, or lactone. Polygnotus (talk) 22:16, 6 June 2025 (UTC)[reply]
Please do not even investigate this route. There are bound to be some really crass mistakes and it will damage our reputation for ages. It is a particularly poor proposal for the more technical topics, which someone complains are difficult to grasp from the lead. Such topics often are inherently difficult to grasp, and AI will therefore likely make mistakes in summarising them. JMCHutchinson (talk) 10:21, 5 June 2025 (UTC)[reply]
@OVasileva (WMF) Thank you, I like to provide my thoughts on the research results. Note that in en-wp, we have clear guidelines towards comprehensibility, explained in WP:MTAU. This is our ideal, and I think it is a good one. Importantly, we aim to strike a balance: First, we try to be as accessible as possible, but without overdoing it, without oversimplifying. Second, there is the "one step down" approach (we determine the target audience of a particular article and write for an audience one education level below that). Therefore, our (ideal) approach will differ a lot from article to article, depending on the topic and target audience. An automated approach, as proposed here, does not make such important differentiation.Many of our articles have indeed a problem with comprehensibility. This is because we lack the manpower to bring them to "featured article" status (which would ensure that all those guidelines are met). Comprehensibility problems are usually only one of many problems an article has. The way to address this is to rework the article, which takes volunteer time. It is dangerous to use an AI to summarize articles that are poor in multiple ways, because garbage in, garbage out applies. To improve on this (and other) issues, we should strengthen our editor base and make editing easier, such as by fixing all the software bugs and wishes that have been open for years and are a real pain especially for newbies. Using gen-AI for content creation is not a viable solution here. --Jens Lallensack (talk) 11:03, 5 June 2025 (UTC)[reply]
This is because we lack the manpower to bring them to "featured article" status No, it is because explaining stuff often requires a lot of underlying information. If I say that Maven is a build automation tool that uses an XML to store dependency information. then that is meaningless mumbo jumbo unless you know what those words mean in this context. What is build automation? What is XML? What are dependencies? And the answer to those question also build upon underlying information. XML is a markup language but what is "markup"? Et cetera. And Wikipedia articles either underestimate the reader (which would be boring) or overestimate (which means that understanding a single sentence requires reading at least the lead section of 3 other articles) them. But they are almost never at the precise level the reader is at. I can read computer related articles fine, but I struggle with chemistry related articles. For someone else, that might be the opposite. Polygnotus (talk) 11:54, 5 June 2025 (UTC)[reply]
When I wrote "problems with comprehensibility", I was referring to problems that can and should be addressed according to our guidelines such as WP:MTAU. I was not talking about problems that go beyond what our guidelines recommend. In my opinion, our guidelines are already sufficient and strike a nice balance; it is just that many articles are not following them. If people disagree they are sufficient, we should maybe first talk about those guidelines, otherwise we might not know what our actual goal really is here. --Jens Lallensack (talk) 12:15, 5 June 2025 (UTC)[reply]
So what should the goal be, precisely? I do not quite understand what the problem is that you are pointing out that is not addressed by the current guidelines. Yes, the reader might lack the context to understand your example sentence about "Maven", but we already have wikilinks to provide that context, no? (And, after all, WP:MTAU also endorses in-text explanations of terms to make sentences understandable in rough terms). So what precisely is it? If you have personalised output in mind (e.g., that takes your degree of knowledge in chemistry into account), then I think that should be implemented in a separate app that is decoupled from Wikipedia, alone because of data privacy issues. --Jens Lallensack (talk) 13:42, 5 June 2025 (UTC)[reply]
I'm not saying the AI should simplify the text, I've been very vocally against that. I'm saying that it could be used to identify where text could be simplified, something within the capabilities of current models. -- LCU ActivelyDisinterested«@» °∆t°09:33, 6 June 2025 (UTC)[reply]
I gave Claude the lead section of a Wikipedia article and asked: "how can i simplify this text, give instructions like change x into y".
It changed the meaning of some things, changed scientific terms to non-scientific terms and WP:COMMONNAMEs to alternatives, and seemingly at random removed important bits of information while it left others in (that I would judge as roughly equally important).
When you say could be used to identify where text could be simplified that can mean instructions like the ones above of specific adjustments, or that it should give a "readability score" for example, so I am not sure how to interpret that. I also opened two tabs and asked Claude "give this a readability score" with the same piece of text. Claude presented me with 2 different readability scores. Polygnotus (talk) 09:54, 6 June 2025 (UTC)[reply]
@Zanahary Yeah, and I responded to that by explaining that conventional LLMs (I used Claude, but I believe others would be similar or worse):
A: are unable to actually figure out what to do in order to simplify a text (casting doubt on their ability to determine whether simplification is required/possible)
B: produce nonsensical results if you ask them to produce a readability score.
Elsewhere I showed that a model trained by the WMF creates output that doesn't match human expectations (it seems to consider long texts difficult to read, but not text with words that are very rarely used and only in the vocabulary of people who know the field.)
Maybe I am weird but if even a model specifically trained by the WMF to gauge readability (I tried a few different chemistry related articles and compared them to articles about US presidents) sucks at it, and if a "normal" model sucks at simplifying text and is unable to determine how difficult a piece of text is, then maybe using LLMs to identify leads that require simplification is just a bad idea, you know? Unless someone can show me a model that is actually good at that task? Polygnotus (talk) 22:13, 6 June 2025 (UTC)[reply]
How many times do they need to say "I do not think this is a good idea" before you stop responding with "But you're wrong -- it is a BAD idea"? jp×g🗯️23:39, 7 June 2025 (UTC)[reply]
Checking the previous test
At mw:Reading/Web/Content Discovery Experiments/Simple Article Summaries#Browser extension experiment, we learn that without actual knowledge of the enwiki editors, a limited test was conducted showing machine-generated content to actual enwiki readers, with 825 summaries (total, not necessarily distinct ones) being read by our readers. Can this, perhaps on testwiki or some beta, please be replicated so we can see what it was that you have actually shown? It normally isn't the intention that content is shown which isn't written by or at least explicitly selected by enwiki editors (the last time this happened, AFAIK, was with the Wikidata short descriptions which have been then rejected by enwiki after much opposition and sabotage by the WMF), and I wonder what has really been shown behind our backs and who would have taken responsability for problematic content (say, BLP violations, wrong or unwanted medical advice, or POV summaries of contentious topics). Basically, you were toying with the reputation of enwiki and its editors, even though the WMF doesn't do content.
So, long rant, TLDR: please put the summaries you used in that previous experiment somewhere online, so we can see what was used beyond that pre-selected "dopamine" summary with all its errors. Fram (talk) 13:41, 5 June 2025 (UTC)[reply]
Seconding Fram's comment, and linking phab:T381253 which may have more information on the topic. I see that there is a Google Docs with more detailed results – while I don't expect to see all of it for privacy reasons, giving the community access to the detailed anonymized data would be great. Chaotic Enby (talk · contribs) 13:45, 5 June 2025 (UTC)[reply]
There's this. I will skip over the baby food Hypatia summary, though it is extremely funny (Her death made a lot of people very sad, and she became famous for standing up for what she believed in.), and focus on the full summary. I do not know much about this subject area but already I see some concerns.
In general there are some strange inclusions and omissions in the summary, which give disproportionate importance to trivia -- I don't think Hypatia's menstrual blood story is the main part of her legacy -- and create implications of cause and effect that were not in the original text. For instance, the summary makes it seem like Synesius's letter to Hypatia was the inciting event for Cyril closing synagogues, etc.
The text makes some logical leaps in regard to dates. For instance, it states that the monk Ammonius was killed in the year 414 after a riot. Maybe he actually was killed in the year 414, but the article text quoted does not link that event to that year.
The AI latches onto some words like "co-opted" without considering the context. In the original text it is being used to point out the irony of Christians coming to admire someone whose followers were anti-Christianity, but the summary applies it to everyone in a way that sounds inadvertently POV-pushing: "Her legacy has been co-opted by various groups over the centuries, including Christians, Enlightenment thinkers, and feminists."
The summary describes "apatheia" as "emotional liberation"; the text describes it as "complete liberation from emotions and affections." To a layperson -- and certainly to the intended audience here -- the summary makes it sound like "apatheia" means being free to be emotional, which is the exact opposite of what's in the text.
The summary states that Theophilus "opposed Neoplatonism." The actual article states that he was "opposed to Iamblichean Neoplatonism." Iamblichean Neoplatonism is a sub-school of Neoplatonism (as the article states elsewhere) and the summary suggests that Theophilus opposed the whole thing.
And so on. So, no major hallucinations, nothing that strays too far from the original text, and nothing that isn't a mistake a human could make, but a lot of small inaccuracies and a weird sense of what's important and what's not. Gnomingstuff (talk) 02:43, 7 June 2025 (UTC)[reply]
Initial thoughts looking at the extension itself, it feels hastily put-together, almost tech demo-esque rather than thought through feature that was near deployment. This should have never been anywhere close to being deployed on a live site. Sohom (talk) 20:23, 7 June 2025 (UTC)[reply]
This appears to be the filtering that is being used, although it seems like manual filtering is on the table as a fallback, and these appear to be the quality assessment criteria. As of May 29 this is apparently not yet a production-level service (nor has it been requested as such (which is somewhat at odds with how it was presented here, but whatever). Gnomingstuff (talk) 21:04, 7 June 2025 (UTC)[reply]
Note for anyone crosschecking that list: "Sorry, we had to truncate this directory to 1,000 files. 4,342 entries were omitted from the list. Latest commit info may be omitted.". #The full summary list below, which I found and posted independently of Sohom, includes a better link. * Pppery *it has begun...19:46, 7 June 2025 (UTC)[reply]
Here is an easier-to-view version of that -- I had trouble loading anything after "Bobby" -- that also includes what seems to be the original text, for comparison. Gnomingstuff (talk) 20:13, 7 June 2025 (UTC)[reply]
some quick takeaways:
obviously these have very little to do with the article itself, and a lot of markdown headers left in (even in the non-truncated set) that speak volumes about what this is actually generating: Lemons: A Sour Powerhouse
a few CTRL-F terms to spot embarrassing stuff: "we're," "cool," "it's important," "it's like," exclamation points. (update: double spaces inserted after a period also seem to be a flashing signal for incoming slop) This movement is why we have earthquakes, volcanoes, and mountains. It's like Earth is a giant, slow-moving conveyor belt!
the model seems to have refused to summarize some articles entirely, but not all (Donald Trump seems excluded, for instance, but Project 2025 is summarized)
Thank you all for the time and effort you’ve put into sharing your concerns and ideas here. I’m writing to reiterate that the project is paused, and that the survey is now closed. We’d like to take some time to digest all of your thoughts, and we'll return to this conversation early next week. -- MMiller (WMF) (talk) 22:58, 5 June 2025 (UTC)[reply]
Thanks a lot for listening to the community on this one. It must not have been the easiest couple of days for you, and I'm happy that you nonetheless took the feedback into consideration. Really wishing you and your team the best of luck. Chaotic Enby (talk · contribs) 23:15, 5 June 2025 (UTC)[reply]
Frankly, the very obvious outcome from this discussion is "the community does not want LLM-generated summaries or anything like it", so if next week we're just going to hear from the WMF again something regarding yet another plan to implement LLM models on Wikipedia, we'll be back to square one. Narutolovehinata5 (talk · contributions) 23:33, 5 June 2025 (UTC)[reply]
Thanks for the update. One reason the community reacted particularly strongly is the idea that this was about to be tested *right away* - showing this AI content to 10% of mobile users within a week. That creates a sense of crisis. In general, editors are supportive of the WMF coming up with new ideas, proposing software tweaks, and building tools that make Wikipedia better for readers and editors. A useful principle to adopt going forward: anything AI-related should be extensively discussed with the community before *ever* becoming visible to readers. —Ganesha811 (talk) 23:51, 5 June 2025 (UTC)[reply]
I've no idea if anybody has already proposed an AI tool to summarise long discussions at The Village Pump, because I can't parse it all. ? - Roxy thedog05:56, 6 June 2025 (UTC)[reply]
@Roxy the dog Shockingly, someone has! Nothing came of it because the AI did not make a good summary (it just described the chronology and POVs, but didn't highlight the bits that were worth reading). Polygnotus (talk) 05:59, 6 June 2025 (UTC)[reply]
One tip I have is that when you notice that one person is responsible for 25% of the comments in a discussion, you can usually skip reading their comments and save a lot of time. Matma Rextalk12:18, 6 June 2025 (UTC)[reply]
I just don't know how it got to this point. Our money is being spent on an AI team at the WMF? It feels like you guys just don't really understand or even like our website. And if that is the case, please leave it be. ForksForks (talk) 13:52, 6 June 2025 (UTC)[reply]
I honestly think the best course of action is to leave Wikipedia to be a human affair (besides bots that do specific tasks like AnomieBot, CitationBot, etc) Generative AI is not the magic potion tech bros are making it out to be, and Wikipedia and it's readers shouldn't be subjected to LLM mistakes because some are bad readers, and or have a low attention span. That shouldn't be our issue, but it will be if this is rolled out. Plasticwonder (talk) 17:54, 6 June 2025 (UTC)[reply]
What is there to digest? The overwhelming consensus is "don't do this." A week later the consensus will most likely continue to be "don't do this." The only possible takeaway, then, is "we're not going to do this," and it takes no digestion to realize this. Gnomingstuff (talk) 19:30, 6 June 2025 (UTC)[reply]
@Gnomingstuff There are definitely more things to digest here other than just "hey stop this". Particularly, what "this" is is still up for debate, does "this" refer Simple Article Summaries, simplifying articles, any work involving generative AI or AI development altogether. Many sentiments have been raised across this discussion and it is important for folks at the WMF to take stock of the situation and understand the prevailing community sentiment and weigh it against work already done in the area. Another way to approach this would be the for WMF to ask "what went wrong here?" and try remedy their process to account against this kind of incident. Sohom (talk) 21:35, 6 June 2025 (UTC)[reply]
"This" refers to "this project," and "don't do this" means to not "pause" it (with the implication that it can be unpaused) but cancel it altogether. There is no amount of process or bureaucracy that can make this bad idea good. If it was introduced to the community two years ago with weekly check-ins it would still be bad. Gnomingstuff (talk) 22:19, 6 June 2025 (UTC)[reply]
"This" refers to "this project," and "don't do this" means to not "pause" it (with the implication that it can be unpaused) but cancel it altogether. There is no amount of process or bureaucracy that can make this bad idea good."
@Plasticwonder and @Gnomingstuff: My meta point still stands that if the WMF wants to do a deeper dive we should let them do that instead of forcing a "shut down, move on" outcome. I agree that AI generated summaries is not the way this should go. However, there is still room for folks to potentially pivot the project to be something like allowed user-generated/human-generated summaries on the mobile website could/should still be on the table as a potential continuation of the workstream but not necessarily this exact project. Sohom (talk) 01:16, 7 June 2025 (UTC)[reply]
We don't have any power to "let them" do anything or to force any outcome. We are not their boss and we are not Hollywood hypnotists, they are going to do what they want.
There might be some value in user-generated summaries but this proposal isn't about those, it's about AI-generated summaries. There is a paper trail of it being developed since 2024 (and maybe 2023?) around the core idea of AI generation. Gnomingstuff (talk) 19:19, 7 June 2025 (UTC)[reply]
@Gnomingstuff, I have no clue which "paper trail" you are referring to. To my understanding, the project started in 2024 as a search for a potential solution to the problem of us having incomprehensible leads on some technical articles (which fell under the broader umbrella of the WMF trying to find new ways to engage folks with the existing content). A hypothesis was proposed late 2024 to see if AI was any good at summarizing article ledes and presenting them in a accessible manner. The first prototype of the project was this one which led to a community confrontation. I see there as being still space to turn around while still pursuing the original goals of the project (which was to find ways of making Wikipedia more accessible to users). The overall goal of the project (and/or workstream) is not set in stone to only use AI-generated summaries. Calling for the project's cancellation achieves nothing other than a punitive victory on our part. Sohom (talk) 19:39, 7 June 2025 (UTC)[reply]
There are a lot of pages linked here, plus on phabricator, this whole thread, etc., I don't have time to dig through all of the linked pages again but there is extensive documentation around every stage of the process.
I don't think a "punitive victory" is a bad outcome here. The "punishment" is not having AI slop inserted into Wikipedia against the community's wishes. As you can see, most people here are in agreement that this is not a bad outcome, and so I don't know why my comment is the one you are picking apart rather than those of hundreds of other people commenting here. Take it up with them too. Gnomingstuff (talk) 19:51, 7 June 2025 (UTC)[reply]
@Gnomingstuff I am not advocating for AI summaries, I hate AI slop as much as other folks here and have been vocal about that in other non-public arenas as well. I think I the Reading/Web team should not pursue AI generated summaries further and in that sense I do want this "sub-project" gone. I do see the stoppage and potential cancellation of work on AI-generated summaries as a positive outcome and not a punitive victory. However, I do want them to continue exploring the overall workstream and project of finding technical improvements in ways so we can make the readers more engaged and the smaller project of trying to find ways of making our ledes/articles less technical. I would see the shutdown of that workstream and overarching project to be a net-negative to Wikipedia and a punitive victory on our part.
My initial response was a direct response to your question of What is there to digest? try to explain how the WMF worked and what they might be considering while the project was stopped (and what "this project" means in the context of the WMF's rather convoluted processes). I am sorry if I gave the impression of specifically picking your response apart. I think we are talking about the same thing just on cross-purpose lol. :) Sohom (talk) 20:14, 7 June 2025 (UTC)[reply]
MMiller (WMF) I'm joining this discussion late, and there's a lot of text here to wade through, so please forgive me if I'm asking something that's already been answered here or on the project page over at MediaWiki. But in addition to the question of accuracy, I'm curious about the questions of cost, sustainability, and environmental impact.
From a technical standpoint, how often would these summaries be generated? Each time a reader loads the page? Each time someone edits the page? Or just once?
Given (1), how much would it cost to generate these summaries for, say, the 7+ million pages on English Wikipedia? Is doing this the best use of donors' funds? What else won't get funded to cover these costs?
What are the social and environmental impacts of (2)? By what proportion would it change Wikipedia's current carbon footprint? How would this impact the health of people living around the servers?
There's mention of making these summaries editable. How much volunteer time do you envision it taking to check the tone, neutrality, and accuracy of each summary? What timeline do you envision for such a project? Will WMF commit to using paid staff time to ensure that this timeline is met, assuming that volunteers don't step up to do this tedious work on their own? How much has WMF budgeted for this work, and what has been done to justify spending donors' money in this way?
How did you come to that estimate in (4)? What value (in terms of, say, dollars per hour) does WMF assign to volunteer time?
How do you plan to assess the impacts of including of Ai summaries on users' perception of Wikipedia's accuracy? What sort of research design do you envision to capture variability in readers' perceptions across countries, cultures, and various demographic factors? How much has WMF budgeted for this work, and what has been done to justify spending donors' money in this way?
I apologise for making this so long. I don't need an answer to every point, I'm happy to sift through the documents where this has been covered. Thanks in advance. Guettarda (talk) 18:24, 7 June 2025 (UTC)[reply]
It sounds like it's missing words to me. Googling the phrase, the 12 results that come back suggest this miiight be an engvar I'm unfamiliar with. CMD (talk) 02:05, 8 June 2025 (UTC)[reply]
Looking at my own sample (not necessarily random, but I wasn't aiming to only pick articles I guessed would have issues):
Antisemitism is an example of why this would have been disastrous in contentious topics: the tone is way off compared to the actual topic, calling genocides sad events and the word itself just a fancy way to say "Jew-hatred."
Austria-Hungary mentions it being formed by joining two countries, Austria and Hungary, which is factually wrong: Hungary was previously part of the Austrian Empire (divided into multiple kingdoms and duchies since 1848), and was elevated to an equal status. The empire was made up of three main parts: Austria (called Cisleithania), Hungary (Transleithania), and the Kingdom of Croatia-Slavonia is also wrong, as Croatia-Slavonia was part of Transleithania.
Axolotl starts with the completely unnecessary title Axolotls: Mexico's Amazing Aquatic Salamander. Then, They stay small and aquatic is blatantly false, as they are on average slightly larger than the tiger salamander (a non-neotenic member of the same genus).
Aztec Empire is mostly accurate for the first half (I can't really judge the second as I'm not familiar with Aztec religion). Calling Xoconochcosome distant lands might be a bit misleading given its distance, although the actual lead calls it some more distant territories within Mesoamerica, so that might be where it came from.
Bohemia mentions that it included areas like Moravia and Czech Silesia (the two other Czech lands), failing to make the distinction between the region of Bohemia and the historical state of the same name (which our current leads manages to do just well). The next sentence, Over time, Bohemia became part of different empires and was affected by wars, is pretty vacuous as it can be applied to pretty much any historical region.
Another summary I just checked, which caused me a lot more worries than simple inaccuracies: Cambrian. The last sentence of that summary is The Cambrian ended with creatures like myriapods and arachnids starting to live on land, along with early plants., which already sounds weird: we don't have any fossils of land arthropods in the Cambrian, and, while there has been a hypothesis that myriapods might have emerged in the Late Cambrian, I haven't heard anything similar being proposed about arachnids. But that's not the worrying part.No, the issue is that nowhere in the entire Cambrian article are myriapods or arachnids mentioned at all. Only one sentence in the entire article relates to that hypothesis: Molecular clock estimates have also led some authors to suggest that arthropods colonised land during the Cambrian, but again the earliest physical evidence of this is during the following Ordovician. This might indicate that the model is relying on its own internal knowledge, and not just on the contents of the article itself, to generate an "AI overview" of the topic instead. Chaotic Enby (talk · contribs) 20:54, 7 June 2025 (UTC)[reply]
Yeah, that seems extremely likely and I don't understand how this got through quality control. Surely they'd tweak their entailment score method to weight appearance of meaningful content not present in the article as an autofail?? JoelleJay (talk) 21:38, 7 June 2025 (UTC)[reply]
This is a searchable list of summaries, along with the original text, although some filtering seems to have been done since. Two things to keep in mind here: one, it's not finished yet apparently, and filtering has not been fully done; two, the summaries suck ass. I mentioned this upthread but since it's buried, here are some search terms to find some of the worst of it. I fully admit this is cherry-picking but it should not be this easy to cherry-pick:
"cool," "awesome," etc.: The word "engineering" comes from a Latin word meaning "cleverness," which is exactly what engineers use to make the world an awesome place!
addressing the reader directly, "we're," "you," etc.: Over time, computers got faster, smaller, and more powerful, leading to the digital world we have today.
didactic phrases like "it's important," etc. It's important to know that pedophilia is different from actually abusing a child. Not all pedophiles act on their feelings, and many would never hurt a child.
phrases that indicate comparisons made up out of thin air, targeted at children (these are targeted at 7th graders): "it's like," etc: Oxytocin is a natural body chemical that acts as a hormone and brain signal. It's like a superpower that helps us feel love, bond with others, and even have babies.
markdown formatting, like hashes, which reveals the "titles" of the "posts" that are being generated ## Persian Cats: Fluffy Friends with a History
exclamation points: Rococo art makes things look exciting and full of movement. It's like a fun, colorful party for your eyes!
double spaces after a period, slop seems to ensue after that [Indra is] also found in Buddhist and Jain stories, but his power is reduced. Think of him like Zeus from Greek mythology. (This one also assumes a Western background, which would seem at cross-purposes with the whole "knowledge gaps" thing, but....)
These seem to be the prompts being used. I know almost nothing about how or whether prompt engineering works, but the main concern seems to be output that isn't in English.
These seem to be at least some of the evaluation criteria to determine whether these are actually good (they're not). People who know more about machine learning will probably know more about whether these are any good.
Looking at the Phab task, they're using the aya-expanse-32b model with five quality metrics: simplicity, fluency, meaning preservation, language preservation and tone, although it is not clear how much each is weighted. For meaning preservation, they are using the SummaCZS model, which is specifically designed for summaries. Roughly, it works by splitting the document and the summary into blocks, and taking, for each block of the summary, the largest entailment probability among the blocks of the original document.An issue with this method is that there is no estimation of how important information is at the scale of the document – the model doesn't care if the sentence in the summary matches a single block or 10, and will not be able to give appropriate weight to each aspect. It isn't clear why that model was picked and not the related SummaCConv, which is less sensitive to individual sentences. Chaotic Enby (talk · contribs) 23:43, 7 June 2025 (UTC)[reply]
Tone: The summary should be written in a style and tone appropriate for Wikipedia. Avoid any editorializing, opinions, or expressive language about the subject and ensure the tone remains encyclopedic, neutral, and professional. Well looks like that just got completely ignored. ARandomName123 (talk)Ping me!23:51, 7 June 2025 (UTC)[reply]
Baffled how any of this was checked by anyone and still pushed through toward live testing, but I guess it makes sense if the research team is purposefully made of people who have never read a single en.WP PAG or MOS page. If the WMF wants to get into kidfluencing, they can take this slop to YouTube shorts. JoelleJay (talk) 21:33, 7 June 2025 (UTC)[reply]
I have been digging through the Phabricator tasks, because no one involved has provided any transparency at all on this, to figure out methodology. This seems to be the page that talks about where the dopamine summary came from and gives the exact prompt that was used to generate it.
The choice of dopamine as the article seems to have been happened before the actual summarizing was done, and doesn't seem to come from a place of "well the rest of the summaries aren't great this is the best we've got": The reasoning here is that it's a verified "good article" and it also has a relatively complex introductory paragraph with lots of technical language. It also has broad general interest and an analog in Simple English.
People noticed that the tone was off, and noticed some very obvious issues with some early summaries: Dopamine is a chemical found in the brain. It is a neurotransmitter. Dopamine is released by neurons to send signals to other nerve cells. Dopamine is a neurotransmitter. Dopamine is a chemical that is released by neurons to send signals to other nerve cells. But there doesn't seem to be much of a focus on whether the summary was in fact a summary of the actual text. Which, since it's generative AI, it wouldn't have been.
I was wondering why the full list of summaries here is way more childish than the Dopamine summary originally shown at the top of thread, and when the change to a more adult reading level happened. It looks like it actually happened the other way around. There seem to have been at least two batches: fall 2024 and spring 2025. The Dopamine summary we originally saw came out of the fall 2024 batch. The summaries here seem to be the spring 2025 batch. I don't know why the tone is so different, given that the iterations of the prompts I've been able to find all specify something at a 7th-grade reading level or actually for 7th graders. I also don't know why anyone thought that the new ones were better, or that the old Dopamine summary was representative of the new stuff. Gnomingstuff (talk) 23:09, 7 June 2025 (UTC)[reply]
The general approach seems to be to serve up a gumbo bowl of popular misconceptions and tell people what they already know. The whale shark summary gives us:
Frankly, I think the whole basis of this project—summarizing articles to a below-high school reading level, purportedly to address a "knowledge gap"—betrays an irremediably misguided understanding of the breadth of this encyclopedia, the capabilities of LLMs, and how Wikipedia works. I think @Jens Lallensack brought up the very apt point that our articles are written for (just below) their individual target audiences and so should not and cannot all be summarized to the same level of simplicity. Someone who reads at a 7th grade level will derive absolutely zero understanding from a TikTok digest of Hodge theory, and that's assuming its summary was manually written by an expert. In the case of AI summaries, it would be literally impossible to dumb down that topic to below an undergraduate math degree, both because it is intrinsically complex and because you could not use only the article body to source the summary. The model could not be tethered only to material present in this article because it does not explain the basic topology and algebraic geometry concepts readers are (rightfully) expected to already be familiar with if they're on this page; that's what the blue links are for. Thus it would necessarily have to draw its summary from a corpus beyond this one page, and indeed, the lower the target reading level, the more expansive the corpus would have to be. Which means the model must be able to deviate from what is present on the target page beyond simple synonymy: it has to define each technical term using a much larger corpus while retaining the context in which the term appears in the target, but it must also distinguish terms that are allowed to be "defined" using that corpus from related concepts described in that corpus that are not brought up or emphasized on the target page. LLMs can maybe be okay at this if given the proper prompt and serious semantic constraints, but the more degrees of freedom they're allotted the more likely they are to stray significantly from what is actually covered in the input. That seems to be what happened in many of the summaries mentioned by @User:Chipmunkdavis and @User:Chaotic Enby that hallucinate meaningful words that don't appear on the page at all.
I just do not see how anyone thought this would be tenable for anything beyond the most basic articles where childish treatments already exist elsewhere, let alone for the "too technical" subjects the WMF specifically developed the tool to address. Either the project needs to be scrapped entirely, or narrowed down to supporting strictly summaries, of just the most accessible topics if sticking to the 7th or 9th grade reading level, generated by humans, and in particular humans familiar with the PAGs and MOS of the target wiki. JoelleJay (talk) 02:23, 8 June 2025 (UTC)[reply]
That assessment does make sense. The models have to rely on out-of-context knowledge to understand the text they're summarizing, but might then fail to meaningfully distinguish what is and isn't in the text itself. A possible solution could be to strengthen the meaning preservation evaluation, which is currently based on SummaCZS. Maynez et al. 2020 makes the difference between intrinsic and extrinsic hallucinations: the former correspond to inconsistencies in summarizing, while the latter originate from incorporating information not in the document. Sadly, Laban et al. 2022 (who developed SummaCZS) explicitly merged both in their metrics, so the paper doesn't give us a great idea of how their method fares on that point specifically.Additionally, their method is based on textual entailment, which doesn't really exclude cases where the summarized sentence only partially derives from the original text, so that can also be an axis of research to look into.Regarding your last point (which is what I would favor), volunteer-written summaries would indeed make a lot more sense, and be philosophically more in line with the idea of a wiki. However, summarizing already accessible topics might be seen as a bit redundant, and it could be interesting to see if we can also summarize more technical topics at a (slightly) higher reading level. Chaotic Enby (talk · contribs) 02:42, 8 June 2025 (UTC)[reply]
To answer the question asked "What was the end goal in the first place?" see my responses above to Gnomingstuff and this comment in the associated AI RFC. I do not agree that the simplification of ledes is necessarily a flawed thing to focus on. However, based on a bit of digging Chaotic Enby and I did this afternoon, the initial generation used a off the shelf large-language model (called Aya) developed by Cohere.ai that seems hosted on Hugging Face with a potentially flawed setup (see above) and extremely rudimentary prompts. The extension that was supposed to be deployed on enwiki itself just fetched a static JSON file containing pre-generated (and potentially out-of-date) summaries and showed it to the user. This seems to be an extremely rudimentary experiment, the likes of those seen for tech demos and mockups, not for software that was supposed to be deployed onwiki. Why this was scheduled to be deployed on a live production wiki is beyond me. I will echo @JoelleJay's call for a pivot of the project towards human-generated summaries, since I don't think even frontier models have solved all of the issues outlined above. I would also urge the WMF to provide a commitment on internal process improvements to ensure that all new features go through sufficient dogfooding and community feedback phases before being tested onwiki. (regardless of whether or not they are AI dependent or reader focussed). Sohom (talk) 03:07, 8 June 2025 (UTC)[reply]
There was an 8-person community feedback study done before this (a UI/UX text using the original Dopamine summary), and the results are depressing as hell. The reason this was being pushed to prod sure seems to be the cheerleading coming from 7 out of those 8 people: "Humans can lie but AI is unbiased," "I trust AI 100%," etc.
Perhaps the most depressing is this quote -- "This also suggests that people who are technically and linguistically hyper-literate like most of our editors, internet pundits, and WMF staff will like the feature the least. The feature isn't really "for" them" -- since it seems very much like an invitation to ignore all of us, and to dismiss any negative media coverage that may ensue (the demeaning "internet pundits").
Sorry for all the bricks of text here, this is just so astonishingly awful on all levels and everything that I find seems to be worse than the last. Gnomingstuff (talk) 08:43, 8 June 2025 (UTC)[reply]
Latest tech news from the Wikimedia technical community. Please tell other users about these changes. Not all changes will affect you. Translations are available.
Weekly highlight
The Chart extension is now available on all Wikimedia wikis. Editors can use this new extension to create interactive data visualizations like bar, line, area, and pie charts. Charts are designed to replace many of the uses of the legacy Graph extension.
Updates for editors
It is now easier to configure automatic citations for your wiki within the visual editor's citation generator. Administrators can now set a default template by using the _default key in the local MediaWiki:Citoid-template-type-map.json page (example diff). Setting this default will also help to future-proof your existing configurations when new item types are added in the future. You can still set templates for individual item types as they will be preferred to the default template. [4]
Starting the week of June 2, bots logging in using action=login or action=clientlogin will fail more often. This is because of stronger protections against suspicious logins. Bots using bot passwords or using a loginless authentication method such as OAuth are not affected. If your bot is not using one of those, you should update it; using action=login without a bot password was deprecated in 2016. For most bots, this only requires changing what password the bot uses. [5]
From this week, Wikimedia wikis will allow ES2017 features in JavaScript code for official code, gadgets, and user scripts. The most visible feature of ES2017 is async/await syntax, allowing for easier-to-read code. Until this week, the platform only allowed up to ES2016, and a few months before that, up to ES2015. [6]
Scholarship applications to participate in the GLAM Wiki Conference 2025 are now open. The conference will take place from 30 October to 1 November, in Lisbon, Portugal. GLAM contributors who lack the means to support their participation can apply here. Scholarship applications close on June 7th.
Chart definitions will live on their own .chart pages on Commons, under the Data: namespace. We want to treat charts as a standalone content type, rather than just a part of an article. It will be easy to reuse the same chart across wikis, and beyond Wikimedia platforms by making them available as links. Editors who want to embed charts in an article will be able to do so with a short piece of wikitext, similar to including an image from Commons, all without needing to interact with complex templates.
We have heard comments that requiring the data come from Commons tabular data may not address some common data sourcing flows, like from MediaWiki APIs or Wikidata Query Service. While those sources are not the focus for this project, we want to ensure the extension is designed in a way that they can be supported in the future.
My memory in addition to that is that it was seen as a minimum viable product. The particular point as been a pain for other editors since the project got to the point of developing this new extension, see mw:Extension talk:Chart/Project#Data source and I suspect other conversations on that talk page. (And I've seen groaning elsewhere.) Izno (talk) 01:22, 3 June 2025 (UTC)[reply]
I want to use this to chart the sizes of the various queues that feed the WP:DYK system: number of nominations pending, number of approved hooks, etc. I'll have a bot that computes these things and updates the data once a day. I guess that falls into the "some common data sourcing flows" bucket. Logically, I would have that data page live somewhere near the rest of the DYK pages, like Wikipedia:Did you know/DYK hook count. Having to put it on Commons won't break anything, but it seems silly, confusing, and arbitrary. I'm all for getting a MVP out the door, but how does hard-wiring Commons:Data into the path for the source make things simpler on the developers? RoySmith(talk)10:37, 3 June 2025 (UTC)[reply]
And, since this will involve a bot to write the data files, it will require that I go through the commons bot approval process, when I already have an approved bot on enwiki which could do the same thing with a lot less fuss. RoySmith(talk)11:13, 3 June 2025 (UTC)[reply]
I don't even see how to run tests without polluting the global namespace. Normally I would start to play with something like this in my sandbox, but the current setup seems to make that impossible. RoySmith(talk)13:15, 3 June 2025 (UTC)[reply]
RoySmith, it's really no big deal getting bot approval on Commons and once you have it you can do other things. The advantage of Commons is the data is accessible to Lua modules from any wiki. Thus your program can be copied to any Wiki, without having to copy the data. Of course if the data is enwiki specific it wouldn't matter so much, but if the data for each wiki was kept under the same tree on Commons than conceivably someone could write a summary program that looks at all wikis data, and that program would then be installable on any wiki. It's nice to have a universally accessible place to store data even though there is some initial setup to get bot approval. — GreenC17:33, 3 June 2025 (UTC)[reply]
Hmmm. I asked on commons and was surprised (in a good way) to discover that I didn't actually need permission. And I've since figured out that I can do my testing in Data:Sandbox/RoySmith, which seems a bit weird, but OK, not a blocker, so I've been playing around with commons:Data:Sandbox/RoySmith/DYK-test.chart, which produces:
so at least I'm making some progress. I still need to figure out some layout issues. And to really make this useful, I'll need @Snævar's Transforms module but that's not quite ready.
The sad part is using Prometheus would be so much easier, but apparently I'm not allowed to do that since it's reserved for production. Even easier would have been Graphite but that's not a thing any more. RoySmith(talk)17:51, 3 June 2025 (UTC)[reply]
RoySmith, Nice. Glad to know about this. I want to graph User:SDZeroBot/Category counter. The issue with time series it grows forever while Commons has a file size limit. One can create new .tab files for each year, but the plumbing works gets complicated on back and front end. — GreenC21:49, 3 June 2025 (UTC)[reply]
That was one of the nice things about graphite. It would time-compress older data so it took up less space. You could get (for example) 5 second resolution for the most recent data points, but the really old data might be aggregated to one sample every hour.
I'm thinking I'll want to store maybe 10 parameters, one sample per day. So maybe 200 kB per year which is trivial. If you've got a lot more data, maybe not so trivial for your use case. RoySmith(talk)21:58, 3 June 2025 (UTC)[reply]
I will not complain too much if this is still in development, but I am somewhat concerned about anything that forces content to be hosted on Commons without any local fallback. In my experience, stuff seems to randomly disappear from Commons a lot, and there is really no recourse except locally hosting it... jp×g🗯️13:50, 5 June 2025 (UTC)[reply]
OMG. I have written a module that takes input from Commons data. The system works very well. However, the data is generated by a bot which can easily write JSON. Editing the data manually would be totally stupid (too difficult, too easy to make mistakes, too hard for others to check). Conceivably there could be a wikipage where some simple formatted data was entered (wikitext) and a bot could periodically copy changes to Commons. But using Commons data would be laughably impractical without a workaround. Johnuniq (talk) 05:59, 3 June 2025 (UTC)[reply]
"But using Commons data would be laughably impractical" I still don't get why that is so unpractical. Is this because people don't want to go to Commons ? Why not ? All other media is primarily there as well. IS it because people don't understand JSON and only understand a simple key:value notation ? —TheDJ (talk • contribs) 09:37, 3 June 2025 (UTC)[reply]
When I looked at it (long ago in May 2020), the only way a human could update a number was to edit the whole JSON file, I think. I didn't worry about it because GreenC provided a bot which did all the hard work of maintaining the numbers and writing them in the correct format. I might be missing something, but I clicked 'edit' at c:Data:Wikipedia statistics/data.tab and saw a hard-to-follow table. I could handle it because I would suck it into a proper editor, search for what I wanted, check that it was the right thing, and change it. I suspect most Wikipedians would be uncomfortable with something so unfamiliar. I haven't seen an example of data for a graph—perhaps that works out ok? Johnuniq (talk) 10:05, 3 June 2025 (UTC)[reply]
@Johnuniq You might want to enable "Tabular Import/Export" gadget in your Commons preferences. It adds buttons to .tab pages to import and export from and to csv and excel files. It's 8 years old, but it still seems to work, even though it could really use an update. —TheDJ (talk • contribs) 10:45, 3 June 2025 (UTC)[reply]
Sure, for some value of "working with datasets". For anyone doing it professionally, it's a basic requirement. But for the average Wikipedia contributor, wanting a chart of their favourite sports team's performance, or their city's population over time..?
You don't need to edit the JSON, at least for updating the tabular data. There's an "Edit as Table" button up at the top when editing a .tab file. --Ahecht (TALK PAGE)14:22, 4 June 2025 (UTC)[reply]
@Pigsonthewing The button appears while editing, so e.g. [7]. Although on that page, when I click it, I get an error saying that "Dataset is too large to edit as a table", which honestly seems like a silly limitation… it's 50 kB of data, my computer has more than 1,000,000 times as much memory, surely it could handle it. It works on smaller pages, e.g. [8]. Matma Rextalk16:05, 4 June 2025 (UTC)[reply]
Probably that button should be more exposed than it is today. Perhaps with a treatment like VE two-button solution (providing both buttons on the top line) or like TemplateData, which has the 'edit with the special tool' link where it is displayed. Izno (talk) 16:14, 4 June 2025 (UTC)[reply]
Because most charts are single use, despite what most developers might assume, and every single chart requires 2 different pages to be created. For example, each Demographics wikipedia page (ie Demographics of India) has 2-4 charts (on average). Given the fact there are about 200 of these alone, there will be 400-800 pages in wikimedia commons just for this single use-case. Furthermore none of these charts are legitimately used outside of wikipedia, perhaps a different language would find it useful, but does that require 2 different files, why not have the option to just have one .chart file? It's easy to nest JSON after all. Additionally it is rather repetitive to create these files, so much so I have a bot request in wikimedia commons just for this purpose. GalStar (talk) 22:44, 3 June 2025 (UTC)[reply]
What I'm not seeing in any of the docs is how to select which columns I want to chart. Let's say I have a data set with 10 columns, but for a particular chart I want to show columns 1, 3, and 4. How do I do that? RoySmith(talk)22:14, 3 June 2025 (UTC)[reply]
Sigh. I really wonder what use case this extension is meant to address. It sure seems to have a non-optimal complexity:functionality ratio. RoySmith(talk)22:43, 3 June 2025 (UTC)[reply]
I'm rather inclined to agree. I personally am working on writing a bot to automatically port everything over, but I am worried about the effects of vandalism in wikipedia commons. GalStar (talk) 22:45, 3 June 2025 (UTC)[reply]
So how will transforms work in practice? mw:Extension:Chart/Transforms says it will allow you to insert Lua modules. That's fine, but I'm not planning to learn Lua just to be able to produce a chart. Will there be some library of sharable modules which do common operations? RoySmith(talk)16:26, 4 June 2025 (UTC)[reply]
No clue, I also don't know how to use lua modules. I think there will be shared lua modules, but from the looks of it, it will be very disorganized. GalStar (talk) 16:32, 4 June 2025 (UTC)[reply]
So, let's see. We have data arranged in tabular form. And we're inserting filters which transform that data into a different tabular form. Sounds like a problem that we've already figured out how to solve, so maybe somebody could build a transform which lets you just execute SQL. Which I'm sure is a bit of work, but given that SQLite and even LuaSQL already exist, probably not a huge job for somebody who has already figured out how transforms work. RoySmith(talk)16:57, 4 June 2025 (UTC)[reply]
In my experience (with data visualization in general, not the Chart extension), SQL doesn't work well for these use cases, because you can't do pivot tables in it (not without weird extensions). I expect that someone will write useful Lua modules to do it soon. Matma Rextalk21:01, 4 June 2025 (UTC)[reply]
@RoySmith Once transforms are enabled, someone could write commons:Module:Select columns that would allow you to do something like "transform":{"module":"Select columns","function":"show","args":{"1":"true","3":"true","4":"true"}} or "transform":{"module":"Select columns","function":"hide","args":{"2":"true","5":"true","6":"true"}}--Ahecht (TALK PAGE)17:43, 4 June 2025 (UTC)[reply]
FYI, Ive started making a bunch of improvements to mys csv and excel import/export gadget, with the goal of getting it where it could become a default gadget on Commons. —TheDJ (talk • contribs) 09:35, 7 June 2025 (UTC)[reply]
I've been working on a bot to generate .tab and .chart files from the {{Graph:Chart}} template. It started as a copy-paste thing, but at the moment it requires 2 inputs:
Name of the article
Names of each of the graphs
I have been trying to convert this into a true bot that doesn't require user intervention and was thinking that somehow using templates to mark graphs needing conversion as well as their names might be the best way forward. Is there any prior example of this that I could use as a template/scaffold?
There should also be an category for charts that could be ported over. So a category of transclusions that only use the arguments x, y, type, xAxisTitle, yAxisTitle, xAxisFormat and yAxisFormat. Anything else is wating for more development work on the WMF side. Snævar (talk) 09:06, 4 June 2025 (UTC)[reply]
I have an edit request for Graph:Chart, the main issue is adding the name and title parameters. Also it'd need to support y1, y2, ... and y1Title, y2Title, ...
This seems like a good way to prevent unsupported items from being ported over for now. (atleast until those parameters on Graph:Chart get added). GalStar (talk) 16:31, 4 June 2025 (UTC)[reply]
I will likely support porting them too. I have to first get my commons bot request approved, and am in the process of filing one for Wikipedia. After I have approval to operate, expanding the scope should be easier. GalStar (talk) 18:12, 4 June 2025 (UTC)[reply]
The old graph extension used the Graph:Chart template, this had width and height properties that allowed for this. However the new chart extension says that "Currently, charts occupy the entire container width where you place them". This is highly undesirable. I tried putting them in a div and then styling that div, but to little success as it causes weird scrollbars. Any ideas as to how to fix this? GalStar (talk) 22:09, 3 June 2025 (UTC)[reply]
I was planning on porting that from the german wikipedia as well, perhaps an admin could include this in common.css? GalStar (talk) 16:26, 4 June 2025 (UTC)[reply]
Common.css will not be modified for this. Since you're making a template for it, you should use WP:TemplateStyles.
It seems that some effort has been taken to hide how this works. I recently saw these edit on my watchlist (I'm about two days behind, due to real-life commitments), and if I hadn't also seen this thread, would have been very puzzled. Certainly, in a construct like {{#chart:Channel Tunnel Traffic.chart}} it's not at all obvious what this refers to; and if you edit the section and preview, a chart does appear but there's nothing to suggest where to go in order to examine the source data. Unlike an image, clicking the graph doesn't help. Contrast transcluded templates, where the preview provides a handy list. Contrast images, where you can click the image in order to get to the file description page, which may itself have a link to the original file page on Commons. So, having read the posts above, I know that it pulls information from c:Data:Channel Tunnel Traffic.chart; but that's only a tiny part of the story, since that page clearly does not have a list of points. Editing the page shows a line "source": "Channel_Tunnel_Traffic.tab" so there is also c:Data:Channel Tunnel Traffic.tab. What else am I missing? --Redrose64 🌹 (talk) 20:36, 4 June 2025 (UTC)[reply]
Oh haha, that was me actually. I am trying to fix this by force adding a "source" field. Hopefully ChartDisplay template fixes some of this confusion. GalStar (talk) 20:41, 4 June 2025 (UTC)[reply]
Oh and I'd like to add that some other edits of mine were accidentally reverted because they looked like vandalism. So it does seem like this confuses a lot of people. GalStar (talk) 20:44, 4 June 2025 (UTC)[reply]
I agree that this is obscure and difficult to follow. Looking at this example, I'm not understanding why Commons is a valid repository as the table includes column headings which are in English. It is therefore language-dependent and so should be stored in the English language Wikipedia like many other tables. Tsk. Andrew🐉(talk) 11:59, 5 June 2025 (UTC)[reply]
The headings can be multi-lingual, but no one translated them for that table yet. I added translations to Polish just now: [9] and this causes the chart to automatically render with these labels, like this: [10]. Matma Rextalk15:50, 5 June 2025 (UTC)[reply]
Thank you for clarifying.
It would be far better if commonly-used words and phrases could be transcluded, in the manner done (for example) on Wikispecies. We shouldn't need to add 200+ translations for word like "year", manually, to 1000s of charts. Andy Mabbett (Pigsonthewing); Talk to Andy; Andy's edits16:01, 5 June 2025 (UTC)[reply]
That can be done with a json file with the year translations, and fetched into each graph using chart's transform feature, see link in my former comment. That should also support adding translations to the graphs themselves (their individual tab pages), because some languages are context sensitive with declensions, even single word mentions. Using wikidata could also be done techically, using the Lua wikidata access, but that has linguistic issues. Snævar (talk) 11:04, 6 June 2025 (UTC)[reply]
I believe it's the comma after the month. In preview, changing "11:00, 3 June, 2025 (UTC)" to "11:00, 3 June 2025 (UTC)" causes it to hyperlink the timestamp, which is a sign it is then detected as a comment. Skynxnex (talk) 15:05, 3 June 2025 (UTC)[reply]
I think that's the issue as well. JeanetteMartin, in at least a few recent comments, your signature has used a non-standard date/time-stamp. Can you tell us more about what's going on? Many gadgets/tools/bots/scripts rely on uniform timestamps. Firefangledfeathers (talk / contribs) 15:57, 3 June 2025 (UTC)[reply]
JeanetteMartin made an odd double signature [11] where the second signature had a valid timestamp but she then deleted the second signature.[12] I guess the first signature was made manually. @JeanetteMartin: If you want a customized signature then use the signature field at Special:Preferences with a checkmark at "Treat the above as wiki markup". When you use the new topic tool or reply tool, your post is automatically signed with your signature in preferences. In other situations, sign with ~~~~. PrimeHunter (talk) 19:51, 3 June 2025 (UTC)[reply]
Its because the second signature is my deadname so I deleted that. And now I see its a bigger issue but I dont know how to fix it. Heck Im not even being allowed to log in! Jeanettemartinfortrump (talk) 12:20, 8 June 2025 (UTC)[reply]
Time precision
Hi everyone,
When using the Wd module to grab dates from Wikidata, how does one change the precision of the returned data? More precisely, I interested in just returning the year from what is usually a down-to-the-day date. Any ideas? Julius Schwarz (talk) 14:35, 3 June 2025 (UTC)[reply]
Thanks for the quick reply @Izno. Unfortunately, I would be using this within a module and I apparently cannot simply add {{#time:Y| before one of the functions of the module... Julius Schwarz (talk) 07:11, 4 June 2025 (UTC)[reply]
Maybe that's a neater solution that my tonumber(string.match( option. Can I just paste :formatDate() after a return X (like return X:formatDate())? Julius Schwarz (talk) 14:28, 4 June 2025 (UTC)[reply]
X needs to be a language object. If X is your date, you could do locallang=mw.getContentLanguage() and then returnlang:formatDate("Y",X)--Ahecht (TALK PAGE)15:25, 4 June 2025 (UTC)[reply]
Why was this changed? I normally check my daily edit patrol counts by going to User contributions for Maile66, click on Edit Statistics at the bottom,and then it takes me where I can find the info. What happened? I can't even find my daily patrol counts. Everything got changed, and I can't find anything. Why? And does anyone know how I can quickly and easily find my Page Patrol counts. Thanks for your help. — Maile (talk) 01:19, 4 June 2025 (UTC)[reply]
I never noticed the "Edit Statistics" link, but I personally use the "User" submenu added by Twinkle (see below) and then select Analysis -> Analysis - XTools. — BE243 (about | talk) 01:57, 4 June 2025 (UTC)[reply]
Yes, the edit stats link does show for me at the bottom of the page. But clicking on that is supposed to take you to the full XTools page, where you can find the patrol stats. Looks like someone fixed this since I orginally posted it. Everything is fine now. Thanks for addressing this. — Maile (talk) 02:03, 4 June 2025 (UTC)[reply]
Could I request the tag ooze (display as and target to: OOZE) for my new script? Similar tags exist for Twinkle, Huggle, RedWarn and Ultraviolet. Thank you :) Ed (talk) 21:00, 4 June 2025 (UTC)[reply]
@Nardog That's a good question. The tool is still in development awaiting release. Having the tag there and ready for release (and beforehand for testing) is important for transparency and clarity that the edits are being performed by an automated tool. Currently I am using the RedWarn tag for the time being. Ed (talk) 12:30, 5 June 2025 (UTC)[reply]
@Nardog: I should point out that if it doesn't end up used, it can just be deleted fairly easily. The only way it couldn't be deleted is if it was attached to more than 5000 revisions, which on its own would suggest it is being used. EggRoll97(talk) 17:42, 5 June 2025 (UTC)[reply]
Toolforge down?
I get an error message when I try to run this operation. This just happened about 3 weeks ago. I let Legoktm know but he hasn't been active this week. Any ideas? Is there a Phab ticket open? LizRead!Talk!23:55, 4 June 2025 (UTC)[reply]
Your title makes it sound like all of Toolforge is down. Is the problem just with this one tool? Which error message do you get? The page works for me. Just now I clicked the blue button, then it spent about 1-2 minutes displaying "Loading...", then it displayed 5 results. –Novem Linguae (talk) 01:11, 5 June 2025 (UTC)[reply]
It looks like it is working now, thanks for the feedback. For what it's worth, this was the error message:
How would we link discussions to an issue list in Wikipedia? It would be painful to maintain the links in the issues list, but if they were manually tagged (as a sort of reversed short code) then could we have a search that shows a link to discussions and dates.
The DC attorney email discussion email made me think of this. It has generated a lot of discussion, which is related to many more discussions/RFCs. Each of those discussions has many comments (full of issues or possible solutions) with the same issue or solution being repeated many times (and often lost in the detail). Wakelamp d[@-@]b (talk) 06:06, 5 June 2025 (UTC)[reply]
An issues list the first step in problem solving techniques used in Issue tracking system or a quality system or a testing system. or a risk management system Our current process on ideas and proposals etc is that a problem and solution are stated together, We get lost in alternate solutions and then don't reach consensus
Example ban all anonymous editors everywhere as they are creating vandalism on Pokemon pages
Then people comment that
it's not a problem/issue (what proof exists? It is not so in my experience)
its not the correct venue (is it just certain IPs - talk to checkuser, have you discussed this on the Pokemon project?)
a solution exists(Why not semi protect Pokemon?)
other discussions or essays have discussed this (have you looked at x y z)
the benefit does not exist
the solution wont work (ideas)
My thoughts is that this process should be an issue called reduce vandalism, then a sub issue called ban anonymous editors which people can tag. I want to try it and see if it works and then put a link in proposals. Sort of like a perennial issues lists Wakelamp d[@-@]b (talk) 09:03, 5 June 2025 (UTC)[reply]
and to be clear, I just want to try it and see if I can make it work as a proof of concept, I just don't know how I would create a tag that can be picked up by a search against each issue. Wakelamp d[@-@]b (talk) 10:47, 5 June 2025 (UTC)[reply]
So the idea is to create Phabricator-like tickets for RFC-like issues on English Wikpiedia, so that you can get bug tracker features such as tagging and giving tickets a parent/subtask relationship? –Novem Linguae (talk) 14:00, 5 June 2025 (UTC)[reply]
Nothing as big as phab/bugzilla/Jira. No one would use it, its too much work., and there are no tasks; we are trying to create a list of problems and see how commonly they are mention. Say [[ISSUE:12]] is the tag prefix (it could be just ##1234)
Village pump discussion discussion XXXX
users are attacking editors on their user page user Alice
-- it's because the revert has a link to the editor page user Bob
--- [ [ ISSUE:12 ] ] [ [ ISSUE:14 ] ] user3
The Issue page would have headers issue number, description, query showing linked pages and a count,
Issue:12 Attacks on editor pages, query, 212
Issue 14 : Revert process does not clearly state what do next
Ignoring the why, there is nothing to stop you putting together such a list in a 1) sandbox or 2) WikiProject. Sometimes there are to do pages like MediaWiki talk:Common.css/to do for long-term tracking of work projects.
Considering the why, if you have wide but specific issues you'd like to address, usually those are best discussed on the policy and guideline pages associated with those issues. Coincidentally, you will also likely find what previous thought has been regarding each of your concerns in the archives of those pages, with occasional pointers to large RFCs held elsewhere. Izno (talk) 20:41, 5 June 2025 (UTC)[reply]
@Izno I am not actually trying to address the issues I mentioned. They were just easy examples, and I have read previous discussions on them.
I can create the list, but I don't know what a tag would look like (a category, a short code, a hash code) whether I am allowed to tag a few discussions to create a proof of concept, and how to create a search for that tag.
@Izno @WhatamIdoing the why. I think village pump discussions might be improved if we could create structured outputs, our problem solving approach might be improved if we had an agreed list of issues, and we should use the same processes that we use on articles such as categorising.
What do I mean by structured data? In main space, talk pages help create the structured output of an article. We don't have anything like that for community discussion. We could create one article per community discussion as a structured output, but I don't think that would help as much because discussions often discuss multiple areas An issue table with two way links would be the first step Wakelamp d[@-@]b (talk) 23:17, 5 June 2025 (UTC)[reply]
I am not actually trying to address the issues I mentioned. They were just easy examples, and I have read previous discussions on them. Of course, but I can think of very few or no things which don't already have a policy or a guideline page that exists to hold what we've come to believe is the consensus about the topics you might see as problematic. There are some pages that even hold consensus or pointers to previous discussions. For example, see WP:VG/S#Reliable sources, which links to previous discussions about those sources.
We could create one article per community discussion as a structured output This would be overly bureaucratic I think. (Aside, this sounds like you want the summary feature of mw:Extension:Flow.)
Hello, for some reason (perhaps I clicked something) when I click Wikipedia links on Safari on my iPhone 15, it has started opening the pages in the standalone Wikipedia app. I keep the app around for occasional use, but would really prefer that clicking a Wikipedia link does not kick me off my browser (even if it loads mobile view despite the phone requesting desktop view). Is there a setting I can fiddle with I'm missing, either on Safari or the app, that stops this behaviour without deleting the app? Thanks, CMD (talk) 06:30, 5 June 2025 (UTC)[reply]
FWIW, I had fixed the reported problem before Graham87 fixed it in a different way. I tried the first recommended fix, and it didn't seem to work, so I went with a system that I was familiar with. I think yearly archives are more user-friendly than "Archive 1", "Archive 2", etc., which give no sense of time. YMMV. – Jonesey95 (talk) 13:02, 6 June 2025 (UTC)[reply]
@Jonesey95: Ah I see now that you'd fixed it *after* the first two messages were posted here. I for one saw the whole "Archives: 2025, 2026, 2027" thing that you created as bizarre (because it isn't that standard here) and was running off that; what you and the first two posters here saw was ... a lot weirder (and is indeed what happens when ClueBot III is misconfigured). FWIW I don't think messages from 2011 and 2012 (and previously 2022) should be in an archive titled with the year "2025" (also see the text starting "ClueBot III will put all of the threads into a single file, not multiple files ..." in the relevant documentation for ClueBot III, which points out that lowercase sigmabot III can create yearly archives in a way that makes more sense to me *personally*). Also, that page went many years without substantive messages (save InternetArchiveBot notifications), so I think even yearly archives are overkill there (especially because the GA review will only be archived along with another section because it doesn't have a header of its own). Furthermore, we have {{Yearly archive list}} for standardising the display of yearly archives. (I won't lose sleep if you *really* want to change it to yearly archives at this point, but I think they'd be better with lowercase sigmabot III as I discussed previously. Graham87 (talk) 14:40, 6 June 2025 (UTC)[reply]
Ahhh!!! I need more shortcut
template is tooo long. It would be nice to have a shortcut "TL: ".
A link to (eg) TL:Wikipedia will go to the Tagalog Wikipedia, as it uses the language code TL. Language codes will always go to the relevant language Wikipedia, so we cannot use those as a local shortcut. Andrew Gray (talk) 17:16, 5 June 2025 (UTC)[reply]
Is it possible to use user scripts in editing with the mobile web edit version? This will be helpful for editors when using the mobile web version of Wikipedia. Migfab008 (talk) 04:56, 6 June 2025 (UTC)[reply]
common.js and global.js are loaded on the mobile site too. If a script you've installed in one of them doesn't work with the mobile editor, then it means the script doesn't support it. Nardog (talk) 13:41, 6 June 2025 (UTC)[reply]
Why do I keep getting notifications that "Topic ' Wikidata weekly summary #678 ' was archived or removed from User talk:[Username]", for multiple users? I have not edited the individual Wikidata user talk pages concerned; nor am I mentioned in that issue of the newsletter Andy Mabbett (Pigsonthewing); Talk to Andy; Andy's edits12:25, 6 June 2025 (UTC)[reply]
The Wikidata weekly summary is also delivered to many user talk pages at the English Wikipedia. You didn't give an example so I'm not sure whether the notifications are about edits at Wikipedia (like [13]) or Wikidata. I tried subscribing to User talk:No Swan So Fine/Archive 13#Wikidata weekly summary #678 and I was then automatically subscribed to the newslettter section on all pages at the English Wikipedia. I guess you did the same here or at another wiki. If you unsubscribe at one section at the same wiki then you are also unsubscribed at all sections. You can disable archiving notifications at "Talk page archiving" at Special:Preferences#mw-prefsection-echo. PrimeHunter (talk) 13:30, 6 June 2025 (UTC)[reply]
The way discussion tools keeps track of what section you subscribed to is by looking at the username and timestamp of the first signature. The idea behind this is that if someone moves a section or renames the title of a section, you do not lose your subscriptions. Unfortunately this means that if you subscribe to something that has been copied pasted to hundreds of users, such as a mass message, you'll be subscribed to every mass message, since they have an identical first signature. –Novem Linguae (talk) 14:11, 6 June 2025 (UTC)[reply]
When I'm in the article editing window, I can select all the text and code without any problem, but when I'm looking at the article and I try to select it, it selects every single thing, including what's outside the article. Can that be fixed? -- Valjean (talk) (PING me) 15:25, 6 June 2025 (UTC)[reply]
@Valjean: It works for me. Does it work if you log out or try here in safemode? Which browser or device are you using and which method to select text? Please also link an example page. It's possible to make code which interferes with mouse operations and we don't know whether you only tried a page with something special. Always give an example when you report an issue. PrimeHunter (talk) 16:15, 6 June 2025 (UTC)[reply]
I have tried on my own user page and on Denmark. I use Firefox and am editing with a brand new laptop (Lenovo Gen 12 ThinkPad X1 Carbon Laptop with Intel Ultra 7 165U vPro Processor, 14" WUXGA 100% sRGB Touchscreen, 32GB 6400MHz RAM, 1TB Gen4 Performance SSD, FHD+ IR+ RGB Camera, and Windows 11 Pro).
On both pages, when I right click and use "select all", the whole page gets chosen. When I do it on a very large article, my previous PC would lock completely for hours, forcing me to reboot, sometimes losing work. I have learned not to do that, not even as a test. -- Valjean (talk) (PING me) 20:54, 6 June 2025 (UTC)[reply]
Right-click, "select all" is a browser feature and it is not possible for a web page to change its behavior directly. What can be done instead is:
Place the article content in a <frame> or <iframe> element
Or using JavaScript, either:
Add a button at the top of the page for "select all" or "copy"
Override the associated keyboard shortcut (Ctrl+A on Windows), taking care to not change its behavior when an element such as a <textarea> has focus
Override the entire context menu
Watch for selection changes, and if the entire page is suddenly selected, change the selection to only the article content
I don't know how to use "safe mode", but when I tried selecting on that example page, it does it. No better there. -- Valjean (talk) (PING me) 20:57, 6 June 2025 (UTC)[reply]
If I understand correctly, you are trying to select just the article content, and not the surrounding tool and menu bars.
This is not possible using the default browser context-menu (right-click) "select all" feature.
I believe the easiest ways to do this, are to either:
(1) Click-and-hold on the first character of text in the article, and then drag your mouse to the bottom of the window, so that it auto-scrolls, and wait until the entire page is selected, then release your mouse.
(2) Just click (without holding) on the first character of text in the article, then scroll to the bottom, and shift-click on the last word in the article. This should result in the same thing.
(edit conflict) @Valjean: My above link automatically uses safemode with safemode=1 in the url so you didn't have to do more. "Select all" is a browser feature to select all as it says, where "all" may mean all the text in a box you are writing in. It sounds like the feature is working as intended. Maybe you just don't know how to only select chosen content. One method: Drag your mouse over the content by holding down left-click from start to end. Another method: Left-click at the wanted start, and then hold down shift while using the keyboard to navigate to the wanted end. Ctrl+⇧ Shift+End jumps to the end of the whole page including the interface. If you do that and keep holding down shift then you can use arrows to back up a little. Is that good enough for your purpose? And why do you want to select a whole article? If it's for printing then the normal print feature in your browser should automatically print the article without the interface. If that fails then try "Printable version" under "Tools" and "Print/export". PrimeHunter (talk) 22:53, 6 June 2025 (UTC)[reply]
@Valjean:?safemode=1, or &safemode=1 if the url already has a ?. But my link already has it in the url so all you had to do was click the link. However, it doesn't do what you want so just forget it for this discussion (it can be helpful for other things). I misunderstood your original post. I thought the normal way to select chosen text was not working for you so I suggested two things which might stop something interfering with the selection. But you apparently wanted to select all text except the interface without having to choose the text. That's just not possible without non-trivial changes to our code. PrimeHunter (talk) 23:39, 6 June 2025 (UTC)[reply]
Not really. Why can't an article be in a "box" that is separate from the surrounding "stuff" (tabs and links) we use as editors? The article is part of the encyclopedia, whereas that stuff, including the talk page, is not. -- Valjean (talk) (PING me) 16:10, 7 June 2025 (UTC)[reply]
An edit by an IP on 25 January 2025 added a bunch of stuff and <hr/>. That is probably what is fouling it up. Some of the stuff added seems to be what was previously behind a single link, namely Western Europe. Perhaps {{Campaignbox Seven Years' War}} should be reverted back to the 1 March 2023 version? The wikiproject might have an opinion on that. Johnuniq (talk) 11:09, 8 June 2025 (UTC)[reply]
Rationale of the proposer: The main effect would be to officially recommend using HTML superscripts and subscripts instead of Unicode subscripts and superscripts (e.g. 2 instead of ². This has generally been done on a de facto basis, for example in widely used templates like {{convert}}, {{frac}}, and {{chem2}}. I estimate only about 20,000 out of about 7 million articles use the Unicode characters outside of templates, mostly for square units of measure or in linguistic notation that should be put into a template. A lot of articles have already been converted to the HTML method, either organically or systematically.
This would also bless the exceptions for linguistic notation, which have arisen after complaints from some editors of that topic, who say these Unicode characters are specifically intended for that purpose.
The other exceptions and sections are I think just summaries of other guidelines, put in one place to help editors who are working on typography or e.g. asking the on-site search engine "how do I write subscripts?" when they really want to know how to write chemical formulas specifically. -- Beland (talk) 04:14, 20 April 2025 (UTC)[reply]
Support upgrading to guideline. I don't see any reason not to and this looks like good advice. However, I am also no expert on HTML/Unicode, so if some compelling issue with this proposed guideline emerges, please ping me. Toadspike[Talk]09:11, 20 April 2025 (UTC)[reply]
Support as good HTML/Unicode practice. However, it could be good to have input from editors who might be more directly affected by this (maybe editors who use screenreaders?) to make sure this will not cause any unforeseen accessibility issues. Chaotic Enby (talk · contribs) 12:59, 20 April 2025 (UTC)[reply]
For context, the reason Unicode characters are allowed for only 1⁄2, 1⁄4, and 3⁄4 is that these are the only fractions in ISO/IEC 8859-1; others can cause problems, according to Graham87 comments at Wikipedia talk:Manual of Style/Mathematics/Archive 4#Accessibility of precomposed fraction characters. The only superscript or subscript characters in ISO/IEC 8859-1 are superscript "2", "3", "a", and "o". I would expect using HTML superscripts and subscripts consistently should avoid screenreaders skipping unknown characters (certainly mine reads out footnote numbers). I use a screenreader for convenience and not necessity, though, and I welcome comments from others! -- Beland (talk) 17:41, 20 April 2025 (UTC)[reply]
Oppose Support. Wikipedia talk:Citing sources is currently having extensive discussions about which rules apply to citations and which do not. Beland (talk·contribs) is heavily involved in these discussions. I believe those discussions should be resolved before any new related guideline are created. Failing that, I notice the essay has no mention of citations. This means whoever wrote it wasn't giving any thought to citations. Therefore an prominent statement should be added that it does not apply to citations. Jc3s5h (talk) 13:24, 20 April 2025 (UTC) The RFCs about citations have been resolved, leaving the status quo in place. And the essay does mention citations, although I didn't notice it because it wasn't very prominent. Maybe it should be in a more prominent place so an editor who comes to the essay looking for information about citations can find it. Jc3s5h (talk) 20:01, 19 May 2025 (UTC)[reply]
I don't think anyone is proposing to use Unicode superscript characters for endnote indicators? It seems reasonable for endnote contents to follow the general guidance on the use of superscript and subscript markup. isaacl (talk) 17:09, 20 April 2025 (UTC)[reply]
I think Jc2s5h means that if the original title of the magazine article is "e=mc²: How a simple formula change the world" (using the Unicode superscript) then WT:CITE is talking about whether it should be 'legal' to replace that ² character with a <sup>2</sup>. (What they're really talking about is whether, if one magazine capitalizes their titles as "Man In The Moon" and the next as "Man on the moon", these different approaches to capitalization can be put in the refs of the same FA or FL and called "consistent", in the sense of "consistently accepting whatever quasi-random capitalization style is used by each individual source without regard to whether it looks consistent compared to the neighboring refs", but if "copy each separate title with no changes of any kind" is accepted, then replacing a ² with <sup>2</sup> would probably also fall in that range.) WhatamIdoing (talk) 21:05, 26 April 2025 (UTC)[reply]
HTML subscripts and superscripts should also be used inside citations. At the end of the section MOS:SUBSCRIPT#General guidelines it says: These guidelines also apply in citations [...]. This is fine. Subscript and superscript are just a matter of typesetting, replacing unicode subscripts with HTML subscripts doesn't change the meaning. Joe vom Titan (talk) 18:12, 27 April 2025 (UTC)[reply]
@Jc3s5h, any interest in changing your vote now that WT:Citing sources#RFC on consistent styles and capitalization of titles has reached consensus against treating capitalization used by sources as an acceptable citation style? With that discussion closed and this essay noting that "these guidelines also apply in citations and template parameters," it seems clear that if promoted, it would not be an an acceptable citation style to retain whatever super-/sub-script formatting is used in the source title. ViridianPenguin🐧 (💬) 16:06, 19 May 2025 (UTC)[reply]
Support with the obvious exceptions of references to characters themselves. I don't see why citations would have an exception here. Headbomb {t · c · p · b}10:50, 21 April 2025 (UTC)[reply]
Support elevating the essay as written to a guideline. It appears to give good practical guidelines for how to deal with most common situations, including the remark that it should apply inside citations. This is the only way to ensure consistent formatting since there are only few subscript and superscript unicode characters. Joe vom Titan (talk) 18:12, 27 April 2025 (UTC)[reply]
Here via WP:RFCC. There's obvious consensus to support here but I'm wary of closing an RFC on a new guideline with such low participation. I'll put it up on CENT. -- asilvering (talk) 19:34, 17 May 2025 (UTC)[reply]
Support, looks reasonable and sounds like it aligns with existing best practice, though I wonder if it is worth adding an explicit exception to confirm that the degree symbol ° should be kept for the normal scientific uses (temperature, arc measurement, etc), rather than using {{sup|o}}. The section about music notation using the two approaches interchangeably confuses things a bit. Andrew Gray (talk) 20:47, 17 May 2025 (UTC)[reply]
No one objected to remove the degree symbol from the template or music guidelines, so I did so and converted articles using the removed parameter. -- Beland (talk) 18:29, 26 May 2025 (UTC)[reply]
Although the degree symbol was historically derived from a masculine ordinal indicator, in modern usage it is not a superscript letter o, either visually or semantically, and it would be quite wrong to use <sup>o</sup> for degrees. I'm not sure why ° would be preferred to a character that is in ISO-8859-1, however. Rosbif73 (talk) 13:57, 26 May 2025 (UTC)[reply]
If the guidelines in MOS for degree signs never change, the recommending the template is not necessary and ° should be preferred. However, if most articles use the template and the guidelines change, then a change to {{degree}} automatically brings those articles into compliance with the new guidelines. I don't understand the last sentence, since the value of ° is the 8859-1 degree sign. -- Shmuel (Seymour J.) Metz Username:Chatul (talk) 14:18, 26 May 2025 (UTC)[reply]
No articles use ° - all instances of that have been converted to U+00B0°DEGREE SIGN and database dumps are scanned for new instances every two weeks. It would save some work if we didn't encourage people to usethe HTML entity; it's easy enough to add from a phone keyboard or the desktop special characters pull-down. -- Beland (talk) 17:43, 26 May 2025 (UTC)[reply]
If people need a way to enter special characters without touching their mouse, I would recommend {{subst:degree}} for this one. -- Beland (talk) 18:45, 27 May 2025 (UTC)[reply]
I also agree that the degree symbol should be an exception, as the intended Unicode symbol is semantically different from a superscript o. I agree with Beland's change to the music template to standardize things there. Chaotic Enby (talk · contribs) 18:52, 26 May 2025 (UTC)[reply]
Yes, it's time to just implement it. The things people are discussing below were just suggestions by the closer, not part of the consensus; the key point is that the articles should not be left in mainspace, and even the gentle suggestion by the closer (which was in no way part of the close or consensus, and is in no way binding the way the requirement to remove them from mainspace is) has been met, since more than enough time has passed for people to review any articles that they believe were salvageable. Further steps forward can be determined after that part is implemented, but constantly re-litigating a settled RFC is inappropriate. --Aquillion (talk) 18:26, 19 May 2025 (UTC)[reply]
The closing statement by @HJ Mitchell says, in part:
"However, I would urge the proposers not to charge headlong into the draftification process without further thought. A lot of people are uncomfortable with the large number of articles—a list of 1200 people from different eras and different nations is very difficult for humans to parse and I would urge the proponents to break it down into smaller lists by nationality, era, or any other criteria requested by editors who wish to evaluate subsets of articles. I would also urge care to ensure that the only articles draftified are those which clearly meet the criteria outlined, even if that takes longer or even considerably longer—we won't fix mass editing without due care by mass editing without due care. There is merit in the idea of a templated warning being applied to the articles before draftification takes place and in a dedicated maintenance category to give interested editors a chance to review. To that I would add a suggestion to check for any articles that exist in other language versions of Wikipedia."
What's your plan for breaking down the lists, avoiding more "mass editing [including draftifying] without due care", and adding warning templates in advance? WhatamIdoing (talk) 21:33, 26 April 2025 (UTC)[reply]
Did you break it down into smaller lists by nationality, era, or any other criteria requested by editors who wish to evaluate subsets of articles? Or is it your idea that this part of the closing summary has magically expired because it wasn't done by your WP:DEADLINE? WhatamIdoing (talk) 22:34, 10 May 2025 (UTC)[reply]
I'm not sure what you mean, I ask as the quote WAID posted explicitly states it. Could you link to which criteria were requested? CMD (talk) 16:47, 11 May 2025 (UTC)[reply]
The closing summary gives them as examples to be requested by editors who wish to evaluate subsets. Are there editors who wish to evaluate subsets, and have they requested these? CMD (talk) 16:59, 11 May 2025 (UTC)[reply]
Firstly, why? Secondly, the discussion that was closed with the summary quoted above, this discussion, and probably other discussions in between the two.
If that is not enough for you, please take this as formal request to break down the list into smaller lists by era and nationality. Thryduulf (talk) 17:16, 11 May 2025 (UTC)[reply]
Because that's what the close is looking for in quite plain language? It's a quite late request, but if you genuinely want to look through them I'll give you a couple. CMD (talk) 17:19, 11 May 2025 (UTC)[reply]
I really don't understand why this is like pulling teeth? Yes, this is a genuine request to do what has been requested multiple times by multiple people in multiple discussions. Thryduulf (talk) 01:42, 12 May 2025 (UTC)[reply]
It is very hard to take that last claim seriously as you refuse to provide any links. Anyway, here are some to start you off. CMD (talk) 02:12, 12 May 2025 (UTC)[reply]
Thank you, finally, for the lists but I don't understand why you need explicit links to the discussion we are currently having and a link to the original being referenced many times. The Australian list alone has 170 entries (which is still really too large for managability, hence the requests for nationality and era), so it's going to take a long while to do a Propper search on just them (and I'm just about to go to bed). Please be patient and remember that this could have started over a year ago now. Thryduulf (talk) 02:19, 12 May 2025 (UTC)[reply]
I don't need links to the current discussion or the original discussion. I was asking for links to what the close asked for, for people to request specific divisions. If they didn't happen then please stop insisting they did. If the request were not made, that has nothing to do with me. I was barely involved in the prior discussion. CMD (talk) 02:35, 12 May 2025 (UTC)[reply]
The "finally" is quite a particularly perplexing comment, these lists were produced less than a day after the first request. CMD (talk) 02:37, 12 May 2025 (UTC)[reply]
That was explicitly framed as a suggestion by the closer, not as part of the consensus. It has no weight or force whatsoever. --Aquillion (talk) 18:27, 19 May 2025 (UTC)[reply]
Chamindu Wickramasinghe – Sri Lanka – sources have been added, needs to be removed from the list. The draft note has already been removed from this article (in June 2024)
So? It is not up to those who don't think there is a need to delete/draftify the articles en-mass to work out which ones those who do believe that is a desirable course of action are referring to, let alone without the latter group having done what was explicitly noted as a prerequisite to deletion/draftification. Thryduulf (talk) 16:33, 11 May 2025 (UTC)[reply]
Jay, I agree: You've had more than a year at this point to follow the directions in the closing summary and break it down into smaller lists by nationality, era, or any other criteria requested by editors who wish to evaluate subsets of articles. Time enough? WhatamIdoing (talk) 16:49, 11 May 2025 (UTC)[reply]
Yes, I would support draftify-ing those articles sooner rather than later, especially before Wikipedia reaches the 7 million articles mark. Some1 (talk) 14:04, 11 May 2025 (UTC)[reply]
Can I point out that there's a talk page for this at Wikipedia talk:Lugstubs 2 list. I've already gone through a bunch of these articles, mainly New Zealanders, to suggest those that might be kept, those are, in my view, a merge – which retains the page history and is a valid WP:ATD – and those that might be deleted. Some have been improved. I've not gotten to all of them by any means. But that's somewhere that anyone about to make any of these a draft needs to have a look at first please. I've not done any work on these lists for a while as it's so time consuming and I'm not sure when I'll get a chance to look again, but a clear procedure for reviewing these was put in place. Ta Blue Square Thing (talk) 10:55, 12 May 2025 (UTC)[reply]
e2a: a quick look through the British and New Zealand ones suggests all are either keeps or redirects – I note a number that have had suitable sourcing added and some with suitable levels of detail, other than the ones that I'd worked through. I imagine the same is true of the Australians as well – an ATD will be available on almost every case if they haven't has sourcing added. I'm not entirely sure that the original list is really that valid from the POV of these subsets if I'm honest. It's certainly not a job that I would like to automate based on the list as it exists Blue Square Thing (talk) 11:07, 12 May 2025 (UTC)[reply]
I'm working through the New Zealanders – 70+ done. There's an interim list at User:Blue Square Thing/sandbox3#NZ. Once I'm done (a few weeks I imagine – I have 22 left) I'll push that list to the same talk page as above
At Wikipedia talk:WikiProject Cricket The-Pope has broken down the Australian list into state teams, which is really helpful. But these will take a while to get through
The instructions on the {{Special draft pending}} tag say that when sources have been added, the tag shouldn't be removed (why?), but instead the article should be listed at Wikipedia talk:Lugstubs 2 list for review.
However, so far, over the course of the last year, almost 200 articles have been individually reviewed and listed there (either with a recommendation to redirect or with sources), and this work has been ignored. The editor who wrote these instructions is no longer editing.
Should we:
Tell people to just remove the tags when they redirect or add sources? (This would require re-generating the list.)
Find some volunteers who will actually follow up on the chosen process? (I believe the process was boldly made up by one editor; I've seen no evidence of discussion, much less consensus.)
I really don't know what is the most effective way to do this. I can see the benefit to removing them as someone works on articles, but it involves removing them from two places. There certainly seems to be evidence that articles have been worked on without notes left on the talk page, so I'm not sure it's reliable to ask people to remove from two places.
It makes sense to redirect as we go though. Ultimately this is a human task – unless there's a really clever way to do it, I don't think it can be automated due to the need to redirect a huge number of the articles – in the original discussion I estimated 75% were redirects
On that subject, there was some discussion about the best way to do the draft/redirect process. MY gut feeling is that it's redundant to send articles to draft, have someone bring the article back to mainspace, and then redirect the article – the draft isn't deleted automatically and that creates more overheads. I think. A straight redirect is better I think
But it's difficult to do this when the tags are still on the articles, I agree. I would have started to do that last March, but for the process that was put in place... It will, fwiw, take some time Blue Square Thing (talk) 19:17, 13 May 2025 (UTC)[reply]
If people pulled the template off the page when redirecting/improving, then we should be able to combine (e.g., with grep) the original list against the list of pages that transclude the template, to find which ones are still in need of work/eligible for being moved to the Draft: space. WhatamIdoing (talk) 21:25, 13 May 2025 (UTC)[reply]
Changing the template message just involves going to Template:Special draft pending and clicking the [Edit] button. However, I don't know how the opponents of these articles would feel about that. What if somebody adds a source and removes the tag, but they think the added source isn't good enough to justify keeping the article in the mainspace? They might prefer more bureaucracy. WhatamIdoing (talk) 18:11, 14 May 2025 (UTC)[reply]
I've now managed to work through all the British and New Zealand articles. Of the 50 British ones, seven need to be removed from the list as sources have been added, and the other 43 are probably redirects – although a number of them (at least 12) have significant possibilities (i.e. I know that if I could expend the time on them that they'd almost certainly have sources added). Of the 89 New Zealanders, one needs to be drafted, 40 have had sources added, and 48 can be redirected (with strong possibilities for 10 or so at least). The detail is at Wikipedia talk:Lugstubs 2 list. I'm about to start on the Zimbabweans.
Perhaps someone could let me know what they'd like me to do next? There's a list of 1,106. A great many of them will be redirects or drafts, but at the minute the note added to the top of each page stops me doing anything very much to those articles – one Charles Chapman (cricketer, born 1860) (British but not appearing on the British list for some reason) has been merged with Charles Chapman (rugby union) as they were the same person, but the article still appears on the original list. I have no idea what an automated attempt at this process would do to an article like that, but I can't imagine that any automated process will work, I can't remove the list, I don't think I'm allowed to redirect them, and I'm pretty certain I'm not supposed to remove them from the list.
Speaking only for myself, I'm annoyed by the fact that we had a lengthy discussion that came to a consensus to do something, and then didn't do it, and that we've had articles that have been allegedly pending being moved into draft space for years. I don't care much more about the procedure than that we get out of that state. * Pppery *it has begun...18:44, 18 May 2025 (UTC)[reply]
So if BST removes the tags for the ones they think shouldn't be draftified, and pulls them off the list, then you're okay with that? WhatamIdoing (talk) 18:46, 18 May 2025 (UTC)[reply]
Well, I tried to support it being done if someone wanted to do it. To be honest, I don't completely understand the situation, but if it helps I think the ones that @Blue Square Thing describes as probably redirects should probably be redirected? Or if the draft tags don't allow that, drafted. Enough time has gone by in my opinion if they're still unsourced -- don't know whether there was an already-fixed timeline?
If I'm understanding this correctly, I think we should just let people go through and draftify/redirect them all (except the sourced ones), removing the tags. If there are some that sources could be found for, well, new pages can always be created later with the sources. Mrfoogles (talk) 18:57, 18 May 2025 (UTC)[reply]
None of these are unsourced articles. The ones on this list were chosen because they:
were created by an editor who fell out of favor with the community, and
are sourced (only) to specific websites.
The tag was boldly created by an editor and suggests a new/unprecedented process that, e.g., claims that redirecting an article to a suitable list would still leave that redirect subject to draftification and eventual deletion. I suspect that his intention was to personally review any article that others thought was eligible to be left in the mainspace. However, he has since stopped editing, so we can't ask him how he thought this would work out in practice. WhatamIdoing (talk) 19:23, 18 May 2025 (UTC)[reply]
Part of the problem is that you have to know where to redirect them to. Which is slightly tricky. Sometimes lists don't exist, which means we draft; sometimes you need to choose a list from options, which is OK but tricky. I can start to do that, but it takes time and is slightly difficult as it tends to rely on having accessed to a paywalled source. But it needs doing – the current situation is starting to get silly and I share the exasperation of Pppery because I could already have dealt with a couple of hundred of these
At least four have already been sent to draft and then the draft deleted. I thought the process we have here guaranteed that they wouldn't be deleted from draft space for five years? (from memory) That doesn't appear to be happening – for whatever reason Blue Square Thing (talk) 19:29, 18 May 2025 (UTC)[reply]
They were probably just draftified independently of the RfC without putting the tag on them.What about just draftifying everything you (or others) haven't already redirected or otherwise exempted via introducing IRS SIGCOV, then you can get started on deciding which other pages to redirect/exempt from within draft space? JoelleJay (talk) 16:15, 19 May 2025 (UTC)[reply]
I was/am interested in working on this myself – I didn’t mean to imply with my comment that it’s somebody else’s problem. 3df (talk) 21:08, 18 May 2025 (UTC)[reply]
Any that have not already been individually assessed as probably meeting notability criteria (or as being redirectable) should just be draftified. The whole point of their getting privileged draftification treatment was so that interested editors had 10x time to trawl through these articles after they were removed from mainspace: I find that there is a rough consensus in favour of the proposal, and a stronger consensus that they should not be left in mainspace. They don't get to hang around indefinitely in mainspace just because the same editors who staunchly opposed the consensus neglected to show any interest in the non-mandatory close recommendation of making more discretized lists (which are supposed to make it easier for the post-draftified articles to be parsed, not as a way for one editor to adopt a set beforehand and delay its articles' draftification by claiming they "need more time" to run through them individually). We most definitely do not need a second RfC to ratify the first one, and a year is more than enough for any editors who cared to ensure draftification is only applied to eligible articles. The rate-limiting step here cannot be the inaction of the same editors opposing draftification, that would completely defeat the consensus to remove these from mainspace. JoelleJay (talk) 20:25, 18 May 2025 (UTC)[reply]
The rate-limiting step appears to be the inaction of the editors supporting draftification.
The immediate question here is, for the (small?) subset that has "already been individually assessed as probably meeting notability criteria (or as being redirectable)", how do we stop them from wrongly getting dumped in the Draft: namespace?
This would be a stupid process:
BilledMammal puts a page on his list of pages to dump in the Draft: namespace.
Alice reviews one. She decides that it does not meet the GNG and redirects it to a List of Olympic athletes from Ruritania.
Bob draftifies everything on the original list, including Alice's new redirect.
Chris un-draftifies the redirect, because it's stupid to have a redirect in the Draft: space when Alice has already determined that this athlete doesn't appear to qualify for a separate, stand-alone article and has already redirected it.
No. I am saying any that are already redirected or clearly ineligible can be removed from the list, any that are not are draftified NOW by an admin, per the consensus that these stubs should not remain in mainspace. The accidental draftification of false-positives is of minuscule concern: editors have 5 more years to go through them. JoelleJay (talk) 23:03, 19 May 2025 (UTC)[reply]
Why the rush? As @HJ Mitchell pointed out in the close, it is more important to get it right than to do it quickly. There are currently multiple people actively working out what doing it right means. Thryduulf (talk) 23:38, 19 May 2025 (UTC)[reply]
I wonder whether the auto-deletion process in the Draft: space has been modified to accommodate this five-year timespan. I suspect that the answer is "no". WhatamIdoing (talk) 00:59, 20 May 2025 (UTC)[reply]
One year is not "doing it quickly". If the editors who believed certain articles ought to be exempted just never bothered to address those articles, then that's too bad for them: there was a consensus to remove the articles from mainspace and into a protected draftspace where they could be worked on, and a stronger consensus not to leave them around in mainspace for some indefinite length of time while some editors maybe work on some selection of them. You and WAID contributed like 50 comments in the RfC unsuccessfully trying to kill the proposal, now you're trying to do the same thing to its implementation. At some point this just becomes disruptive. JoelleJay (talk) 03:29, 20 May 2025 (UTC)[reply]
Please read this entire discussion where all your complaints have been fully addressed and/or rebutted multiple times. I'm not trying to kill it's implementation, I'm trying to ensure that the damage to the project is minimised by ensuring that the due care the closer found consensus for is actually applied. If that takes longer than you want, then I'm sorry but the community wanted due care rather than haste. Thryduulf (talk) 03:41, 20 May 2025 (UTC)[reply]
Yet the consensus was that it is more damaging to the project that these articles remain in mainspace, and it certainly did not include your definition of "due care". JoelleJay (talk) 03:53, 20 May 2025 (UTC)[reply]
Instead of talking about hypothetical "editors who believed certain articles ought to be exempted just never bothered to address those articles, then that's too bad for them", how about we talk about "the editors who did address those articles, and who are addressing those articles, and who have been addressing those articles for over a year now, but who have been told that they're not allowed to take the tag off or remove the articles from the list"?
This process has been badly designed, with incomplete documentation, instructions that contradict normal practices, no tools to separate these drafts with their RFC-mandated five-year time period in the Draft: space from the ordinary six-month G13 process, and an implicit dependence on an editor who is not editing any longer. One goal (i.e., boldly redirect articles that editors believe won't qualify) is simple and straightforward under normal circumstances, but it's being stymied by editors who are trying to follow the directions they've been handed, because the tag says nobody's allowed to remove it.
If we want to move forward on this, then we need to figure out things like how (e.g.,) Liz and Explicit identify Draft: pages that are eligible for G13 deletion, and how they could not have their systems screwed up by these pages, which aren't eligible for five years.
We need to get this right. I've no sympathy for people who ignored this for the last year and a half, but now that we've been reminded about it, they think it's an emergency. People have been posting on the designated talk page for well over a year, and their questions and comments have been ignored by you and everyone else who just wants these pages gone. If you don't choose to help, then that's fine, but the result is that sorting out this process is going to take longer. WhatamIdoing (talk) 05:04, 20 May 2025 (UTC)[reply]
Hang on, we were explicitly told not to remove the hatnote and not to redirect. That was supposed to be handled sensibly – multiple reassurances were given at the original RfC and since. If someone were to draft all those with the hatnote remaining, you'd send articles which obviously meet the GNG to draft – there are hundreds that either were in the original process or that need to removed from the list – almost 50% of the New Zealanders for example. That would, in my view, be likely to be used as an argument against any future mass-draftification of articles. Any support that I was able to give to the original RfC was based entirely on the assurances received that redirects would be handled sensibly. I imagine I would feel I had been lied to if they were simply all drafted without any consideration for the process that I've been working my arse off on for periods of the last year Blue Square Thing (talk) 08:48, 20 May 2025 (UTC)[reply]
The proposal says
If this proposal is successful: All articles on the list will be draftified, subject to the provisions below: [...]
Any draft (whether in draftspace, userspace, or WikiProject space) can be returned to mainspace when it contains sources that plausibly meet WP:GNG[d]
Editors may return drafts to mainspace for the sole purpose of redirecting/merging them to an appropriate article, if they believe that doing so is in the best interest of the encyclopedia[e]
}}I imagine any resistance to removing hatnotes or redirecting would be due to concerns the article would just be recreated from the redirect without undergoing scrutiny for GNG and without having the hatnote returned. Maybe it would be helpful to have a hidden category for redirects from this list and/or a talkpage banner noting they were originally part of LUGSTUBS2 on them as well as on any pages that are returned to mainspace as GNG-compliant. Anyway, I don't see why we can't just draftify the pages that haven't been worked on by you guys (or that you have found non-notable), while separately addressing redirection/removing hatnotes for those that remain. JoelleJay (talk) 17:45, 20 May 2025 (UTC)[reply]
A talk page banner might be more helpful – cats can get deleted easily.
In terms of what to draft and when, it would be more efficient to redirect first where a redirection is possible. In some subsets, this is nearly all articles; in other subsets it will be fewer. It would be possible to work fairly quickly through those I think – over the last day or so I've reviewed all 170 articles on the Australian list. 147 of those can be redirected in the first instance (a number having strong possibilities); 23 need to be kept. None need to be drafted. Of the 89 New Zealanders, one needs to go to draft. The others are all redirects or to be removed from the list and kept. The same won't be true of Pakistanis, for example, where there are a lot fewer lists for redirection.
I'm not entirely sure how it would be possible to identify those that have been worked on btw. I've come across some today which other people worked up but haven't left a note anywhere about Blue Square Thing (talk) 20:09, 20 May 2025 (UTC)[reply]
The practical reason why we can't just draftify the pages that haven't been worked on by you guys (or that you have found non-notable) is because you don't actually know which ones haven't been worked on.
The ones that can be redirected can be put in a new list, removed from the original list, and a banner put on their talk pages. The ones that BST et al have determined should be kept can likewise be put in another list and a banner put on their talk pages. The ones that others have since worked on but which have not been actively endorsed as demonstrably meeting SPORTCRIT can be moved to draft alongside all the other eligible pages for the individualized attention that the community decided should take place in draftspace. JoelleJay (talk) 20:50, 20 May 2025 (UTC)[reply]
That makes sense. The banners are a good idea – who will create them? Can I check:
a) that we're talking about dealing with the list at WP:Lugstubs 2 list (1,106) – these are the ones that were tagged with the hatnote? This is not the same list as the one at WP:LUGSTUBS2] (1,182). I can't remember why they're different – I think everyone on the first list is on the second one. From memory I think the query was re-run and some came off it. They had probably been improved to the extent that they dropped off the list
b) where would you like me to create the lists? Wikipedia talk:Lugstubs 2 list is a bit of a mess because I've stuck so much stuff on there and the lists that are on there are messy as well
c) I think the original idea was to re-run the query again first to remove the ones that would have fallen off the list. I wouldn't have a clue how to do that. Is that something someone could do? It might save a bit of time and effort
Once we have the banners made and an idea about where to create the lists, we're good to start moving on this I think. Is it worth discussing a formal timeframe? Blue Square Thing (talk) 07:55, 21 May 2025 (UTC)[reply]
Whichever is the most recent agreed-upon list should be used. We can run a new query on it, then look over any pages that no longer qualify through the query to make sure their disqualification is legitimate. I think the three new lists (redirectable, likely notable, all remaining eligible stubs) can just be put in a new talk page section. I don't know anything about making banners or running quarry queries; perhaps @Pppery has background or knows editors who do? JoelleJay (talk) 16:33, 21 May 2025 (UTC)[reply]
I have some familiarity with Quarry queries, but it's not clear to me what is being asked for right now. Or, one you have a clear request, you can ask at WP:RAQ (although that's largely a single-person operation too). * Pppery *it has begun...16:46, 21 May 2025 (UTC)[reply]
I think the intent is to just run the same query as before on the current list to see if any other names now need to be removed? JoelleJay (talk) 17:07, 21 May 2025 (UTC)[reply]
I think that would be best. It would also be best to actually deal with the ones that have been sorted out before re-running the list. Do you have a link to the query?
I'm 99% certain that the list at WP:Lugstubs 2 list is the list that had the template added to it. I know of at least two articles where editors have removed the template, but that list hasn't been edited since BilledMammal put it there, so it should be reliable Blue Square Thing (talk) 17:49, 21 May 2025 (UTC)[reply]
One of the inefficiencies in Wikipedia talk:Lugstubs 2 list#2025 procedure is that, for redirecting non-notable subjects, I think we need to remove the template from the page and the name from the list. But if we are reasonably certain that everything on the list got tagged with the template, I'd love to simplify this to "anything still transcluding the template is getting moved" (after a reasonable but short pause to get those known-non-notable subjects redirected). WhatamIdoing (talk) 17:58, 21 May 2025 (UTC)[reply]
I've only found two without the template, and I've looked at getting on to 750 of the articles over the last week. If at all possible it would be better to use those using the template (the other two have easily good enough sourcing I think – Alexander Cracroft Wilson and Chamindu Wickramasinghe) and then conduct a check with the quarry query afterwards or run through and check them some other way. There doesn't seem to have been any mucking around with the list other than the three (not four) which were drafted early and have since been moved back to mainspace e2a: a look at the number of articles with the template, shows that there are six more somewhere where it's been removed. I'll sort out which at some point by comparing the lists Blue Square Thing (talk) 18:07, 21 May 2025 (UTC)[reply]
23 June. That goes everyone a month. If it goes a bit further than that then fine, but a deadline in this case is probabyla good diea to stop me from prevaricating Blue Square Thing (talk) 19:02, 21 May 2025 (UTC)[reply]
That sounds good to me. I've updated the directions to state that date. I've also removed instructions to edit the list itself. We can use the templates themselves to track it. (I assume nobody's spammed the template into other articles; if my assumption is invalid, then we'll have to check the list.) WhatamIdoing (talk) 21:00, 22 May 2025 (UTC)[reply]
I actually managed to do some myself yesterday morning (the Auckland redirects), but had a ridiculous day at work so wasn't able to leave a note here. It sees to work, although it's slightly trickier that I thought – need to remove the class rating from the talk page and the circular redirect from the list as well. I also added R with possibilities to the ones I did as they're ones that I think have that. Oh, and in some cases we can redirect to a section...
It would be better if we could re-run the querry that BilledMammal used in the fist instance as there are 400+ articles I've not managed to check – the Sri Lankans and Indians. But if we can't do that, I think this is the best option Blue Square Thing (talk) 04:26, 23 May 2025 (UTC)[reply]
AIUI the WikiProject banner figures out redirects automatically, so you can ignore those. We should be able to get a bot or an AWB run to handle the circular redirects. (Surely we have a bot that can do this?) WhatamIdoing (talk) 05:06, 23 May 2025 (UTC)[reply]
I've started more work on these – it's just the class on the redirect talk page that I'm slightly worried about.
The special draft pending template still says to remove people from the list. Do we actually want to do that or does the template need changing to remove that? Blue Square Thing (talk) 17:04, 24 May 2025 (UTC)[reply]
@Blue Square Thing, ignore the class on the redirect's talk page. A while ago, we updated Module:WikiProject banner to auto-detect redirects and ignore whatever the banner incorrectly claims the class is. Eventually, a bot will remove it (but it's basically a WP:COSMETICBOT edit, so it won't happen quickly).
Here's a potentially useful option. Many of these articles have a see also section with a link to a list. One potential solution is that if the article still meets the criteria (which will need to rechecked obvs) and if it contains such a link, it gets redirected to the list that's linked; if multiple lists are linked someone tells me and I sort it out (this is rare fwiw)
Fwiw I rather think this has been a lot more complex than everyone expected it would be. I did start working on this in March 2024, after the list was finalised. The original rfc included multiple assurances that redirects would be dealt with sensibly. I think we can do that, but I'm waiting to be told how to do it Blue Square Thing (talk) 04:21, 19 May 2025 (UTC)[reply]
Agree that if there is a clear and obvious redirect target then redirecting there is far more appropriate than draftspace for the article, as per WP:ATD. Joseph2302 (talk) 19:12, 19 May 2025 (UTC)[reply]
Yes, it could be. It would mean that the draft article would stay as well however, which is inefficient from a storage post of view. It would involve double the work involved, as rather than simply redirecting the articles I'd have to move them back and then redirect them. Blue Square Thing (talk) 08:33, 20 May 2025 (UTC)[reply]
But wouldn't you have to do such move for any articles you end up working on in draftspace anyway? Moving to mainspace and then redirecting is just one more trivial step than what was already expected to happen if this RfC got implemented. JoelleJay (talk) 17:51, 20 May 2025 (UTC)[reply]
Given the numbers of articles that will end up as redirects – as above, of the 170 Australians, 23 are keepers right now and the other 147 are all redirects; not a single draft – it would be a lot more efficient for me to just have to do the redirects. I have them sorted in teams anyway, so the redirection notice will essentially be the same. Given that I've ploughed through all of those over the last 28 hours, I don't see why I couldn't manage the redirection process over a similar sort of timeframe for those 170. Having to bring back from draft first, more than doubles the time it would take – I'd have to do all the drafts first to keep the note I'd need to place in the reason box and then go through and do all the redirects by team afterwards. That's really adding to the work – all of it by hand. From a technical efficiency perspective, it must also be better to not have absolutely unnecessary drafts kicking around for five years either. All I need is for someone to work out exactly what process to go through and to have a bunch of people agree it. I'm not sure how long it would take to do work through the full 1,100 and come up with a list to draft, but it wouldn't be that long so long as I'm in the country and able to work at it Blue Square Thing (talk) 20:15, 20 May 2025 (UTC)[reply]
I don't see any reason not to redirect most of, if not all of the remaining articles as well, unless I am missing something here? Let'srun (talk) 23:54, 24 May 2025 (UTC)[reply]
We don't always have lists to redirect to – so, for Afghan cricketers, for example, I don't believe there's a suitable list. I've managed to redirect the New Zealanders who need redirecting and have started to remove tags from those I think we should keep, but it's a slightly complex process to do by hand. It will take a little time to get it done right Blue Square Thing (talk) 14:04, 25 May 2025 (UTC)[reply]
This process is now under way. I'm focussing on removing tags and redirecting. It takes a long time and all has to be done by hand. If anyone can figure out a way to automate any or all of the process it would really help. In particular, I've stopped doing anything to the talk pages – it's just taking so long. Thanks to all the people who have been cleaning them up, but if there were an automated way to do this it would really, really help matters. I'm aware that I'm leaving work for other people to do in the short term. I will try and return to the talk pages if I can do, but sorting out the articles seems like a sensible priority in the relatively little time I'll have to do this
I think the fact that redirecting was not actually easy was the entire reason why draftification was chosen in the first place. Frankly, I favoured just straight deleting them and if there's a WP:LUGSTUBS3 that will get my !vote. FOARP (talk) 11:01, 2 June 2025 (UTC)[reply]
The assurance that redirection would be handled automatically was the only reason I was able to give any support to the original proposal. Unfortunately BilledMammal is away for at least most of the rest of this year otherwise that might have happened. I appreciate that people wanted to punish Lugnuts by removed their articles entirely, but there are clear ATDs in many cases and redirection would have almost certainly been the result of AfD discussions in the cases where there are realistic ATDs. So I'll keep going. If you could look through the 200+ Indian articles and see if any have had loads of sources added it'd help massively. Thanks Blue Square Thing (talk) 11:32, 2 June 2025 (UTC)[reply]
The reason why I prefer straight deleting is because recreation of the content worth keeping (which is minimal) is way easier and cleaner. Redirects are cheap... to create... FOARP (talk) 14:18, 2 June 2025 (UTC)[reply]
To be clear, are we redirecting the ones with no substantial edits, or draftifying them? Taking the first on the Indian list, C. R. Mohite, since they were an Umpire what is the redirect target supposed to be? List of Baroda cricketers? But then is it even verified that he played for Baroda rather than just coming from there? Draftify looks like a way easier option.
BTW to me this was never about "punishing" Lugnuts. This was about saving editor time vs a massive time sink with minimal value-creation that was negligently dumped on us. FOARP (talk) 14:28, 2 June 2025 (UTC)[reply]
I've redirect the first ten in the list, none of which had any source but ESPNCricinfo and so were straight-forward NSPORTS fails. FOARP (talk) 14:49, 2 June 2025 (UTC)[reply]
Thanks for doing what you're doing there. I really appreciate anything that anyone else does to help this process. The key is to find the small number of articles where sources have already been added and that need to be removed. Then redirecting.
Yes, redirect to wherever is most obvious – any that cause significant problems shout and I can check on CricketArchive, which is paywalled unless you know the way around it – so Mohite played 25 matches for Baroda, but the redirect you have is just as good.
Redirects, for me, have other advantages. They make re-creation of the article as a duplicate more difficult and retain cross-wiki links (Mohite is linked from multiple pages, for example). Drafting removes those. Eventually we might get notes added to articles – like on List of Otago representative cricketers for example – which summarise careers and so on. The problem, of course, is that that takes time. More clarity over the process from the get go and a set of lists organised in some way are all things that would make that easier if we do this again. Blue Square Thing (talk) 14:55, 2 June 2025 (UTC)[reply]
Honestly, we should just delete these articles and save ourselves the time, and then use the time save to create real articles. But if redirecting is how we're resolving the issue right in front of us today then that's how we're resolving it. I'll do the others in the India list after work. FOARP (talk) 15:21, 2 June 2025 (UTC)[reply]
None of the first ten anyway. For all the protestations that time was needed, in reality no-one was doing anything nor was there any obvious signs of the intent to do anything. Even if it wasn't intended, the effect of this was simply to suspend the decision for a year with no obvious improvement. FOARP (talk) 08:52, 3 June 2025 (UTC)[reply]
I think having them sorted into lists of countries **really** helps. Knowing what sort of sources are available for each country does as well. It would be better to present future lists by country (preferably by team); I think it's much more likely that the process gets done better and quicker if we can do that. Shorter lists will help as well – give me 50 New Zealanders and I can tell you what needs to happen to them within a few weeks. BilledMammal largely not being here to shepherd the process obviously hasn't helped fwiw Blue Square Thing (talk) 10:59, 3 June 2025 (UTC)[reply]
CricketArchive, which is paywalled unless you know the way around itIs there an easier way than inspect>sources>refresh>pause load? That's how I've been doing it the last few years. JoelleJay (talk) 23:06, 2 June 2025 (UTC)[reply]
Hitting Esc quick enough also works I believe. Or if you can still find it, I have Opera 12 installed - the last update before they moved the browser to Chromium I think. For some reason it ignores the redirects to the paywall. Obviously it's years out of date now, but it's the only thing I use it for and it seems to work Blue Square Thing (talk) 07:14, 3 June 2025 (UTC)[reply]
Picking a random name Arnell Horton (Arnell Stanley Horton), there is more information available about him, but even what was in the stub has not been copied to the notes field on the redirect target. Better to do this slower without losing the information. All the best: RichFarmbrough20:18, 2 June 2025 (UTC).[reply]
I appreciate that we're, at least temporarily, losing information, but there's just so much to do. I'm going to copy the lists of names on to the talk pages of the teams the redirects have been done to so that we know which ones need to be gone back to. I have no idea how long it would take to copy across as we worked through, but I might have two or three half-days available until the deadline and that'll be about it Blue Square Thing (talk) 07:14, 3 June 2025 (UTC)[reply]
I took a look at the Zimbabwe list. Dobbo Townshend is clearly notable. I've redirected a couple more. But most of the other ones don't have clear redirect targets and should probably be PRODded. SportingFlyerT·C00:07, 4 June 2025 (UTC)[reply]
The whole point of LUGSTUBS was to draftify these articles in a protected draftspace rather than going through the PROD/AfD process for each individually. JoelleJay (talk) 16:05, 4 June 2025 (UTC)[reply]
Update: All but the British, Indians, and Sri Lankans are just about done. I know what's probably happening to the British articles, so my calculation is that of the 805 articles that have been dealt with (excluding Indians and Sri Lankans), 695 have been redirected to a list of some kind or developed and removed from the list, I've PRODed 7, which leaves 104 to send to draft. It's about 13.7% being drafted or PRODed. I've not calculated how many have been removed from the list after having been improved or as false positives (a handful) – gut feeling says around 75–100, maybe a little less. Sri Lankan lists are scarce, so that will probably increase the percentage of drafts. I'm not sure about the Indian lists Blue Square Thing (talk) 08:41, 4 June 2025 (UTC)[reply]
Indians are all done 65%ish redirect or keep the article fwiw, but I didn't look too hard for places to redirect to. Just the British and Sri Lankans to do now Blue Square Thing (talk) 20:46, 6 June 2025 (UTC)[reply]
Sri Lankans all done – just a 22% redirect rate. I think we now know how to deal with these sorts of articles more effectively if we wanted to do this again Blue Square Thing (talk) 07:55, 7 June 2025 (UTC)[reply]
Split "additional considerations apply"/"marginally reliable" from "no consensus" at RSP
Currently, the "additional considerations apply" and "no consensus" statuses have the same "MRel" yellow grouping at WP:ReliableSourcesPerennial. This has caused some confusion for closers and those unfamiliar with what RSP actually is: a summary of past consensus and not any sort of guideline; "no consensus" makes a source's status "no consensus" instead of preserving the previous status. This also makes it a bit harder to differentiate "consensus for additional considerations" from "no consensus".
Thus, I propose we split out "additional considerations apply" and "marginally reliable"—as the new version of MRel colored Codex's purple200 (#d9d0e9)—away from the now-separate "no consensus" category that retains its yellow color. This purple provides sufficient color contrast against foreground text and seems the most friendly to colorblind people. This proposal would update the RSP legend, change the options in future source-reliability RfCs, and sort existing MRel sources.
Against This was proposed recently, I was against then, and I still am. Yellow means some variant of "stop and think, consider if this is really the best source for the information", the distinction between "no consensus" and "marginal reliability" is effectively the difference between pale bright yellow and faded bright yellow. Headbomb {t · c · p · b}16:13, 10 May 2025 (UTC)[reply]
One has full consensus behind spending time thinking about this one and detailed directions on how to, as opposed to the far more general "we're not sure if this source is reliable, double-check".
This is what I said when you said this during the "proposed recently" you mention, which is an idea lab workshop and not a proposal. Aaron Liu (talk) 16:30, 10 May 2025 (UTC)[reply]
I agree that these two terms should be seen differently. I've thought about the colors (which should be yellow and which purple) and think it makes sense to make MRel purple, since MRel sources are reliable in specific cases, while "no consensus" sources are not necessarily reliable for anything. Thus, I support this proposal. Toadspike[Talk]16:46, 10 May 2025 (UTC)[reply]
To me "no consensus" is a subset of "additional considerations apply", the consideration being that there was no consensus on the sources reliability. If a close is unclear it can be discussed with the closer, and updated if necessary. The issue as I see it is how editors interpret MRel. The currently colour gives the idea it's between generally reliable and generally unreliable, which isn't true. MRel means you need to read the entry as it's not as simple as GREL/GUNREL, not some gradient between the two. Maybe the solution is to change the colour for all MRel entries. -- LCU ActivelyDisinterested«@» °∆t°16:47, 10 May 2025 (UTC)[reply]
Removing the stigma of MRel could also help with other inconsistencies in the list. At the moment sources that are reliable in general, but not in specific situations, are listed as green or yellow depending on the source. These could both be moved to the new colour that indicates nothing other than you must read the sources entry. -- LCU ActivelyDisinterested«@» °∆t°16:50, 10 May 2025 (UTC)[reply]
I agree with what you say about MRel besides the part on "no consensus". No consensus means there was disagreement between which of options 1-4 to pick. Almost always, this is disagreement between options 1 and 3, making the source's reliability somewhere between these indeed. "No consensus" does not mean participants realized a part of the summary that you need to read, unlike "additional considerations apply". Aaron Liu (talk) 16:54, 10 May 2025 (UTC)[reply]
No consensus is just another additional consideration, what would be best in such cases would be to summarise the majority opinions in the discussion so later editor could see a quick overview. -- LCU ActivelyDisinterested«@» °∆t°09:53, 11 May 2025 (UTC)[reply]
No we shouldn't. Such entries should not be green, the desire to have them green is because editors try to abuse the MRel status (as shown in the diff about the Telegraph). Only sources that have a consensus that they are reliable in all areas should be green. Arguing that as it's green it's reliable is as bad as arguing it's yellow it must be removed. Per my comment below anything without a clear consensus for the whole source should just have its colour removed. -- LCU ActivelyDisinterested«@» °∆t°11:01, 14 May 2025 (UTC)[reply]
Only sources that have a consensus that they are reliable in all areas should be green.
That goes against the plethora of sources split into several entries by topic, some of which are green.If "arguing it's yellow it must be removed" means we should drop yellow, why shouldn't we drop green as well? They are the same level of useful. Aaron Liu (talk) 01:58, 15 May 2025 (UTC)[reply]
Green should be for sources that there is a definite answer for, that could include a definite answer for a certain aspect of a source. It is obviously different than an slee of sources that are all different for different reasons. -- LCU ActivelyDisinterested«@» °∆t°12:54, 28 May 2025 (UTC)[reply]
Green is not a definite "reliable". Green status has misled editors into keeping a source no less than yellow has removing. Besides Jacobin back in the eons it was green, see also A.V. Club's consideration to identify AI-generated content, BBC's many different sections some of which are questionable, and Aon whose common different types of data is often different from what editors believe it is. Those (except BBC, which should maybe just have a separate entry) would benefit from an "additional considerations" status but did not receive one—I say due to stigma. That these aspects were from consensus is irrelevant to the fact that green is no more definite than additional considerations in what to do with a source.Additional considerations can also include a definite answer for a certain aspect, and I haven't heard from you yet why those should be lumped with entries that are just boilerplate no-con text with standard reminders should. Separation would make it much more distinguishable at-a-glance. Aaron Liu (talk) 01:03, 29 May 2025 (UTC)[reply]
Why shouldn't we separate "definite consensus on certain aspects and definite consensus it is otherwise generally reliable" in MRel from "no consensus"? Aaron Liu (talk) 11:23, 29 May 2025 (UTC)[reply]
Disruptive editing based on "no consensus" or other "additional considerations" closes are unfortunately common, but the misuse of "no consensus" closes is no less common than the other MRel closes. The issue is how editors misinterpret the whole class, not a subjection of that class. -- LCU ActivelyDisinterested«@» °∆t°14:19, 12 May 2025 (UTC)[reply]
I believe that's only because "no consensus" and other MRel closes are grouped in the same class, which is why we should separate it. Aaron Liu (talk) 19:38, 13 May 2025 (UTC)[reply]
I would suggest removing the colour from all the MRel entries. Editors are just going to start to assume purple is not green, in the same way they treat yellow. Splitting out 'no consensus' results from other similar 'additional considerations' results won't change this behaviour. The "'Green' -> 'Any other colour it doesn't matter' -> 'Red'" spectrum is the issue. Instead change it so that only those with a consensus that the full source is either generally reliable/unreliable have a colour (green/red), and all other don't. -- LCU ActivelyDisinterested«@» °∆t°10:54, 14 May 2025 (UTC)[reply]
Ah for some reason I hadn't thought of that lol. After looking around a bit I think gray600 for dark-mode blacklisted entries might work alongside ActivelyDisinterested's compromise, which I support while preferring my proposal.On "Editors are just going to start to assume purple is not green,"—which I just realized I hadn't addressed—I say they're not and will not have the same connotations with purple as with yellow, as there's nothing with purple that suggests caution. It's a value-neutral and distinct color. The same logic applies to why people won't assume no-color is not green. And in the end, this proposal is reversible. Why not give it a try and see the response and impacts? Aaron Liu (talk) 00:52, 29 May 2025 (UTC)[reply]
How could the logic be the same you suggestion is to separate out how certain results are recorded, thereby changing there status. Mine was to have all those results remain as one category but modify how they are all recorded. As I said seemingly so long ago now purple will become value laiden because of it's use, that it isn't now isn't the point. -- LCU ActivelyDisinterested«@» °∆t°08:09, 29 May 2025 (UTC)[reply]
The same reason grey won't become value-laden in your use applies to purple as well. In fact the only value purple could get is "there's a caveat to the source's general reliability" instead of yellow's connotation, while the latter's far more negative value would transfer to grey in your proposal, no? Aaron Liu (talk) 11:21, 29 May 2025 (UTC)[reply]
As I think I said last time, there isn't any practical difference between "consensus that additional considerations apply" and "no consensus that the site is either generally reliable or generally unreliable" so I don't see the benefit in making the list more complicated. Especially as it would lead to arguments about what happens if there is a discussion that leads to no consensus between MREL and either generally reliable or generally unreliable? Thryduulf (talk) 16:53, 10 May 2025 (UTC)[reply]
There is. For example, Jacobin is generally reliable for its reporting but almost always publishes opinion pieces and thus needs additional considerations. Here's another example:
Editors consider Social Blade, a social media analytics website, reliable when it comes to objective statistics and data. This does not apply to the site's "grades", "rankings", and "estimated earnings" information, which have dubious methodologies. There is consensus that Social Blade is ineffective in determining notability as it is a primary source.
These very much cannot be replaced by "no consensus".
what happens if there is a discussion that leads to no consensus between MREL and either generally reliable or generally unreliable?
I don't see how such a scenario could occur; if it did, it should probably be "no consensus" while noting the consideration that some editors supported. And even leading to such arguments is better than the current case where "no consensus" and specific considerations and warnings are conflated. Aaron Liu (talk) 17:01, 10 May 2025 (UTC)[reply]
I didn't say there was no difference, I said the was no practical difference - i.e. what the person evaluating a source currently marked in yellow needs to do/know is the same: The source is neither generally reliable nor generally unreliable, you need to read the entry (and possibly the associated discussion) to understand why and in what way.
I don't see how such a scenario could occur when you have two groups of editors, one arguing that it's of medium reliability and the other arguing that it's generally (un)reliable, with neither group's arguments gaining consensus. Thryduulf (talk) 17:11, 10 May 2025 (UTC)[reply]
There is usually little more value found in reading "no consensus" statements than reading "generally reliable" statements. With a few exceptions, the bulk of those do not specify topics (except specifying "don't use for contentious topics" for no consensus, a designation which effectively already says that). As a result, editors often just take either just "GRel" or "no consensus" at face value. This contributed to The Telegraph (which has a separate entry for trans topics) being blanket removed from all citations within GenSex in the initial fallout chaos of that RfC. Meanwhile, it is absolutely required to read "additional considerations" statements. That's the practical difference.
one arguing that it's of medium reliability and the other arguing that it's generally (un)reliable
I don't see how an argument between "additional considerations apply" and GUnRel would happen. Instead, wouldn't the two groups have consensus that Source is unreliable in Topics, and debate between GRel and GUnRel for the other topics? Aaron Liu (talk) 17:21, 10 May 2025 (UTC)[reply]
Agree with Thryduulf and Headbomb that this is unnecessary. I feel that it's likely to lead to more red tape and arguments over what each color means; and in general RSP seems to be working as-is, so I'm opposed to major suggestions for revisions unless there's a very clear need. The distinction would imply a degree of sweeping certainty that I don't think RSP ought to assert. The basic point is that if something is yellow its use is debatable; the degree to which guidance is provided by the discussions differs and has to be decided on a case-by-case basis. I also don't agree with the assertion that a no-consensus outcome cannot provide useful guidance; in fact, many of the existing yellow RSP entries say something along the lines of "there's no overall consensus about its reliability but many people who weighed in do agree on [basic guideline boundaries]", eg. definitely don't use it for X or its fine for Y. --Aquillion (talk) 18:40, 10 May 2025 (UTC)[reply]
Because many people wanted to impose additional considerations as a mechanism to prefer other sources when possible, which is what WP:MREL means in practice. Immediately after the entry was added to RSP, editors began removing [The Telegraph] from articles. Special:Diff/1233432855 — User:Chess16:29, 7 August 2024 (UTC)
Anecdotally, such removals were very widespread.
I also don't agree with the assertion that a no-consensus outcome cannot provide useful guidance
Indeed they can and there's many examples, but NoCon entries at RSP overwhelmingly do not provide useful guidance beyond "no consensus". Out of the 6 no-consensus results for entries from U to Z, 4 do not. It's all at most basic reminders of "expert-authoreds are reliable", "don't use this for exceptional claims", "prefer other sources", etc., which apply to all sources at such levels of community trust. Aaron Liu (talk) 11:52, 12 May 2025 (UTC)[reply]
If anything, we should get rid of green. The major problem I think, is green becomes: 'go, don't think about it, how its used, or what for.' Alanscottwalker (talk) 18:51, 10 May 2025 (UTC)[reply]
The purpose of green is "stop bringing querulous arguments to RSN" - since the purpose of RSP is to document consensus from RSN. Obviously this won't work on the sort of person who needs to hear it, but at least others tell them to go away in fairly short order. It's also useful for cases like Sky News Australia (fringe source) versus Sky News UK (normal NEWSORG) - David Gerard (talk) 21:22, 10 May 2025 (UTC)[reply]
Like I said at the idea lab, apart from the detail of the specific colors used I support this proposal, and disagree strongly with the suggestion that no consensus is the same, either formally or practically, as a consensus that additional considerations apply."No consensus" is a lack of guidance either way as to whether a source is reliable. "Additional considerations apply" is not just not a lack of guidance, it's often much more and more specific guidance than we have for most sources. They are total opposites and do not in any way imply the same thing, and the fact that some people appear to have the misconception that they do is in my view even stronger evidence for splitting them. Loki (talk) 21:44, 11 May 2025 (UTC)[reply]
If we decide that there is no consensus on how to rate a source, then it seems to me that is covered by Option 2, having a specific no consensus option will just result in many sources being labelled as that, which I don't think is particularly helpful in resolving the question of whether the source is usable, if people think the source is not reliable then !vote that, if reliable, that and if not sure, then option 2 works. Selfstudier (talk) 12:21, 12 May 2025 (UTC)[reply]
I don't want a specific no consensus option either. I thought the current predominant RfC options list included "No consensus" as option 2 (as seen in the 2024 Telegraph RfC) instead of "Additional considerations apply"/"Marginally reliable". Also, this would probably change the number of option 2 since it's a different scale. We would probably see something like "Option 1: GRel, Option 3: GUnRel, Option 4: Deprecate, Option A: Additional considerations". Aaron Liu (talk) 13:24, 12 May 2025 (UTC)[reply]
Still not sure if this would be improper, but hopefully it isn't; Pinging participants of August 2024 discussion: @Barkeep49, Levivich, Chess, Selfstudier, and Barnards.tar.gz:. Thryduulf, ActivelyDisinterested, and LokiTheLiar also participated but are already here.Another example of the stigma associated with the current combination can be found in a discussion on Vox's opinion content. Most participants later rejected the premise that there was an additional consideration for Vox, but that doesn't make exchanges like these any less exemplary of the hesitance to label additional considerations as additional considerations thanks to its current grouping that seemingly makes it insinuate, emphasis mine:
I agree Vox tends to wear its opinions on its sleeves, but when you distill out the facts, they are still reliable and engage in proper editorial practices. As more and more sources take this type of accountability journalism approach, I think we can't rule out their reliability, just know when the writer is speaking in a subjective voice versus an objective voice (eg per WP:YESPOV). We need editors to be fully aware of how to use such articles, not only from Vox but other sources in the future. — User:Masem 15:03, 3 December 2021 (UTC)
Do you think it should be yellow to alert editors to this? I fear if it's green, editors will just adopt it in wikivoice without question, and any editor who questions that will be told it's green at RSP, end of discussion. — User:Levivich 15:21, 3 December 2021 (UTC)
Given that what's happening with Vox is indicative of many other nominally reliable sources, I don't think it should change as the source is still good, but one just has to be more careful of what's included in wikivoice. — User:Masem 16:05, 3 December 2021 (UTC)
The current grouping also causes newcomer confusion in reading things; when Jacobin was changed to no consensus, TarnishedPath said: I've changed it back to Green, as your own close found no consensus for additoinal considerations.Aaron Liu (talk) 20:10, 13 May 2025 (UTC)[reply]
TarnishedPath's action there was objectively wrong, per the explicit description on the page and the outcome of the various Telegraph discussions. If someone does not understand rules written in plain English then that is a problem with the person not the rule. Thryduulf (talk) 23:21, 13 May 2025 (UTC)[reply]
Like I said, newcomer confusion. It's not too hard to assume—from the current RfC options layout of "1: GRel, 2: Additional considerations apply, 3: GUnRel" combined with the "traffic lights" coloring scheme—that yellow means considerations apply. Aaron Liu (talk) 01:06, 14 May 2025 (UTC)[reply]
People should familiarise themselves with the instructions and descriptions before commenting. If someone does comment before doing so and gets it wrong then we should educate them that they have got it wrong. If they don't read the current simple plain English descriptions why should we assume they would read the descriptions for the proposed, more complicated system? Thryduulf (talk) 01:38, 14 May 2025 (UTC)[reply]
You're going to have to try something other than complete non-sequiturs if you want to convince me that more complicated ways of conveying the same information will improve problems caused by people not bothering to read plain English descriptions of a very simple system. MREL and no consensus are both between red and green: they are neither generally reliable nor generally unreliable. Thryduulf (talk) 02:11, 14 May 2025 (UTC)[reply]
Indeed it is below GRel, but practically it's too different from "no consensus" to get the removal treatment; nearly always the additional considerations want one to treat a source the same as GRel with exceptions, while yellow indicates that the source as a whole should be treated below GRel. For example, no-consensus sources should not be cited by exceptional claims nor preferred over other no-consensus sources, and GRel sources are preferred over no-consensus sources. Such is not the GRel treatment deserved by sources with additional considerations while a usage does not fall under an exception.This yellow grouping lumped with the no-con treatment is a misleading signal, and this proposal's purpose is to address this misleading signal, while making additional considerations less stigmatizing for RfCs to conclude in. With purple, there is no way to assume—from the [proposed] RfC options layout of "1: GRel, 2: Additional considerations apply, 3: GUnRel" combined with the "traffic lights" coloring scheme—that yellow means considerations apply. Yellow would not be assumed to be additional considerations as the latter's no longer on the scale of survey options. This solution does not introduce additional pathways for assumptions. I see no way one could infer a wrong meaning and skip the legend when seeing the purple color, while as described above it's natural to assume if additional considerations is put on the traffic-lights scale. You could describe a way that TarnishedPath could plausible stumble into. Aaron Liu (talk) 03:05, 14 May 2025 (UTC)[reply]
I support this proposal.
The purpose of "additional considerations apply" is editor can't oppose the use of a source solely because it's WP:MREL, an editor has to explain why the "additional considerations" apply in this situation to make the source unusable.
For example, MREL for WP:XINHUA means avoiding it if the Chinese government might have a motive to use it for propaganda or disinformation. It would be disruptive to remove it from articles where that wasn't present.
However, the current practice of "no consensus = WP:MREL" is any editor can oppose the use of a source solely because it is WP:MREL and give no further justification, because the "additional considerations" were never agreed upon. Chess (talk) (please mention me on reply)05:13, 15 May 2025 (UTC)[reply]
Support per Chess. One is a consensus for (more or less specific) acceptable uses, the other is a lack of consensus, and they play out very differently in practice. Chaotic Enby (talk · contribs) 17:37, 15 May 2025 (UTC)[reply]
Sometimes editors have a disagreement about whether a redirect would be more appropriately categorized as R from other capitalisation or R from miscapitalisation. This proposal is for a guideline to help decide which to use when there are such disagreements:
For articles that have been through an RM or similar discussion on capitalisation, considering various factors such as WP policies and guidelines, common and official name usage in sources, etc., and a consensus on the title capitalization has been reached, redirects from different discussed capitalizations should be tagged R from miscapitalisation. Where such discussions have occurred without reaching a consensus, the redirects should be tagged R from other capitalisation. Where no such discussions have occurred, changes from one to the other should not be done without a solid reason and discussion, at least with the editor who originally placed the tag.
I don't necessarily agree, some redirects can be valid alternate capitalisations but not be the primary one or the one Wikipedia ends up favoring (thinking of "official" examples at MOS:TM for instance), and they shouldn't be tagged as "miscapitalisations" just because they went through a RM. Chaotic Enby (talk · contribs) 18:45, 19 May 2025 (UTC)[reply]
That's essentially what I've been trying to say. But for some reason there's an obsession with adding redirects to a specific maintenance report, and completely ignoring WP:NOPIPE. Additionally, Dicklyon has now created a new template that adds redirects to the miscapitalization category while using language that is already reflected in the R from other capitalization template. Hey man im josh (talk) 17:28, 21 May 2025 (UTC)[reply]
That was more or less the intent, and pretty much as Thryduulf suggested, though the language around "non-preferred" is significantly different from that at "other". Dicklyon (talk) 01:36, 22 May 2025 (UTC)[reply]
Prior discussion was at Template talk:R from miscapitalisation#Template intent. In context, we're talking about something that matters to approximately zero readers, so the calculation here should be to maximize usefulness to editors. If an article links a redirect that is an error according to Wikipedia style, the error should be fixed, regardless of how the capitalisation would be classed by some other style guide. The proposal here would make the miscapitalisation rcat useful for tracking and fixing those errors.
As a distant second choice, I would support a proposal to clarify that the miscapitalisation rcat is only to be used for errors that would be erroneous under any reasonable style, like Gospel of mark. The option I oppose most here is the unclear status quo, which has led to too much strife over something that matters to zero readers. Firefangledfeathers (talk / contribs) 18:53, 19 May 2025 (UTC)[reply]
In context, we're talking about something that matters to approximately zero readers, so the calculation here should be to maximize usefulness to editors. +1—Bagumba (talk) 09:01, 20 May 2025 (UTC)[reply]
I agree, however, in this case, it's very clear far too many redirects that are very clearly not errors in capitalization are being tagged as such. Hey man im josh (talk) 17:30, 21 May 2025 (UTC)[reply]
I agree with Chaotic Enby. Just because there has been an RM doesn't mean that capitalisations not chosen are wrong - not even if you define "wrong" as "not in accordance with the English Wikipedia's style guideline" rather than "always wrong". Iff there is some value to editors (who? why?) in tracking things that are incorrect in the eyes of editors who deeply care English Wikipedia's style guidelines (which is a very small subset of all editors) regardless of what the real world says, then there should be three categories of redirect - one for capitalisations that are always wrong, one for capitalisations that are (sometimes) correct in the real world but not on Wikipedia and one for capitalisations that are (sometimes) correct in both places. If there is no desire for a three-category system, then the only correct answer imo is the status quo. If people are being disruptive about it then the solution is topic bans and similar until they learn not to waste editors' time on something that has approximately zero benefit to readers. Thryduulf (talk) 20:30, 19 May 2025 (UTC)[reply]
When a redirect such as Computer Science that is tagged as R from miscapitalization is linked in an article, it shows up in a category and maintenance report. Sometimes the right fix to get if off the list is not to simply lowercase it. For example, in "Department of Computer Science", the capitalization is correct (assuming that's from the proper name of a department), but the fix would be either to restructure the link (avoiding linking words within a proper name is generally a good idea), or to pipe the link, avoiding the miscapitalized redirect. The other alternatives are less satisfactory: (a) not tagging the redirect as a miscapitalization would mean many errors would be harder to find and fix; (b) leaving the link as is would mean it keeps showing up in the maintenance categories and reports, diluting their usability. Many redirects from moves are like this. Marking them as miscapitalizations is still the usually best thing to do. And this guideline was really only for cases where editors disagree; if there's a general consensus that "other" is more appropriate than "mis", of course that's what will be used. When well-intentioned editors disagree which is best, as with NFL Draft, it seems better to stick with previously established consensus than to make a big deal about it and start a new big argument. Dicklyon (talk) 04:14, 20 May 2025 (UTC)[reply]
No, and I'm not suggesting "simply to avoid redirects". I'm suggesting it as a way to avoid a miscapitalized redirect, or any redirect that shows up on a maintenance report if there are links to it. Those are worth changing, if we want maintenance reports to be useful. Dicklyon (talk) 14:34, 20 May 2025 (UTC)[reply]
Then the maintenance report should be changed to avoid listing cases where WP:NOPIPE tells us that the current wikitext is correct and no change is desirable. If that's the report's sole purpose, bin it. There are plenty of actual problems of other types to find and fix. Certes (talk) 09:30, 25 May 2025 (UTC)[reply]
I support that idea of fixing the report to ignore piped links, which would make it more useful for its main purpose. This is only tangentially related to the question that brought us here. Dicklyon (talk) 15:15, 25 May 2025 (UTC)[reply]
Department of Computer Science: Tangential to the main purpose of this discussion, but MOS:LINKINNAME says: "Do not place a link to a name within another name. For example ... Do not write: [[Gilbert du Motier, Marquis de Lafayette|Lafayette]] Avenue → Lafayette Avenue —Bagumba (talk) 10:13, 20 May 2025 (UTC)[reply]
This is not very complicated. Here was an RfC I'd suggested at Dicklyon's talk page: "If a lowercased page name, such as NFL draft, has an uppercased redirect (NFL Draft) which is the actual official name of the topic, should the official name be labeled a 'capitalisation error' by Wikipedia?" Any guideline should include clear language to not label official names, well-sourced names, or names often uppercased, as "capitalisation errors" in Wikipedia's voice. Randy Kryn (talk) 03:27, 20 May 2025 (UTC)[reply]
Obviously the basis of that RFC wording presumes something about "Wikipedia's voice" telling others that they are wrong to capitalize. This is not at all what these maintenance templates are for. They put things in categories to be worked on. They do not put anything into the reader-visible article space. Dicklyon (talk) 03:54, 20 May 2025 (UTC)[reply]
Since an uppercased redirect appears in visible space at the top of the article (see NFL Draft's redirect to NFL draft, top of page just under the title), some readers undoubtedly click on it. At that point the redirect page becomes, automatically, visible space, with text in Wikipedia's voice. Randy Kryn (talk) 04:05, 20 May 2025 (UTC)[reply]
Obviously a reader can get to it if they click the right places. If that's bothersome we could tweak the messaging in the template to clarify that it's the wrong capitalization for Wikipedia, with no implication for the outside world. Dicklyon (talk) 04:17, 20 May 2025 (UTC)[reply]
Also, your inclusion of "actual official name of the topic" seems like a re-hash of an argument lost to consensus. A very biased RFC proposal, imho. Dicklyon (talk) 04:19, 20 May 2025 (UTC)[reply]
I see "official" causing problems in future. "Not an obvious error" or something similar would be better, i.e. NFL Draft (= other) vs NFL dRaFt (= incorrect). Scribolt (talk) 06:50, 20 May 2025 (UTC)[reply]
No. First off, it's about more than official names. Sometimes the article is at the official name and there's still disagreement over the redirect with different capitalization. Second, the MOS is already clear that official name is not part of determining WP's capitalization style. Third, there's often disagreement about what the official name is, with some editors claiming "official name" status for terms just because they appear in a list capitalized somewhere. Giving "official" names special status is contrary to the guideline of avoiding unnecessary capitalization. Fourth, sometimes the "official name" is not really the topic (e.g. the official name of the televised show "NFL Draft" is real, but the NFL draft topic is not really that; as mentioned above, in the rare event that a capitalized version of the name is needed and is linked, a pipe to avoid the miscapitalized redirect can be used, as the best alternative that doesn't destroy the whole purpose of these maintenance categories). Dicklyon (talk) 06:51, 20 May 2025 (UTC)[reply]
Thanks. I'm less focused on the arguments for or against the change, and more on how to properly word the RfC question if it comes to that, but I see that the "official name" thing might be a bit of a red herring.
I'd stay away from mentioning specific templates, as that is just one possible solution. Perhaps there's alternatives outside of reusing those templates, as some editors seem to attribute an ideological "right" or "wrong" from a grammar perspective. {{R from miscapitalisation}} says:
Pages that use this link should be updated to link directly to the correct form without using a piped link hiding the correct details
For Wikipedia maintenance purposes, how can we track such links—where the Wikipedia consensus is to change the case—for attention? If not "R from miscapitalisation", what are alternatives? —Bagumba (talk) 09:16, 20 May 2025 (UTC)[reply]
This clearly has nothing to do with RM. Also, "miscapitalised" is different from "does not follow Wikipedia's current style guide". 2 june is a miscapitalisation, Qixiaying Railway Station (the article has been moved both to and from that version) is not. —Kusma (talk) 10:39, 20 May 2025 (UTC)[reply]
I understand that difference, but it's not very relevant to the purpose of the miscapitalization tag, which is to put things in maintenance categories and reports so they're more likely to get fixed. Maybe there's a better name for it? Dicklyon (talk) 14:34, 20 May 2025 (UTC)[reply]
And the point of RM and such discussions is just that that's where consensus may have been established for which capitalization is right for Wikipedia. It becomes relevant when editors otherwise disagree and a record of consensus exists (e.g. with NFL Draft being wrong for Wikipedia). Dicklyon (talk) 14:36, 20 May 2025 (UTC)[reply]
No, that difference is very relevant. I was leading the charge for clearing out Wikipedia:Database reports/Linked miscapitalizations before you came along there. Back on 13 January 2023 I had the list down to as few as only ten items. It had over 1,000 items in September 2022, before I started my last push to clear it out. Now, since you've pushed your extreme MOS interpretation of proper names that aren't proper names, and prohibition of uses of title case that are widespread outside of Wikipedia – and formerly common on Wikipedia – onto the list, I've abandoned the project. Just as well, the editors tagging misspellings are pushing the project's limits on gnome capacity so as to take away any time I might have had to systematically fix miscaps in the past. – wbm1058 (talk) 16:05, 20 May 2025 (UTC)[reply]
I'm sorry that you abandoned it @Wbm1058, but I appreciate your efforts to focus on actual miscapitalizations and correct them, as opposed to over inclusion of what are actual legitimate alternative capitalizations. Hey man im josh (talk) 17:54, 21 May 2025 (UTC)[reply]
You've not made these more likely to get fixed. Quite the opposite. You had to bump the report limit from 1,000 to 2,000 to make room on it for everything. If everything is broken, then nothing is broken. Project abandoned. – wbm1058 (talk) 16:16, 20 May 2025 (UTC)[reply]
I actually had it down to a pretty small number for a while, too, when I was using JWB (down to 295 last September compared to 518 last May and over 1500 now). Recently Hey man I'm Josh has been pumping it up with things that I don't consider to be errors (at the same time as not letting me add thing that there is a consensus are not right). And there's still a lot of move cleanup pending, which few people are helping with, and this report helps track that, if we use it right. Dicklyon (talk) 05:00, 21 May 2025 (UTC)[reply]
I'm always available to discuss what may be perceived as an error, but you had it nowhere close to being finished when I started tagging more redirects. Additionally, your usage of JWB, and your refusal to actually listen to the criticism offered and adjust your usage caused you to be banned from automated tool usage altogether. Your subsequent appeal a month or two ago was also denied by the community.
Additionally, there's obviously been no consensus that a name regularly used by others that doesn't conform with Wikipedia's style guidelines is an error. Hey man im josh (talk) 17:52, 21 May 2025 (UTC)[reply]
Yeah I'm struggling to see where the confusion comes from @Kusma.
{{R from other capitalisation}}: From other capitalisation: This is a redirect from a title with another method of capitalisation. It leads to the title in accordance with the Wikipedia naming conventions for capitalisation, or it leads to a title that is associated in some way with the conventional capitalisation of this redirect title. This may help writing, searching and international language issues.
{{R from miscapitalisation}}: From a miscapitalisation: This is a redirect from a capitalisation error. The correct form is given by the target of the redirect.
They seem pretty straight forward already, one is a clear error and the other is meant to conform with Wikipedia guidelines, but may be acceptable in other situations. This is why I oppose a third category. I've had a tough time understanding the issue for over a year now, except that Dicklyon wants to bypass a lot of redirects and one template encourages this while the other says not to do so (WP:NOPIPE). Hey man im josh (talk) 17:38, 21 May 2025 (UTC)[reply]
@Hey man im josh: I have never particularly cared about the categorisation of redirects. Anyway, I looked through the "miscapitalisation" category and found many redirects that seemed to be from perfectly acceptable other capitalisations (I gave one example of a Chinese railway station above), so should anyone care about these categories, they would need to be cleaned up before they can be mechanically used. Generally, systematically bypassing redirects (even those where this would be an improvement) seems to be an activity that can wait until Wikipedia runs out of serious multi-year backlogs, so putting an infrastructure in place for this probably can be safely postponed for another decade or two. —Kusma (talk) 22:30, 21 May 2025 (UTC)[reply]
Any redirect that uses capitalisation different from the target is alternative capitalisation - including miscapitalisation. I don't think we need an extra template/category. I don't think we need both of the ones we have. We should just modify the "alternative capitalisation" - that it includes a multitude of sins of varying degrees. Cinderella157 (talk) 11:26, 21 May 2025 (UTC)[reply]
But not every alternative should be "fixed". The "miscapitalization" tag has always been to track the ones that should be, typically as part of RM cleanup. Personally, I don't see a need for any further discrimination of alternatives. Dicklyon (talk) 15:31, 21 May 2025 (UTC)[reply]
Dicklyon, as I understand it then, the template (miscapitalisation) and associated category is used to amend links in articles so that they link directly rather than through a redirect. Does this not equally apply if a link in an article is to an "alternative capitalisation"? Cinderella157 (talk) 00:21, 22 May 2025 (UTC)[reply]
It doesn't directly amend links, but lets interested editors know what they can work on. Many of the ones marked "other" really should be marked miscapitalization (or non-preferred capitalization) and should get fixed. But not all. In particular, a huge number of "other capitalization" redirects from lowercase have been created for article titles that are over-capitalized and have never been discussed (because, sadly, many article creators don't know to choose sentence-case titles, and then when people try to link they get red links, so they create the redirects). Sometimes when I find those I move the article title to lowercase and mark the over-capitalized redirect. But until someone actually looks at or discusses the capitalization question, it's just "other". And some others may genuinely have both lowercae and uppercase correct forms (though I don't recall why right now). Dicklyon (talk) 00:31, 22 May 2025 (UTC)[reply]
FYI, here's an example case I fixed, when I was working this beat: 30 links to jpeg. Not everything is miscapitalized when it's using uppercase that the MOS patrol want to downcase. Some cases are where lowercase redirects should be bypassed to capitalize them. But I consider this work to be lower priority than correcting actual A–Z misspellings. – wbm1058 (talk) 18:39, 21 May 2025 (UTC)[reply]
Indeed, fixes in that direction (e.g. United states -> United States) are still widely needed, and uncontroversial. I do a lot of those, too. But recently Josh has been tagging lowercase things as miscapitalizations even when a discussion has taken place and there's clearly no consensus for his claim of proper name status. He wants his way, both ways. E.g. List of schools in the Auckland region, where there's no consensus that "Auckland Region" is a proper name, just because an administrative unit of the name exists. The RM discussion close was very clear that there was no consensus (after an earlier close in which a consensus to lowercase was found). Dicklyon (talk) 00:52, 22 May 2025 (UTC)[reply]
tagging lowercase things as miscapitalizations: Those are more likely to be "other capitalisation" and not errors, because a lot of them can be linked as basic English phrases using common nouns. Consider: Green Bay Packers quarterback Aaron Rodgers, a four-time N.F.L. most valuable player ...[14] While there is capitalized NFL Most Valuable Player, editors can choose to write it with basic English, without capitalization, and it reads just fine in lowercase. A lowercase redirect there could legitimately be "other capitalisation", not a miscap, if we are going to consistently apply this "outside Wikipedia" argument. (I still argue that these redirect cats are hidden categories for Wikipedia internal use only.)—Bagumba (talk) 03:39, 2 June 2025 (UTC)[reply]
Three categories?
I'm actually warming up to Thryduulf's suggestion of having a third category, capitalizations that may be OK in other styles but are not in accord with WP's capitalization guidelines. If someone is willing to work on creating such templates, and fixing up the reporting machinery to make a report on "linked not-ideal capitalization redirects" or whatever we'd want to call it, I'd be willing to help and give it a try.
That doesn't solve all the problems here (e.g. where Josh wants to label Water supply in the Wellington region as a miscapitalization, even though there has never been a consensus for capitalizing Region there, and even though the lowercase is dominant in the outside world, just because there is an official name Wellington Region, for which there is also no consensus for capitalization, after discussion at RM). Should we have yet another category for that kind of thing, whatever it is? Links to these don't need to be on a maintenance report, since there's no reason to change them. Dicklyon (talk) 14:53, 20 May 2025 (UTC)[reply]
I suppose it would be helpful at this point to agree on what types of capitalisations differences exist (numbered for ease of reference only)
Capitalisations that are always incorrect (e.g. 4 june)
Capitalisations that are always incorrect in some contexts but always correct in others, examples include
Where a phrase is both a proper noun and a common noun (sometimes there is disagreement about whether something is or is not a proper noun)
Where something is a term of art in some professions but not others
Differences between different (national) varieties of English
Differences between audiences, e.g. legal English will correctly capitalise some terms that are correctly not capitalised in lay writing (even by the same author)
Different cultural contexts, e.g. an adherent of a particular religion may capitalise a term that non-adherents do not
Capitalisations that are always incorrect in some contexts but about which there are differing opinions in others (e.g. NFL Draft is correct for the TV programme, but opinions differ regarding the event).
Capitalisations that are correct or incorrect depending on stylistic choices (e.g. SEE MONSTER vs See Monster)
For some of these there is disagreement on which is correct on Wikipedia
This means there are cases of capitalisations that are unambiguously incorrect on Wikipedia but correct in (some) real world contexts (e.g. for trademarks)
Multiple capitalisations are in free variation, with none being particularly more common
Multiple capitalisations, one is significantly less common but not incorrect where it is used
This can vary over time, in both directions.
We don't need six (or more, I may have missed some) categories but as long as we have more than one we need to decide which belong in which. Thryduulf (talk) 18:07, 20 May 2025 (UTC)[reply]
It really boils down to two categories:
Capitalisations that are always incorrect (e.g. 4 june) – these the gnomes will correct.
Capitalisations that may be incorrect in some contexts (this is for all the MOS-enforcement stuff, i.e. uses of title case and disputed proper names) – these the gnomes will ignore.
Because gnomes will ignore #2, there was no need to create such a category before, but apparently now there is a need. – wbm1058 (talk) 18:26, 20 May 2025 (UTC)[reply]
OR… Gnomes simply need to remember the banner at the top of every MOS page… the one where we say “exceptions may apply”.
Gnomes do wonderful work (thank you), but they do tend to get myopic. When they get pushback on an edit, we need consider that we may have bumped into one of those “exceptions”. Blueboar (talk) 19:00, 20 May 2025 (UTC)[reply]
Hey, if you wanna see some of the somewhat annoying "pushback" I've gotten lately, checkout the bottom of my talk page at the moment. I stick to the maintenance categories that the non-administrator executive editors have declared to be "always incorrect", and sometimes push back by changing their categorization of the redirect to make it a valid alternative form rather than incorrect. – wbm1058 (talk) 19:43, 20 May 2025 (UTC)[reply]
Speaking as a capitalization gnome, I can assure you I don't ignore things that are incorrect in WP, and I'm generally alert to exceptions. I rely on the categorization/reports to keep me in over my head with work to do. Dicklyon (talk) 04:55, 21 May 2025 (UTC)[reply]
If the categories are hidden then it would be best to leave discussion to the people who actually use them, rather than the rest of us tell them how they should use them. Phil Bridger (talk) 20:07, 20 May 2025 (UTC)[reply]
I made a new "R from non-preferred capitalisation" template, and tried it out (see Midland Line, New Zealand). It still populates the same category and gets picked up on the same reports, but avoids doing what Randy is complaining about. Seems to work. So I'll just use that for now for the things where the consensus is that they're not right caps for WP. Dicklyon (talk) 05:37, 21 May 2025 (UTC)[reply]
If that's the needed compromise,then c'est la vie. I never perceived the issue that some others did. These types of categories read:
This is a maintenancecategory, used for maintenance of the Wikipedia project. It is not part of the encyclopedia and contains non-article pages, or groups articles by status rather than subject ... These categories can be used to track, build and organize lists of pages needing "attention en masse" (for example, pages using deprecated syntax), or that may need to be edited at someone's earliest convenience.
... you haven't solved anything from a maintenance standpoint ... But it solved the non-maintenance issue some raised about the mere presence of the word miscapitalisation if a reader actually clicked on the redirect. —Bagumba (talk) 07:37, 22 May 2025 (UTC)[reply]
@Wbm1058: I'm ready and willing to make the trivial edit to change what category the template populates, when you or someone is ready with the report making. Let's talk. Dicklyon (talk) 16:00, 30 May 2025 (UTC)[reply]
capitalizations that may be OK in other styles but are not in accord with WP's capitalization guidelines That's literally what the R from other capitalization is meant to be for, so a third template is entirely unnecessary. R from other capitalization and R from miscapitalization are already in existence, their usage cases are quite clear. Hey man im josh (talk) 14:24, 21 May 2025 (UTC)[reply]
I think putting all the "R from other" redirects with incoming links on a report of things to fix would be not what's intended for those. But I do agree than many of those would be better as "R from non-preferred" so we'd track links to them in those categories and reports of things worth fixing. Dicklyon (talk) 15:27, 21 May 2025 (UTC)[reply]
The documentation says that pages tagged are added to miscapitalization category it's pretty clearly gaming and not appropriate to add many of these to that category, especially just for your pet obsession of one report. Hey man im josh (talk) 16:37, 21 May 2025 (UTC)[reply]
It was easier to use the existing category than to rewrite the report to draw from a different category that could be called non-preferred. This was the minimal fix to address Randy's complaint. I agree that not every "other" capitalization should be put into this category. I would not object if you or someone wanted to help migrate to something more evolved, as long as it still supports the maintenance reporting. Dicklyon (talk) 06:12, 22 May 2025 (UTC)[reply]
This new template is inappropriate, as it still tags pages as miscapitalizations instead of alternative capitalizations... I strongly oppose it's usage, especially considering it states that redirects pointed to these redirects should be bypassed. What are you not understanding about what defines an error??? This is so fucking exhausting and clearly WP:GAMING. Hey man im josh (talk) 16:35, 21 May 2025 (UTC)[reply]
Why are you so opposed to fixing things like NFL Draft over-capitalization, yet so insistent that Auckland region needs to be capitalized? Certainly it would be better to adopt my consensus-based guideline than go with your pure opinions. Exhausting it is. Dicklyon (talk) 06:07, 22 May 2025 (UTC)[reply]
Personally, I think we should use {{R from miscapitalization}} for cases that are always erroneous (e.g. Barack obama), and {{R from other capitalization}} for all others; I don't really see a need to introduce a third redirect category into the mix. Separating out "non-preferred" capitalizations from other alternative capitalizations doesn't seem like a useful distinction to draw; almost any redirect that differs solely in caps will be non-preferred, because the capitalization that is preferred should just be the page title. ModernDayTrilobite (talk • contribs) 16:53, 22 May 2025 (UTC)[reply]
See my comment of 00:31, 22 May to Cinderella above, for why quite often the one in the redirect is the preferred one, and the title capitalization is non-preferred, but it's just that nobody has noticed and fixed it yet (you find a few thousand examples if you review my move log). In general, it would often be wrong to assume that the "other" is "non-preferred". It would be safer to think of "other" as meaning not yet determined which might be preferred or non-preferred or wrong. Dicklyon (talk) 02:26, 23 May 2025 (UTC)[reply]
Another bunch of examples are the <year> National Soccer League Grand Final articles. Josh recently created a bunch of redirects from lower case and tagged them miscapitalized, for who knows what reason. Anyone who looks at sources can see that the lowercase is preferred on WP, and the capped are over-capitalized. So I changed them to "other", and since he has made it controversial I opened an RM instead of just fixing them. So these "other" are not "non-preferred", unless the RM generates a consensus that capitalizing is correct, which seems very unlikely. Dicklyon (talk) 00:48, 24 May 2025 (UTC)[reply]
Having looked (so far) only at the first page of Google Books results you link to in that RM, I'm seeing a mix of capitalised and non-capitalised uses so it's unlikely that either can be accurately described as "always incorrect". Thryduulf (talk) 01:08, 24 May 2025 (UTC)[reply]
Wikipedia relies on sources to determine what is conventionally capitalized; only words and phrases that are consistently capitalized in a substantial majority of independent, reliable sources are capitalized in Wikipedia.
If I'm following this right, there are three outstanding potential issues:
The new template still categorizes the redirects as "miscapitalisations", which some people oppose
The new template could instead point at a new category, but this would still need to be created and targeted by reports that collect linked non-preferred capitalisations
Some people object (in some or all cases) to the way editors are using the reports currently. They would similarly object to editors using the new reports.
Is there a compromise possible where we focus on addressing #2? It addresses some of the concerns about categorizing non-preferred capitalisations as errors while still enabling work on fixing non-preferred capitalisations. Firefangledfeathers (talk / contribs) 03:08, 24 May 2025 (UTC)[reply]
Yes, it's good to regroup and avoid TLDR for newcomers. I'll add for #1:
This is a maintenance category, used for maintenance of the Wikipedia project. It is not part of the encyclopedia and contains non-article pages, or groups articles by status rather than subject.
Josh did a mod in this edit (which I reverted), indicating some problem with this concept. He suggests that piped non-preferred redirects should not be fixed, which would make the related category and report useless for maintenance and improvement of the encyclopedia. Same problem he has with marking non-preferred capitalizations as miscapitalizations, or partly the same. That is, Thryduulf's suggestion of having a third category does not address his problem that brought us here. Maybe someone else can try to talk to him, as I'm running out of ideas. Dicklyon (talk) 07:11, 24 May 2025 (UTC)[reply]
Josh also cited WP:NOPIPE in his edit summary of the edit I linked above. In truth, I don't see how it applies one way or the other here, but I agree that piping through a miscapitalized (or non-preferred capitalization) redirect is a bad idea, and fixing them is part of process of working on the reports of links to such things. If someone is able to refine the reporting to ignore links that are piped, then they wouldn't need to be fixed to make the reports useful, but until then, fixing them is pretty much needed.
I went ahead and applied the new tag to a bunch of redirects with "in the NFL Draft" in their titles. If we decide to make this template do something a bit different, that will be done in one place, so I'm pretty sure there should be no reason for Josh or anyone else to object to those. There are a lot more to do. Dicklyon (talk) 05:30, 25 May 2025 (UTC)[reply]
"Not preferred on Wikipedia" and "incorrect" are very much not the same thing. "NfL Draft" is correct in some circumstances, even if that's not many, so it should editors should not be instructed to always "fix" it. We need either two categories and two templates, one for redirects that are always incorrect and one for everything else; or three categories and three templates, one for redirects that are always incorrect, one for those that are always non-preferred on Wikipedia, and one for those that are true alternatives. Three templates with two categories is doesn't help anybody. The longer this discussion goes on, the more I favour the two-category solution with strong guidance that miscapitalisation is only for redirects that are always incorrect. If that makes it harder to deal with something as trivial as possibly incorrect capitalisations then so be it. Thryduulf (talk) 09:33, 30 May 2025 (UTC)[reply]
Thryduulf is correct that it'd be better to amend the documentation of Template:R from non-preferred capitalisation to say that incoming links should sometimes/often be fixed, rather than imply they always need fixing. In a sentence like "James said 'my greatest dream was to be picked last in the NFL Draft'", the best link style option is to link the non-preferred cap redirect instead of piping to the article. Most links won't be in situations like that, but some will.
I have amended it to say "usually". I have no objection to having a third category to go with the third template; that needs to be worked out with someone who is willing to help with the corresponding report(s). Dicklyon (talk) 14:53, 30 May 2025 (UTC)[reply]
@Firefangledfeathers It's not that I object to the three-three option it's just I'm not really convinced that it actually adds enough value over the two-two option for the ongoing maintenance load.
@Dicklyonthat needs to be worked out with someone who is willing to help with the corresponding report(s) Why? If nobody is interested in fixing an error, you have to consider whether it is actually an error at all? Thryduulf (talk) 15:13, 30 May 2025 (UTC)[reply]
Thanks for clarifying. I continue to favor the three-three solution. People are interested in fixing the errors, and it seems like the next steps are creating the third category and then requesting for help with the reports. I presume this should happen at Wikipedia talk:Database reports. I'll wait to see if there are objections. Firefangledfeathers (talk / contribs) 15:20, 30 May 2025 (UTC)[reply]
It won't be hard to get this implemented; I can probably figure it out myself. But I'm also not really convinced that the three-category solution is needed. I don't see any problem sticking with the two-category solution, or even the two-tag solution, if we go back to business as usual, tagging non-preferred capitalizations as miscapitalizations so they get on the report of things to fix. I still don't see what's Josh's reason for objection is, and Randy's objection that the redirect can show up in a hatnote and therefore a user might stumble on the otherwise hidden tag seems pretty trivially weak. Nevertheless, I'm willing to try your suggestion of a compromise third tag/category. Dicklyon (talk) 15:36, 30 May 2025 (UTC)[reply]
I am also not convinced by the objections, but the people doing the objecting are numerous. We could have a big ol RFC about it—which will surely generate many pages of "why does this matter?" comments—or we can compromise. Firefangledfeathers (talk / contribs) 15:39, 30 May 2025 (UTC)[reply]
Likewise, I think we should not lose track that these are redirect categories are documented as being for internal WP maintenance only, and are more or less hidden from the outside. They're not intended as grammar references for the masses outside WP, nor do I believe anyone realistically uses them as such. Yet, we must acknowledge that MOS is polarizing, and these objections exist. —Bagumba (talk) 15:55, 30 May 2025 (UTC)[reply]
if we go back to business as usual, tagging non-preferred capitalizations as miscapitalizations so they get on the report of things to fix this is the fundamental thing people are objecting to: Just because a capitalisation is non-preferred doesn't mean it is incorrect. Thryduulf (talk) 15:50, 30 May 2025 (UTC)[reply]
Then "people" should be more clear what aspect of this maintenance process bothers them. Maybe all we have to do to fix it is change a few words in the documentation or category names. But it's hard to know what solution will be most satisfying if people won't be clear. And I do appreciate your idea of the third/middle way, as it seems to address as much of the objection as I can see. Your waffling by saying you're not sure it's worth it just takes us back to square one, which is also an alternative. Dicklyon (talk) 15:55, 30 May 2025 (UTC)[reply]
I'm genuinely not understanding what you are finding unclear about this. Only capitalisations that are actually incorrect (not just non-preferred) need correcting. Don't "correct" things that don't need correcting. Thryduulf (talk) 16:03, 30 May 2025 (UTC)[reply]
OK, that sounds like my hypothesis number 1: "You don't want to see more downcasing of NFL Draft (and other links containing that phrase) where it appears in articles." (not just NFL Draft, of course, but other non-preferred capitalizations that appear in articles). I appreciate the clarification of your position, and I strongly object to it. These things should be corrected, even if you don't want to label them as errors. Dicklyon (talk) 17:57, 30 May 2025 (UTC)[reply]
These things should be corrected, even if you don't want to label them as errors. This is the fundamental disconnect - capitalisations that not incorrect in context (and things that are non-preferred are not incorrect) are not something that can be "corrected". Making such trivial style changes such as NFL Draft to NFL draft without substantial changes to the article are, in the majority of cases, both pointless and disruptive (e.g. watchlist spam), [[NfL Draft|NfL draft]] even more so. Spend your time and effort fixing things that are actually incorrect (e.g. john smith → John Smith) and you should get no pushback and thanks for improving the encyclopaedia. Thryduulf (talk) 19:17, 30 May 2025 (UTC)[reply]
I get a ton of thanks already for my case fixing work. I realize that you, as a long-time opposer of capitalization fixes, are not among those thanking me. I find your effort here to sabotage the case-fixing process by declaring style errors to be not worth fixing is way out of step with consensus in such things. Dicklyon (talk) 00:17, 31 May 2025 (UTC)[reply]
I don't oppose capitalisation fixes, I oppose fixing capitalisations that do not need fixing. From my perspective, consensus is a lot closer to my position than it is to yours given how much opposition implementing the outcomes of discussions attended almost entirely by MOS regulars attracts. Thryduulf (talk) 01:15, 31 May 2025 (UTC)[reply]
There's a disconnect with MOS:CAPS advising to avoid capitalisation except when they are consistently capitalized in a substantial majority of independent, reliable sources are capitalized in Wikipedia versus fans of individual institutions (like the NFL) that choose to overcapitalise. But projects' WP:LOCALCONSENSUS needs to convince the wider community that the general MOS is to be IAR ignored, or that the MOS needs modification. —Bagumba (talk) 01:56, 31 May 2025 (UTC)[reply]
Thryduulf, you do oppose capitalization fixes, frequently, by saying they're not necessary. But guidelines say they're not right. There's essentially no pushback on case fixing as move cleanup after a consensus to change case, and also relatively little on all the other case fixing I do without discussion. There's always Randy arguing that caps are better, but he doesn't object to the cleanup fixes once consensus is achieved. Josh mostly doesn't object either, he just doesn't like the labels. So when you say "given how much opposition implementing the outcomes of discussions", I think you're hallucinating; or show me what you're talking about. Dicklyon (talk) 06:08, 31 May 2025 (UTC)[reply]
If nobody is interested in fixing an error ... It's more that it's not for the faint of heart and few dare. Witness the pitchforks even after RfCs reach a consensus. —Bagumba (talk) 16:12, 30 May 2025 (UTC)[reply]
@Firefangledfeathers: Is the concern here that it's a quotation, and the original source capitalized "NFL Draft"? If so, we should not hold non-preferred capitalizations to a higher standard than we do with non-preferred spellings. While MOS:PMC reads: In direct quotations, retain dialectal and archaic spellings, including capitalization (but not archaic glyphs and ligatures, as detailed below in § Typographic conformity), but MOS:CONFORM says A quotation is not a facsimile and, in most cases, it is not a requirement that the original formatting be preserved. Formatting and other purely typographical elements of quoted text should be adapted to English Wikipedia's conventions without comment, provided that doing so will not change or obscure meaning or intent of the text. I question the blanket need to always retain non-preferred capitalizations for quotes, and I'll note that nobody is similarly clamoring about {{R from misspelling}} and the need for {{R from non-preferred spellings}}. There is a double standard. A few one-off IAR cases to pipe, as you suggest, seems reasonable. —Bagumba (talk) 15:46, 30 May 2025 (UTC)[reply]
Plus the way this specific example is written, since the quote is from a spoken comment, the written capitalization is a style choice by the publication, not the speaker. That being said, it's standard for publications to alter the style of written or spoken quotations to conform to their own style guidelines, and the quoted Wikipedia guideline aligns with historical writing practice. isaacl (talk) 16:55, 30 May 2025 (UTC)[reply]
Probing the objections
@Hey man im josh: – I'm trying to understand your position better. I have several conjectures about what you might be trying to say, some mutually contradictory and some not:
You don't want to see more downcasing of NFL Draft (and other links containing that phrase) where it appears in articles.
You do want to see more downcasing of NFL Draft where it appears in articles, but don't want the current "miscapitalization" categories and reports to be used for that.
You have some alternative suggestion for a method of maintenance that would be more appropriate here.
You object to downcasing links piped through NFL Draft (and other redirects that appear on maintenance reports), since they affect only the maintenance cat and report but have no effect on the article appearance.
If you can let us know which ones of these, if any, characterize your position, that would be useful. Also if the answers are different for other redirects with non-preferred capitalization, such as List of Railway Stations in Japan, Association Football, Chibcha Terrane, etc., or, replacing "downcasing" by "upcasing", Covid-19, Zip code, Allmusic, Wrestlemania 25, it would be good to know what kind of considerations make some of these different. Currently these are all tagged as "miscapitalizations", so I wonder if you think some of those should not be, and if not, then what. Dicklyon (talk) 22:16, 26 May 2025 (UTC)[reply]
Well, yes, if anyone else has any objections to using the miscapitalization and/or non-preferred capitalization tag on any of these or other specific redirects, I hope they'll let us know, perhaps with reference to those hypothesized positions. Dicklyon (talk) 04:33, 30 May 2025 (UTC)[reply]
Partly. There are places where "NFL Draft" is correct and so should not be changed. There are places where it is entirely non-problematic so it should only be changed as part of a substantive edit (and even then doesn't matter if it isn't changed).
See #1. Using the current miscapitalisation categories/reports for things that are not always incorrect is what is problematic.
See extensive discussion elsewhere in this section.
[[NFL Draft|NFL draft]] and equivalents should not be changed unless a substantive change is made to the article at the same time, or it is a situation where "NFL Draft" is actually correct. See WP:NOTBROKEN, WP:COSMETIC and similar.
Most is not all: Sure, but in a large extent, they are independent issues. One is whether conceptually there are use cases for {{R from non-preferred capitalisation}}, the others are specific redirects, and whether or not it is applicable, which is decided on a per-case basis. —Bagumba (talk) 17:34, 30 May 2025 (UTC)[reply]
The draft itself is lowercase… but the name of the TV program that airs it (but also contains commentary, bio segments and other bits and pieces) would be upper case. Blueboar (talk) 17:27, 30 May 2025 (UTC)[reply]
I'm not aware of a TV show called "2025 NFL Draft" or "2025 NFL Draft on ESPN". Could someone please locate a reliable source that has the official name of this hypothetical TV program? ESPN airing the 2025 NFL draft doesn't mean it's an officially named TV program like most people would think of.
The shows are usually branded, e.g. 2019 NFL Draft on ABC.[15]. And WP prose is typically "ABC aired the 2019 NFL draft" and not with the program like "ABC aired 2019 NFL Draft on ABC" —Bagumba (talk) 18:09, 30 May 2025 (UTC)[reply]
I found one recently with NFL Draft in a list of shows that some network aired, so I put [[NFL draft|NFL Draft]] to avoid linking the miscapitalized redirect, so I wouldn't end up back there again from the report. But that's the only one I've seen so far. Dicklyon (talk) 06:12, 31 May 2025 (UTC)[reply]
I saw Harry Connick Jr., with the draft listed in his filmography. Since it's the show, I linked it instead to NFL Draft on ABC.[16] If there really was a TV show called NFL Draft, it should link to NFL Draft (TV program) (naming consistent with WP:NCTV). It could also probably be tagged with Category:Redirects with possibilities, as a possible standalone page. That aside, it's similar to disambiguation pages only being linked from the main space with titles ending in (disambiguation) (WP:INTDABLINK), so we can distinguish an accidental link that should be changed to preferred capitalisation versus one that we consciously want to remain capitalised. —Bagumba (talk) 10:36, 31 May 2025 (UTC)[reply]
@Thryduulf:, you say "3. See extensive discussion elsewhere in this section." as "some alternative suggestion for a method of maintenance that would be more appropriate here." I'm not sure what part of this extensive discussion has proposed an alternative way forward, other than your three-category suggestion, which I've partly implemented. What else might you be referring to? Dicklyon (talk) 03:26, 1 June 2025 (UTC)[reply]
This is a ridiculous tempest in a teapot. "Mis-capitalization" or "incorrect capitalization" in this context really, really, really obviously means "capitalization that is unnecessary and undesirable per WP's own style guide and previous consensus decisions". It literally is not possible for it to mean "incorrect according to all usage and every source in the world". There is no agreement on capitalization, of anything, across all sources, publishers, writers, editors – beyond things universally treated as proper nouns (and proper-noun phrases) like "Assyria", "Oprah Winfrey", and "the Arctic Ocean". So it simply is not rationally conceivable that the meaning is anything like "universally considered incorrect by off-site publishers". If people are going to continue to pitch pointless, obstructive, and editorial-time-wasting hissyfits about this stuff, just change the wording of the category to "unnecessary capitalization" or "over-capitalization" and be done with it. This kind of bikeshedding over trivia has been long-term corrosive to editorial productivity and goodwill.
To the extent "NFL Draft is sometimes properly capitalized" ... [And why does this always seem to be about that f***ing subject over the last year or so? GIVE IT A REST. STOP OBSESSING. This subject, like all other subjects, do not "belong" to you.]: That's only going to be true when it appears in a proper name, that WP consensus agrees is a proper name, such as the title of published work (when given in title case). So the issue simply isn't an issue.
These "objections" are a patently manufactured drama, and attempt to drag out indefinitely a matter already settled by RfC (after failures multiple times to settle it via RM and MR), and re-settled by AN. Just drop the stick before you beat the horse corpse all the way to center of the earth. I can't read minds, so I cannot prove motivations, but it is very difficult to not come away with an impression of "me and my little WP:FACTION are going to fight against everything that DickLyon in particular does, until the end of time." This needs to stop. It needed to stop several years ago. — SMcCandlish☏¢ 😼 11:28, 2 June 2025 (UTC)[reply]
"Mis-capitalization" or "incorrect capitalization" in this context really, really, really obviously means "capitalization that is unnecessary and undesirable per WP's own style guide and previous consensus decisions". given that multiple people in good faith believe differently to you, and have explained why in detail, this is clearly not correct. The rest of your bad-faith rant castinging multiple unfounded aspersions is something that I encourage you to self-revert before it becomes an ANI matter (this is not your first warning). Thryduulf (talk) 11:34, 2 June 2025 (UTC)[reply]
Quite frankly, I'm with SMcCandlish in thinking that your opposition to my case fixing work is not in good faith, and that it has been ongoing very obnoxiously for years. It's OK that you don't think case fixing is important or "necessary", but in general, whatever your feelings, you should not fight attempts to improve the encyclopedia's compliance with its own guidelines, which is what you're doing here. And it's you that has made it personal, here and numerous times before. Dicklyon (talk) 14:32, 2 June 2025 (UTC)[reply]
I and others, including you, have argued there for doing just that - and that is the correct venue to make that argument. However the discussion remains open and so people following here should be aware that it is happening. Thryduulf (talk) 22:07, 26 May 2025 (UTC)[reply]
I used the standard template with the standard wording (I just suppressed the default header because I couldn't figure out any way to get a level 3 header) to make sure the notice was neutrally worded. Thryduulf (talk) 23:49, 26 May 2025 (UTC)[reply]
Our mission is to enrich Wikimedia projects with high-quality and diverse content related to the Middle East and North Africa (MENA) region. This initiative focuses on creating new articles, multimedia, structured data, and more, covering topics from MENA countries, communities, and diaspora worldwide.
Who Can Participate?
All registered Wikimedians are welcome to join! Whether you're an individual contributor or part of an organization, your support is valuable. We encourage content creation in any of the six official UN languages (Arabic, English, French, Russian, Spanish, and soon Chinese).
What Kind of Content Are We Looking For?
New Wikipedia articles focused on MENA topics
Multimedia contributions on Wikimedia Commons (photos, videos)
Structured data for Wikidata
Language entries on Wiktionary
Public domain texts on Wikisource
Note: Make sure your content follows local Wikimedia guidelines and licensing policies, including Freedom of Panorama for media files.
Join us in bridging content gaps and showcasing the richness of the MENA region on Wikimedia platforms!
Stay tuned for more updates and participation guidelines. Reda Kerbouche (talk) 09:08, 23 May 2025 (UTC)[reply]
Per both the header at the top of this page and the editnotice, This page is for concrete, actionable proposals. As written, it sounds like the "proposal" in question here is "go create new articles", which is what we've been doing for the past two decades and plan to continue doing indefinitely into the future.
There is a lot of community skepticism of affiliate activities after we've seen numerous flashy announcements of ambitious-sounding projects filled with vague corporate buzzwords (e.g.Building strategic relationships with key stakeholders, identify growth opportunities) and funded by expensive grants that ultimately do little or nothing to improve the encyclopedia. I assume that there is more detail/planning to your initiative than is described in your note above and on the project landing page (where you may wish to fix the broken header tabs), but it may behoove your interests to craft announcements that assuage rather than exacerbate the aforementioned fears. Sdkbtalk15:00, 23 May 2025 (UTC)[reply]
Thank you for your feedback; it’s both valid and appreciated. And we took time to discuss all the questions with the whole team.
We understand that from a first read, this may seem like a broad or familiar call to action. However, the Million Wiki Project is not just about encouraging content creation, it’s about coordinating and resourcing communities in multiple regions (some are underrepresented) to increase content equity across multiple Wikimedia projects. If you think the details are insufficient in the landing page; we can expand it based on the feedback we receive.
We’ve seen firsthand that in many MENA countries, editors face barriers like limited outreach, infrastructure, or access to local events. This project provides logistical and financial support (e.g. internet stipends, local editathons etc.) to empower them to organize impactful campaigns.
At its heart, this project is about inclusion; bringing everyone along on this journey, even those who haven’t had the chance to participate before. While the name may highlight a numerical goal (a million contributions), our true aspiration is to ensure that every Wikimedian feels they have a place and a voice in this movement.
This project has been co-designed by experienced editors, supported by the grant committee of the Project, and built on the feedback received from the community organizers. It's an ongoing process; and we’re learning every step of the way. Abbas14:00, 3 June 2025 (UTC)[reply]
I'm confused about what this is actually about. Does create one million new contribution and content pieces mean one million edits or one million articles? Does it include images on Commons and documents on Wikisource? Why does any of this need funding? If you are paying editors, it may slow things down (on enwiki), as draft articles would have to go through the Articles for Creation review process. Toadspike[Talk]16:18, 23 May 2025 (UTC)[reply]
Thank you for raising these valid questions. The “one million” target includes meaningful contributions across Wikimedia projects: new additions/articles, structured data, Commons uploads, Wikisource documents, and more. Full details are available here. To clarify: we are not paying editors for content creation. Instead, we provide microgrants to communities and affiliates who want to run campaigns, editathons, similar to other movement grants. These are needs-based, and only support logistics, internet costs, etc. We're especially encouraging experienced editors to lead these initiatives, precisely to maintain quality and alignment with Wikimedia’s standards, including AfC processes when required. Reda Kerbouche (talk) 17:36, 2 June 2025 (UTC)[reply]
Why is this project restricting its support to content in "official UN languages", the majority of which have limited, if any, connection to the MENA region? Is such blatant discrimination normal practice? AndyTheGrump (talk) 16:25, 23 May 2025 (UTC)[reply]
English does make sense as the international lingua franca, and of course (Modern Standard) Arabic as the standard language used by half of the Middle East, but it misses on relatively large wikis (such as Persian, Hebrew, Egyptian Arabic and Turkish Wikipedias), which are all more relevant to the region (and likely have more native speakers who might be able to help on MENA topics) than Spanish or Russian. Chaotic Enby (talk · contribs) 16:37, 23 May 2025 (UTC)[reply]
Thank you for your questions @AndyTheGrump and Chaotic Enby:; it's important to clarify this point. At this stage of the Million Wiki Project, we’ve chosen to focus on contributions in the six UN official languages (Arabic, English, French, Spanish, Russian, and Chinese). This was a strategic decision made by the organizing team and the grant committee to ensure consistency in tracking, reporting, and coordination across different regions and communities. The choice is based on practical reasons:
These languages already have strong foundations across many Wikimedia projects.
They are widely spoken or used in official or educational contexts in several MENA countries.
They provide a shared framework for documentation and collaboration with international partners and communities.
The scope of the project is limited to the mentioned languages; which reflects the priorities and capacity of this phase. However, we will consider other languages as the project evolves. Reda Kerbouche (talk) 17:43, 2 June 2025 (UTC)[reply]
FWIW - for most parts of West Asia and North Africa you're far more likely to be able to communicate in French over Hebrew, Farsi or Turkish. Oh... and Russian these days will stand you in pretty good stead in the Gulf. Regards, Goldsztajn (talk) 03:34, 28 May 2025 (UTC)[reply]
I agree with @Sdkb that the project page does read as corporate-written (or possibly AI-written, with little concrete difference between both). It could be good to clarify it in more concrete terms on the landing page, although there seem to be more detail on meta:The Million Wiki Project/FAQ (to reply to @Toadspike's query, it seems to count new page creations on all projects). Concerningly, neither that page nor meta:The Million Wiki Project/Funding Guidelines talk about how this meshes with our policies on paid editing, despite repeatedly talking about "transparency". Chaotic Enby (talk · contribs) 16:29, 23 May 2025 (UTC)[reply]
Original Media:** Photos, audio, or video content taken or created by the uploader(s).ChatGPT very often generates bullet point lists of the form **Short Title:** Longer explanation of what is meant by the short title. (as it uses **this syntax** to bold text). This very much looks like a remnant of that syntax that wasn't correctly removed, especially since the asterisks don't seem to be referenced anywhere. Chaotic Enby (talk · contribs) 21:36, 23 May 2025 (UTC)[reply]
That's quite concerning. Jtud (WMF), the WMF Grants team should probably be aware of this whole thread (if you're not the right point person, I'd appreciate you forwarding this or letting us know who the right person would be). Sdkbtalk19:18, 24 May 2025 (UTC)[reply]
All major decisions, structures, and policies were drafted by human contributors — the grant committee members — many of whom are seasoned Wikimedians; we made sure no policies were breached. As everybody does, we consulted AI tools to proofread the English draft, e.g. grammar checks and language structure. We understand the importance of human tone and accuracy in Wikimedia spaces, and we truly welcome community edits to improve clarity or remove awkward phrasing or markup remnants. cordially Nehaoua (talk) 17:22, 2 June 2025 (UTC)[reply]
From Meta:The Million Wiki Project/Eligibility Criteria: This effort covers a wide range of countries, including Algeria, Bahrain, Egypt, Iraq, Jordan, Kuwait, Lebanon, Libya, Mauritania, Morocco, Oman, Palestine, Qatar, Saudi Arabia, Somalia, Sudan, Syria, Tunisia, the United Arab Emirates, and Yemen, as well as topics relevant to their diaspora communities worldwide.. There is an obvious omission here, which I hardly need spell out. Can I ask why the 'MENA' region appears to have a hole in it? AndyTheGrump (talk) 16:35, 23 May 2025 (UTC)[reply]
Given how Iran, Israel, and Turkey are all missing, while Somalia is there, it looks like the list of Arab League members was used for some reason (although for some reason Djibouti and the Comoros were excluded but not Somalia). Chaotic Enby (talk · contribs) 16:40, 23 May 2025 (UTC)[reply]
Combined with the requirement that submissions be in a UN official language, I'm not sure this looks like an evenhanded approach to the Middle East. Wehwalt (talk) 17:37, 23 May 2025 (UTC)[reply]
It isn't. Not remotely. And given the issues the English-language Wikipedia already has with partisan editing with regard to many 'Middle East' topics, the last thing we need is to look like we are endorsing such a perspective. This ill-thought-out project should never have been approved in the state it is. AndyTheGrump (talk) 19:37, 23 May 2025 (UTC)[reply]
This ill-thought-out project should never have been approved in the state it is. – They should make this the collective slogan of wikimedia projects. Thebiguglyalien (talk) 🛸21:31, 25 May 2025 (UTC)[reply]
Other than Arabic, Farsi, Pashto, Urdu, Kurdish etc is written using Arabic script. It is *the* most representative script across the entire region, including other scripts would not be "even-handed". Regards, Goldsztajn (talk) 03:51, 28 May 2025 (UTC)[reply]
@AndyTheGrump and Chaotic Enby:, we understand that geopolitical or regional classifications can differ. For example, countries like Turkey, Iran, and Other countries, while geographically part of the broader Middle East, are classified under different regions by the Wikimedia Foundation’s regional structure (e.g. CEE, Northern & Western Europe).The countries listed were selected based on a few practical factors:
Existing connections with local Wikimedia communities and affiliates
Participation in the WikiArabia conference
Inclusion in the League of Arab States, which formed a cultural basis for our first project phase
That said, this is not a political exclusion (it's a reflection of community capacity and scope). We’re open to expanding this framework in the future as our network grows. Reda Kerbouche (talk) 17:51, 2 June 2025 (UTC)[reply]
As far as I know, Iran is very much classified as MENA by the Wikimedia Foundation. Also, that wording of "Turkey, Iran and Other countries" is a bit weird given that there was only one other country mentioned.It could be much better to present it as a contest about Arab countries, not about MENA countries. Chaotic Enby (talk · contribs) 20:19, 2 June 2025 (UTC)[reply]
I would guess that all the countries on the list are more underrepresented on Wiki than Israel is. I completely support the WMF focusing its efforts on areas that are underrepresented, although who knows what they are thinking here. (t · c) buidhe21:49, 26 May 2025 (UTC)[reply]
Hi Reda - sorry that you had to face this intense scrutiny all at once, it's really worth trying to get the community on board before launching stuff like this, then these issues will be dealt with in advance. One more point, you say "we are not paying people for editing" (paraphrase) but the funding page says "Contributors performing significant verified work (e.g., high-quality editing, multilingual translation, metadata curation)." I'm fine with that (a lot of people might not be), but concerned that you gave a different answer. All the best: RichFarmbrough21:16, 2 June 2025 (UTC).[reply]
It perhaps would have been better received had it been posted at WP:VPW or WP:VPM, since this is really just an announcement to the community about an available resource rather than a proposal for the community to implement. signed, Rosguilltalk14:15, 3 June 2025 (UTC)[reply]
Sorry again for the bother, but I haven't gotten any response on how the payment might work regarding our paid editing policies. It could be good to clarify what is meant by contributors being paid for "significant verified work". The FAQ page (item 19) currently states that funds could go to targeted contribution campaigns, is there any information about what they might be? How much involvement do the project's partners (which I assume are providing the funding) have in the selection and organization of these campaigns?As you state that the project is committed to transparency in its funding, it could be great for Wikimedia volunteers to have more information about these points. Chaotic Enby (talk · contribs) 22:41, 2 June 2025 (UTC)[reply]
Stale Drafts in User Space
I see that about a week ago there was a discussion about notification of stale drafts in draft space. There are also stale drafts in user space. There are currently about 39,500 pages in user space that are labeled as drafts but have not been edited in twelve months (and so would have been purged from draft space). I have proposed at Bot Requests that a bot notify the originators of these drafts, if the originators are in good standing, and produce a report listing stale userspace drafts by blocked users (some of whom may be subject to G5). Robert McClenon (talk) 16:21, 27 May 2025 (UTC)[reply]
What problem are you trying to solve here? AFAIK there has never been a consensus for anything like G13 applying to userspace. Thryduulf (talk) 16:42, 27 May 2025 (UTC)[reply]
True, but when labeled as drafts with the AFC submission template, or containing nought but the article wizard text, they are. That is the problem that Robert McClenon is trying to solve. 204.111.137.20 (talk) 16:41, 30 May 2025 (UTC)[reply]
No those aren't the problem @Robert McClenon is trying to solve, because they are already deleted under G13. This must be for content that isn't eligible for an existing process and I'm asking what problem these pages are causing such that we need a process to deal with them (and haven't received an answer). Thryduulf (talk) 17:18, 30 May 2025 (UTC)[reply]
Well I must be misunderstanding then, because generally unless explicitly labelled as something more specific, userspace content is merely treated as random miscellany, sandboxes, essays, collections of links etc. 204.111.137.20 (talk) 18:37, 30 May 2025 (UTC)[reply]
Pages such as User:Arilang1234/Draft/Comrade Chiang Ching are clearly drafts of articles (I have not even attempted to evaluate that example for quality, notability, etc). It's entirely unclear to me though what problems pages like that are causing such that they need to be dealt with, nor what Robert McClenon is proposing to do with them. Thryduulf (talk) 19:40, 30 May 2025 (UTC)[reply]
I know that people already receive notifications for stale draftspace pages they created, if that isn't already being done for userspace pages with the AFC submission template it should be. For other userspace pages I agree that even if clearly a draft of some kind that notifications would be without a clear purpose except perhaps to nag. Though it may be I'm missing something that came up in the discussion that prompted this post which is not linked and I have no ability to find. 204.111.137.20 (talk) 02:38, 31 May 2025 (UTC)[reply]
I'll just note that I recently moved an article (Pine Island Canal) to main space that I started as a sub-page (although not labelled with a "draft" template) 11 years ago, and which went un-edited for 6 years. I presume that by your standards it should have been deleted long ago. I do not believe I ever abandoned that draft, I just often had trouble finding the time and interest to work on it. Donald Albury18:01, 27 May 2025 (UTC)[reply]
I think we should be deleting less drafts, not more of them. If a page has no useful encyclopedic information, then sure I'd understand deletion. But our wiki is a work in progress and if someone can only make a draft, then they make the stepping stones for the next editor. JackFromWisconsin (talk | contribs) 18:25, 27 May 2025 (UTC)[reply]
What do you (Robert McClenon) propose that such originators in good standing do with the notifications? Didn't we used to recommend that users move draft articles to user space if they want to avoid WP:G13? Don't we still do that? I know what I would do with such a notification from a bot, but I don't think it would be very civil. Phil Bridger (talk) 19:55, 30 May 2025 (UTC)[reply]
I am being asked by several editors what problem I am trying to identify, and what I am proposing to do. I think that I have identified one interesting situation, and, in a way, two problems. The interesting situation is that there are 39,525 userspace drafts that have not been edited in one year. I am not labeling it as a problem. One of the two problems is that some editors think that the existence of 39,525 stale drafts is a problem, and want to do something about it, such as review the drafts manually and send some of them to MFD. That is a problem because it wastes the time of the reviewers at MFD, many of whom also improve articles or review AFC drafts or gnome categories, and many of whom also have day jobs. The only solution that I know for that problem is for the reviewers at MFD to Keep the drafts and to tell the nominators to stop ragpicking. The problem that I am proposing to address is that some of the drafts have been forgotten by their authors, who may either want to take another look at them, or realize that they don't have a use for them any more. The purpose of the bot is to notify the authors of the forgotten drafts that the drafts are there. I know that I sometimes start work on things and forget about them. I am not proposing that the drafts be deleted, unless the author chooses to tag them with U1 and/or G7. Robert McClenon (talk) 02:47, 31 May 2025 (UTC)[reply]
User:Phil Bridger writes: I know what I would do with such a notification from a bot, but I don't think it would be very civil. Why not just delete it? Deleting a notification from a bot isn't uncivil. I can see that some authors would want to opt out of receiving the notifications, and that is a feature that can be discussed in the bot approval process. Robert McClenon (talk) 02:47, 31 May 2025 (UTC)[reply]
So some editors will stop complaining about the existence of unfinished drafts,
So I won't have to listen to complainers complaining about other people not finishing everything they start.
Because even if I thought that last one was worthwhile, the second one probably isn't going to work in a large fraction of cases.
In terms of a BOTREQ, I suggest not spamming long-inactive editors and/or accounts with no e-mail address. There's no point in trying to reach inactive editors by posting on their talk pages.
The process that I think would actually be effective is:
Edit Category:Stale userspace drafts to clearly explain that the purpose of this category is to help currently active editors (e.g., anyone complaining about the existence of drafts in that cat) find drafts that they might want to adopt and finish themselves. Perhaps we could even rename the cat to something like "Userspace drafts that may be available for adoption".
Allow editing the edit summary after you publish it
I suggest that contributors be able to edit their own(not the ones of other editors, for quite obvious reasons) edit summaries in the article history after they publish it(Also, there should be a record of edit summaries edited), so that in case of bad edit summaries, the contributor can go back and change their edit summary.
This solves the problem where people forget to add edit summaries(or accidentally press the publish changes button before finishing writing) or when a user realizes the edit summary probably wasn't good enough. Thehistorianisaac (talk) 01:02, 28 May 2025 (UTC)[reply]
This would require a significant software change, and similar requests have been declined before. phab:T15937 is open (and has been since 2008) and contains some discussion and links to older discussions. Thryduulf (talk) 02:13, 28 May 2025 (UTC)[reply]
That is just not happening. If we allow one, we risk ending up with a situation where we create a infinite turtles of edit summary of edit to edit summary of edit of edit summary of edit of edit summary. Sohom (talk) 21:25, 28 May 2025 (UTC)[reply]
I don't see how this would work, there would have to be an edit summary log implemented for administrators as well as some sort of reverting, however I see how this could also be malicious if there isn't a time limit (timer) for these edits. Also, if there was a record for this, there would need to be at least some filtering to exclude blank summaries and spam to not clog up the logs. Gonna eatpizza (talk) 17:07, 30 May 2025 (UTC)[reply]
I sometimes forget an edit-summary or accidentally mis-state some detail. Easy enough to make a WP:DUMMY EDIT to fix it. Or better yet, I've started a habit of making an actual good edit to that article, where the ES mentions the current edit and also the preceding one with the bad ES, to atone for my mistake:) DMacks (talk) 17:17, 30 May 2025 (UTC)[reply]
Yes, dummy edit seems fine. You could see it as a flattened version of the proposal where the revision comment history that would be required by this proposal is flattened into the revision table and stored there. Sean.hoyland (talk) 17:24, 30 May 2025 (UTC)[reply]
Should the Wikipedia logo be changed for one day to commemorate the 7 millionth article? To the right is the modified version of the last millionth's logo.Catalk to me!02:39, 28 May 2025 (UTC) Edit: Chaotic Enby has created a logo that better resembles the one used in the last million. 23:54, 28 May 2025 (UTC)[reply]
This. The serif font, yellow/gold gradient, and banner border are all weird. I know Wikipedia is known for having a long-outdated look (and some of us are proud of this), but if we're creating something new to represent our progress it should look...new. Toadspike[Talk]06:38, 28 May 2025 (UTC)[reply]
Changing the logo would probably take at least a couple days, maybe a week or two, because of needing to get consensus, then needing to write a patch and deploy it. Those are not fast processes. Would folks still want this if it's weeks after the 7 millionth article date? –Novem Linguae (talk) 04:18, 28 May 2025 (UTC)[reply]
Readers aren't necessarily checking the exact number, so celebrating the milestone even a few days/weeks late would still be just as meaningful in my opinion. Chaotic Enby (talk · contribs) 11:42, 28 May 2025 (UTC)[reply]
A better source of inspiration?Meh, that logo isn't especially modern or elegant – I especially second Toadspike's more detailed remarks. While a serif font could be okay (assuming we're going for Linux Libertine Bold), the border on the text, and the yellow-white gradients, all look tacky and not very professional. If we really want, a variant of the other 6 million logo would look more elegant.The circumstances are also less than ideal, as, from what I understand, the 7 millionth article came in the middle of a batch of 200-something mass created city council articles, which isn't really what we wish to encourage.Edit: with a cleaner logo, support – although I still believe that the circumstances are less than ideal, it is still a strong message to show that Wikipedia is still just as thriving. Raw article count shouldn't be encouraged for editors, but these flashy logo changes are mostly destined to readers (and potential readers), and the communication opportunity is pretty good. Chaotic Enby (talk · contribs) 09:49, 28 May 2025 (UTC)[reply]
I'm sure there are non mass-created articles in the final 1,000. At a slight topical shift, if we want to encourage quality, we're currently at 6,741 FAs. A bit of work to go to catch up to a 0.1% total article rate, but we could also celebrate 7,000. On a longer view, we could begin planning for the big 10k FA, presumably with a much longer lead time than we had for this. (Although in both cases only if this doesn't pressure the FAC coords, who presumably should treat potential milestone FAs the same as any other.) CMD (talk) 09:58, 28 May 2025 (UTC)[reply]
A logo with a more fitting styleSadly, the 6 million logo above wasn't available in a SVG version (besides a lower quality autotraced one), although I've tried to make one in the same style for 7 million articles. Feel free to make any improvements to it! Chaotic Enby (talk · contribs) 11:18, 28 May 2025 (UTC)[reply]
Support this version. Thank you for creating it, Chaotic Enby! I agree in principle with the "quality, not quantity" folks, but the two are not mutually exclusive. 50K GAs and 10K FAs are milestones we should reach soon, which we can also celebrate with a logo change. But we celebrate easily-understood milestones to encourage readers to become editors, and article count is the most easily-understood milestone of all. Toadspike[Talk]12:56, 28 May 2025 (UTC)[reply]
Support this version. I think that changing the logo for a brief period of time is a great way to advertise the progress done so far. Quality would be way harder to advertise in my opinion (Since it is way harder to shorten into one number and to objectively measure) Madotea (talk) 18:05, 29 May 2025 (UTC)[reply]
Oppose in favor of Wikipedia celebrating quality over quantity for a change, which is even more important in the age of AI. Generating a lot of text is not an accomplishment in and of itself. Levivich (talk) 12:02, 28 May 2025 (UTC)[reply]
Btw I'd probably support marking major milestones like 10M and 25M articles, but I don't support changing the logo every 1M articles. It's WP:EDITCOUNTITIS to keep track of such small intervals--the encyclopedia grew by 16%, from 6M to 7M. Wow, big deal. Levivich (talk) 16:56, 29 May 2025 (UTC)[reply]
The interval isn't the passage of time, it's the article count. We already celebrate the passage of time: Wikipedia's 20th birthday was celebrated and its 25th will be celebrated next year. Sure, change the logo for those anniversaries. But our article count increasing by 16% does not seem like anything worthy of celebration to me. When you have 6 million articles, adding another million is not a big deal. Even less so when we hit 8 million. I'd rather we reserve logo celebrations for actually-meaningful milestones, like 5,000 FAs, or 500,000 women biographies, or a million articles about the southern hemisphere... take your pick, there are plenty of meaningful milestones to choose from. "16% increase in article count" isn't one of them, IMO. Plus, it sends the wrong message: that what we're about is article count. Given that every year there will be new notable topics (new notable events, new notable works, etc.), article count increasing is a given; it's not an accomplishment in and of itself. Levivich (talk) 19:21, 29 May 2025 (UTC)[reply]
Oppose Anything like this or Wikicup that encourages simple creation without any expectation of quality is bad behavior. How many of the 7M articles are GAs or FAs? Its less than 1% of the total article count which is not a good look if we're just praising simple creation. Masem (t) 12:05, 28 May 2025 (UTC)[reply]
0.69% GA or FA, although GA is likely bottlenecked more by reviewing time than it is by content creation. CMD (talk) 12:45, 28 May 2025 (UTC)[reply]
How does the Wikicup encourge simple creation without any expectation of quality? Points are only awarded for quality articles (GAs, FAs, etc.) and for DYKs. Cremastra (u — c) 12:36, 28 May 2025 (UTC)[reply]
I still feel that the Wikicup encourages rushing processes along to earn points during the limited time the cup is held. Any type of gamification of wikiprocesses can be a problem. Masem (t) 17:24, 28 May 2025 (UTC)[reply]
No comment on the oppose, but as to the WikiCup comment the opposite is true. I and the other WikiCup judges have been disqualifying entries rather frequently for not being of high quality. I do get the gamification concerns though, but claiming the Cup "encourages simple creation without any expectation of quality" is false. Epicgenius (talk) 20:09, 28 May 2025 (UTC)[reply]
Gamification is a great tool. Backlog drives can make good progress on or clear out a backlog, and also serve as a great recruitment tool and raise WikiProject morale. Definitely a net positive, imo. Outliers can be dealt with via ANI and/or a re-review system. –Novem Linguae (talk) 20:28, 28 May 2025 (UTC)[reply]
Oppose. We shouldn't celebrate an editor dumping nearly 200 identical poor articles in violation of WP:MASSCREATE just so they can claim the 7 millionth article. The less attention we give to this, the better chance we have to stop such silliness. Quality over quantity seems more apt than ever here. Fram (talk) 14:46, 28 May 2025 (UTC)[reply]
Despite having more articles, our pageviews have not really changed - existing in a range of 7 - 8.5 million since 2015. While it's possible that without an expansion of articles we'd be even lower, I am skeptical that our readers actually care about our number of articles. Instead I think it makes us as editors feel good. I think there's a way to make the editing elite feel good without changing the logo, and also agree with the general focus on quality of information for our readers rather than focusing on the quantity of articles, and so I oppose this logo change but support other ways of celebrating the milestone. Best, Barkeep49 (talk) 15:09, 28 May 2025 (UTC)[reply]
According to Wikipedia:Statistics#Page views: Most articles have very low traffic. In 2023, 90% of articles averaged between zero and ten page views per day. The median article gets about one page view per week. Because the top 0.1% of high-traffic articles can each get millions of page views in a year, the mean is about 100 times the median. If that % still holds true today, it would mean that ~6,300,000 articles of the 7 million articles average between 0 and 10 page views a day. Some1 (talk) 23:37, 30 May 2025 (UTC)[reply]
Support we can find time to celebrate, and though 7 million articles of varying quality is arbitrary, all milestones on a volunteer encyclopedia are probably a bit arbitrary. and ChaoticEnby's work looks nice. Bluethricecreamman (talk) 17:16, 28 May 2025 (UTC)[reply]
Given the fractious nature of the post-7 million discussion and the incentive structure that led towards it, and perhaps very pertinently due to it being seemingly impossible to identify the actual 7 millionth article given how rapidly things are in flux, I have come around to leaning oppose towards celebrating a specific article. I'm not at this moment opposed to celebrating "7 million articles" in the plural, but it should be clear that the proposal is not to "commemorate the 7 millionth article". CMD (talk) 20:13, 28 May 2025 (UTC)[reply]
Mild oppose Would have little impact and celebrates the wrong thing (article count vs. quality) North8000 (talk) 21:00, 28 May 2025 (UTC)[reply]
Conditional Support, upon consensus on which article to represent the 7-million articles milestone at Wikipedia talk:Seven million articles, and that the chosen article is of acceptable quality. There is a shortlist of articles which may represent the milestone. While some may have started as stubs or start-class articles, the respective authors of the shortlisted articles and other editors have started on improving the quality of the articles, possibly in hopes of their article getting chosen at the end of the consensus building exercise. There is no rush to push the logo out. – robertsky (talk) 04:08, 29 May 2025 (UTC)[reply]
"The English Wikipedia has reached 7,000,000 articles with [chosen article]" seems like a misleading statement then if we don't exactly know what the 7-millionth article is and are just choosing one to represent it. Some1 (talk) 12:04, 29 May 2025 (UTC)[reply]
Out of curiosity - what is the current count of GA & FA articles? Are we anywhere close to a milestone on those? If so… THAT would be something that is much more meaningful to celebrate. Blueboar (talk) 17:00, 29 May 2025 (UTC)[reply]
We're at 41,835 GAs, 6,741 FAs, and 4,655 FLs (for a total of 53,231 quality articles). I'm guessing the next big milestones would be 50,000 GAs, 7,000 FAs and 5,000 FLs, and the latter two would be reachable in one or two years (although I doubt enough readers care about lists to celebrate it on the main page). Chaotic Enby (talk · contribs) 18:19, 29 May 2025 (UTC)[reply]
Comment: Edited the 6 million red logo to be 7 million. Font for the red banner is Roboto Condensed, and then bolded, if anyone else wants to do it (I have no idea how to properly photo edit.) Red 6 mil logo but for 7 milARandomName123 (talk)Ping me!21:24, 29 May 2025 (UTC)[reply]
Support. We have to celebrate the small wins. This is good PR, attracts press attention, puts Wikipedia in the news, reminds people of the website that is secretly funneling ChatGPT's wisdom. The next 8M milestone may be 6-7 years away, and that's if the project survives – it most likely will, but don't take it for granted. Levivich makes a reasonable point above about celebrating quality instead, but it's not easy to communicate a milestone like 50,000 good articles to the intended audience ("are the other 6.5M articles bad?"). Featured article milestones are a better sell, but our count of FAs is embarrassingly low. – SD0001 (talk) 21:57, 29 May 2025 (UTC)[reply]
On PR: I'm unsure about the design style of the logos put forward. They are inconsistent with Wikipedia/MediaWiki's design style, though I certainly cannot make anything better. Aaron Liu (talk) 03:26, 30 May 2025 (UTC)[reply]
My proposal went with the Linux Libertine font, which is the one used in Wikipedia's logo typography (although bolded for better readability, so the letter shapes slightly differ). That's the main reason why I didn't want to copy the exact style of the "6 million" logo. Chaotic Enby (talk · contribs) 13:07, 30 May 2025 (UTC)[reply]
"50,000 good articles to the intended audience ("are the other 6.5M articles bad?") What happened to the other 0.45 million? :P Regards, Goldsztajn (talk) 21:59, 30 May 2025 (UTC)[reply]
SupportChaotic Enby's version for up to a week (seven days for seven million?) While I'm definitely in the quality-over-quantity camp, I think it's worth making a (not-too-gaudy) statement that can be appreciated by the media and casual visitors – we're still here, we're still creating and improving content, and we're still mostly human. For the same reason, if we do have a special logo it should be up for more than 24 hours – it may be easy for us insiders to forget that people who care about Wikipedia don't necessarily visit the site every day. – ClaudineChionh (she/her · talk · email · global) 02:04, 30 May 2025 (UTC)[reply]
Support I like the red 7 million logo, and I like seven days for seven million. This is a fun tradition, and its a little victory to celebrate! We should be proud of what we've accomplished! CaptainEekEdits Ho Cap'n!⚓03:57, 30 May 2025 (UTC)[reply]
Changing to oppose. The moment has passed. I'm very disillusioned here. How could we not make a simple logo change happen in time?? We did it easily, and with no fuss at six million. We took like... a day, and nobody raised a fuss. At any rate, with Vector 2022, we need a square logo (sans the Wikipedia subtitle), in an svg, which nobody has even created. So chock this up as a dismal and upsetting failure. When we hit 8 million, I'll make sure to do this like 6 months before we think we'll hit that number, so we have enough time for everybody to complain and do like three close reviews. Super disappointing. Where'd our spirit of fun go? CaptainEekEdits Ho Cap'n!⚓05:17, 4 June 2025 (UTC)[reply]
Support Variety is the spice of life and so celebrating this with a splash is a healthy sign of continuing vigour. I'm not fussy about the format – the key thing is to show that we're still alive and kicking.
Editors who prefer quality to quantity can celebrate that too but the numbers there are not so good. Currently there are just 6,743 FAs and 41,837 GAs and my impression is that those numbers don't rise so steadily. So, we should count our blessings and celebrate what we can.
Ugh. A fine demonstration of Wikipedia's unreliability; the English language Wikipedia has 7,005,640 articles (and Wikipedia as a whole has 65,043,936). What's celebratory to some is self-congratulatory to others, and this does beg the question "but are they any good?" NebY (talk) 12:04, 30 May 2025 (UTC)[reply]
Support each million articles is a huge milestone (considering each one has to hold its own weight). I think either ChaoticEnby's version or the one initially proposed would work.
Support red or pink ribbon versions. This is an important milestone that should be celebrated! Yeah, many (maybe even most) articles aren't of great quality, but should that really matter? Wikipedia will always be a work in progress, and said progress should be recognised wherever possible. Loytra (talk) 18:25, 30 May 2025 (UTC)[reply]
Support but make the text on the ribbon gold. I have been waiting for this for ages, Finally I am here for an event that I am not blocked for! Toketaatalk18:28, 30 May 2025 (UTC)[reply]
Comment - maybe including a casualty count would make it more interesting - x articles, y editors imprisoned, z articles taken down by court order. Maybe y is zero-ish for English Wikipedia and z is one-ish (temporary). More impressive than 7 million articles in a way. Sean.hoyland (talk) 18:44, 30 May 2025 (UTC)[reply]
Notably, something needed is going to be showing of community consensus -- such as a closed discussion finding as such. — xaosfluxTalk20:59, 30 May 2025 (UTC)[reply]
The community already did this for the 5M and 6M milestones and so there's an existing consensus and tradition. Andrew🐉(talk) 21:27, 30 May 2025 (UTC)[reply]
You might want to cut and paste this bullet and its replies into an "implementation" sub-heading. I agree that getting someone to formally close the discussion would be a good idea (maybe list it at WP:ANRFC?). Do we know which of the multiple proposed logos achieved consensus? Do we know how many days the altered logo should be up for? –Novem Linguae (talk) 22:37, 30 May 2025 (UTC)[reply]
@CaptainEek: "solid support"? By my rough count it's a little less than 2/3 supports and 1/3 opposes, with a fair number of weak on either side. I'm not outright opposed, but I think it's a stretch to say "solid" given Wikipedia's notions of consensus. Regards, --Goldsztajn (talk) 22:12, 30 May 2025 (UTC)[reply]
@Goldsztajn at a rough count of 20 to 8, that seems solid to me, and it's going to take some time to get the ball rolling. Like, if you were in a room of 28 people, and 20 of them were on one side, even if they were grumbling, you'd say "clearly they have the majority". CaptainEekEdits Ho Cap'n!⚓22:20, 30 May 2025 (UTC)[reply]
They don't do it 3/7 days in a week? I didn't realize how much slower the process is these days. I guess the lesson for 8 million is to plan out a logo change ~ten thousand articles before it happens. CaptainEekEdits Ho Cap'n!⚓01:12, 31 May 2025 (UTC)[reply]
I'd concur with the 20 support, but I count 12 opposes (including my Meh, but not Chaotic Enby's) that are more on the oppose side than the support side. Regards, Goldsztajn (talk) 00:36, 31 May 2025 (UTC)[reply]
FWIW - the last print edition of Britannica had 40,000 articles, I'd be less grouchy celebrating 7 million Wikipedia articles *and* more GAs than the last print edition of Britannica had articles. Regards, Goldsztajn (talk) 02:40, 31 May 2025 (UTC)[reply]
Support and it makes me a little sad that even something this tiny and cute is being dragged into the deletionist hellpit. I guarantee no reader is going to look at the logo and think "wow, these articles must suck and/or be created by the Wikipedia scapegoat." Gnomingstuff (talk) 16:39, 31 May 2025 (UTC)[reply]
Support: I think we’re probably due for a discussion about how and whether to celebrate x millionth article milestones going forward. However, I say we should celebrate this milestone with a logo change, even if for one last time. Spirit of Eagle (talk) 23:21, 31 May 2025 (UTC)[reply]
I am not opposed to this, but I would point out that the new Vector skin's Wikipedia logo is quite small nowadays. If we implement the same logo design as in years past, it might not be legible anymore. Mz7 (talk) 02:47, 1 June 2025 (UTC)[reply]
Oh, and on the subject of Vector 2022 the logo actually consists of three separate images (logo, wordmark, tagline) which are specified separately in the config file (whereas legacy Vector still uses one file). So you will need to change the logo proposal to fit in that format. * Pppery *it has begun...03:05, 1 June 2025 (UTC)[reply]
Hmm, what if we just temporarily change the tagline away from "The Free Encyclopedia" to a ribbon that says "7 Million Articles". Sounds like that is possible and would be the cleanest solution. Mz7 (talk) 03:09, 1 June 2025 (UTC)[reply]
Ehhh, I really dislike that design. I would rather the ribbon text be illegible than adopting a yellow Wikipedia logo with font that looks like we're back in the 90s (lol). Mz7 (talk) 03:03, 1 June 2025 (UTC)[reply]
Support for a week, as a tradition that shines a positive light on Wikipedia's progress. I prefer the ribbon style, with Chaotic Enby's version as first choice for its SVG format, but I would rather see any commemorative logo implemented than to have this discussion deadlocked any further. — Newslingertalk11:07, 1 June 2025 (UTC)[reply]
Oppose In favour of Wikipedia celebrating quality over quantity. Why should we strive to i-don't-know-how-many stubs without serious content? The Bannertalk19:07, 1 June 2025 (UTC)[reply]
Support. It is still a notable achievement. We won't have a perfect encyclopedia where each and every article is GA-grade until the Sun burns out, but I think we can certainly celebrate 7 million articles. It is a good way to communicate to casual readers about the number of articles that Wikipedia had. SunDawn (talk) 01:43, 2 June 2025 (UTC)[reply]
Support fun times. The "quality over quantity" argument is specious. Only 7 million things for the entire history of the universe are found to be notable? Our quantity is on the low end. Furthermore it infers nothing about quality, they are not mutually exclusive traits. -- GreenC01:55, 3 June 2025 (UTC)[reply]
Here's the square!To clarify, I did resize it to be square at one point, but the MediaWiki documentation did mention that there were exceptions to the "square rule" if the logo had text underneath (in which case 135x155px seemed appropriate). The square thing appears to be for the logo alone (without text) in new skins like Vector 2022, and I just uploaded it separately. Chaotic Enby (talk · contribs) 08:43, 4 June 2025 (UTC)[reply]
Oppose, creating three URLs with 200 words each shouldn't be treated as superior to creating one URL with 600 words. It's already hard enough to maintain quality control without telling people that having the first edit in the article history is somehow more meaningful. Thebiguglyalien (talk) 🛸18:14, 4 June 2025 (UTC)[reply]
"Basic" is not a good description of the topics this board is for - to me "basic" implies simple, uncomplicated questions about fundamentals rather than anything to do with subject matter. Questions relating e.g. policy belong on the policy village pump regardless of there complexity, questions unrelated to the subject of the other village pumps belong here even if they are very complex. If the length of "miscellaneous" was an issue (and I'm not convinced it is) then surely the obvious thing would be to change it to "misc"? Thryduulf (talk) 11:32, 1 June 2025 (UTC)[reply]
I think "miscellaneous" is fine. If we were going to change it, "basic" is not at all correct. "Other" would be more accurate. Anomie⚔11:54, 1 June 2025 (UTC)[reply]
Proposal: Reimplement the births and deaths in the pages after 1980
I would like to propose that we reimplement the births and deaths of people of people born after 1980. As a reader, I've always enjoyed reading about which famous people were born in a particular year, and I was hoping that we could bring this back. I could say that there are too many people to be included, but if we set clear criteria on who is included and not included, I think would be better. Interstellarity (talk) 01:29, 2 June 2025 (UTC)[reply]
My browser would struggle to load such massive pages. The death lists are already split into months, with reduced citations. Catalk to me!02:04, 2 June 2025 (UTC)[reply]
How is it determined who gets to go on those pages anyway? The only guidance I've found so far is Wikipedia:Timeline standards#Births section which states There may be other restrictions as to who may appear, but absent other consensus, the person must have a Wikipedia article. That text was added by Arthur Rubin with this January 2017 edit that also changed "The Births section list all births in that year" to "The Births section lists births in that year". The edit summary cites a "consensus at WT:YEARS" but I haven't been able to identify the relevant discussion in the archives. I did find a link to Wikipedia:WikiProject Years/criteria#Births and Deaths that states in its entirety At the least, the person must have an individual Wikipedia article. "Death of John Doe" or "Murder of John Doe" does not qualify. Possible exception for the birth of twins or multiples.
The essay Wikipedia:Recent Years exists but is marked as inactive and it's not clear how much consensus it has. That states it applies only to the years 2002-2025. The Births section states One method of determining which births could be included is if there are Wikipedia articles in English and at least nine non-English languages about the individual in question. Prince George of Cambridge, for example, has several non-English articles on him, listed on the left sidebar. Although inclusion may then be automatic, it will not necessarily be permanent. and the Deaths section reads Persons who are internationally notable are included, as demonstrated by reliable sources. Heads of state or government (other than interim/acting leaders) are typically considered internationally notable..
If you go back long enough (c.2005), I remember once seeing a recommendation to always add newly created articles to the relevant year/day pages! If we kept that up now, there would be 18,000 entries on some of the 1980s pages.
I had a poke through the WT:YEARS archives as well and I think this may be one of those practices that emerged without an explicit discussion about it - certainly we must have been being selective by the time we hit 2-3 million articles in 2010, just on practical grounds. Andrew Gray (talk) 22:34, 4 June 2025 (UTC)[reply]
Latitude and longitude
Hi all - not sure whether this is possible but it would be nice. I see a lot of latitude and longitude coordinates given to impossibly precise levels of accuracy - buildings and structures given with coordinates like 41.572947546321°N, 125.462903749248°W. While I like accuracy, this pinpoints a building to within 1/1000 of a micrometre - which is probably overkill. Is there anyway of automatically truncating such precision to, say, six decomal places? That would still give precision within about 20 centimetres, which is close enough for any practical coordinate purposes. (PS, I'd prefer if they were all in ° ' ", but that's probably just me and not worth doing). Grutness...wha?03:59, 3 June 2025 (UTC)[reply]
It's the fault of whoever added it like that and you are welcome to change it. It's hard to do automatically, though, since the proper precision depends on the size of the thing that is being located. A building is worth more digits than a river, etc. Maybe a bot could be written for certain types of articles that the bot can recognise, but I'm not sure it would have few enough false positives. Zerotalk07:33, 3 June 2025 (UTC)[reply]
Most of these will be copied directly from services like Google Maps which displays the location you click to 5 decimal places but puts about 15 decimal places on the clipboard. e.g. on it's minimum zoom level I got 51.23262708044534, 0.23095125460548796 despite 1 pixel making tens of kilometres of difference at that latitude.
The first step to fixing over-precision is to identify the scale of the issue. For example get a bot to list all the articles with coordinates more precise than 6 decimal digits (or the equivalent in DMS). There is likely to be some way of cross-referencing articles with Wikidata to group them by the "instance of" property. Thryduulf (talk) 09:18, 3 June 2025 (UTC)[reply]
My thought would have been to trim down some overly-precise examples and leave an edit summary referring to WP:OPCOORD or the coord template documentation. When other editors see it some may take note and make similar edits. However, the guideline seems a bit technical and I suspect that some editors would find it easier to understand "If it's the same size as a football field use X level of precision" - perhaps it would be helpful if OPCOORD also included a precision/object conversion chart equivalent to the xkcd table. EdwardUK (talk) 15:13, 3 June 2025 (UTC)[reply]
Ideally yes, but rows need to be worded carefully. Going back to the structure example earlier, there are some bridges that have a rather extreme length dimension, however we are still going to want coordinates that are within its width dimensions and approximately midway down the length. 184.152.65.118 (talk) 16:14, 6 June 2025 (UTC)[reply]
The OP's suggestion is good. I don't think we have anything on Wikipedia that warrants precision to less than 20 centimetres, so a bot could easily truncate to 6 decimal places. Articles where lower precision is needed (such as cities or countries) can be taken care of manually. Let's not let the best be the enemy of the good. Phil Bridger (talk) 21:44, 6 June 2025 (UTC)[reply]
If we have a reliable source that cites the coordinates to greater precision than that we should keep them. I sort-of remember Geni mentioning that this is the case for some museum exhibits. Thryduulf (talk) 23:11, 6 June 2025 (UTC)[reply]
Wikivoyage imports ("copies", not "dynamically transcludes") coordinate data from Wikidata when it's available. Wikidata stores the lat/long data as degrees/hours/minutes (12° 3' 45"). Wikivoyage uses the decimal format (12.345). One result of the automated conversion is that I've seen a few that look like "12.34500001". This is false precision. WhatamIdoing (talk) 00:13, 7 June 2025 (UTC)[reply]
There must be articles on smaller objects, but I don't know that latitude and longitude would be appropriate. Are there any articles on individual electrons? I guess not, because they are indistinguishable particles, but we can work up from there. Phil Bridger (talk) 08:32, 7 June 2025 (UTC)[reply]
From my layman's knowledge of quantum mechanics I would say that they don't exist any more, having been destroyed by the process of detection. I may be wrong. Phil Bridger (talk) 19:48, 7 June 2025 (UTC)[reply]
I think that even with objects as small as the Strawn-Wagner Diamond, 20cm is likely close enough - unless we want to go around altering the coordinates every time the cabinet is dusted! Even then, 7 digits would put it within an inch. We don't need anything listed to 12 digits unless we start getting articles about specific atoms, and they vibrate so... that way lies madness. Grutness...wha?12:33, 7 June 2025 (UTC)[reply]
English Wikipedia doesn't specify a specific font to be used for article text. It just uses the one configured in your browser for sans-serif text, so you can change your browser to use a different sans-serif font. isaacl (talk) 21:59, 6 June 2025 (UTC)[reply]
@AbchyZa22 It would have been better to ask @Minorax this question directly on their user talk page, as they are best placed to answer it.
Trademarks generally require you to use the registered mark, otherwise the trademark is rights are lost, e.g. in the US if you haven't used a trademark for 3 years it is removed, see Trademark#Maintaining registration. A logo from 2002 which is not in current use shouldn't have any remaining trademark rights. 86.23.109.101 (talk) 22:09, 28 May 2025 (UTC)[reply]
{{Trademarked}} is generally used for files that are in the public domain or ineligible for copyright as logos are still subject to trademark protection despite not being copyrightable. {{Non-free logo}} already covers that. --Min☠︎rax«¦talk¦»02:28, 29 May 2025 (UTC)[reply]
I was going to write an article on Henry Benvenuti when I discovered Everybody Wiki has its own "Henry Banger Benvenuti" article which looks like a perfectly reasonable one to just import. We used to have our own Henry Banger Benvenuti, long since deleted for copyvio, but the Everybody Wiki version doesn't look like it's based on that. Everybody Wiki is CC BY-SA 3.0 so as far as I can tell there's no problem with copying it. The only issue I can think of is that we're CC SA-BY 4.0; is that close enough to satisfy the "Share Alike" constraint?
And, sigh, it looks like I'm not allowed to link to Everybody Wiki because it's on the blacklist, which will make it annoying to provide proper attribution. RoySmith(talk)15:45, 30 May 2025 (UTC)[reply]
AFAIK CC BY-SA 3 may be republished under CC-BY SA 4. That remote article does not appear to have any licensing for their image. It doesn't look like that site has Special:Export configured, so we can't just to a transwiki (if you know more about exporting from that site let me know). — xaosfluxTalk16:11, 30 May 2025 (UTC)[reply]
Although, I've started to discover that the article's author may have been drummed out of enwiki due to UPE and socking, so possibly this isn't a great idea to begin with. RoySmith(talk)16:25, 30 May 2025 (UTC)[reply]
I have no idea why they disabled Special:Export, but it is possible to export via the API: https://en.everybodywiki.com/Special:ApiSandbox#action=query&format=json&export=1&exportnowrap=1&titles=Henry%20Banger%20Benvenuti&formatversion=2* Pppery *it has begun...21:30, 30 May 2025 (UTC)[reply]
General help on Accelerationism article
I've been overhauling the accelerationism article over the past few months to include ideas under its original definition which, while summarized in the intro paragraph, were otherwise pretty sparse for most of the article's existence as far as I can tell. I've been mostly alone in that, and now I want to get some general help from others on it, preferably from people with access to Wikipedia Library since public sources tend to be pretty sparse on specific info. Previously lacking Wikipedia Library access, I used some primaries which I think is justified by secondaries naming those authors/works as significant in the movement (considering the rules on WP:PRIMARY), but I nonetheless feel like I may be falling into just summarizing specific source texts in sequence rather than talking about the ideas/concepts more generally while referencing source texts. Plus, it takes time and energy to comb through papers for info I can use. The article could be improved a lot further with other people for second opinions on editing and for reading through papers. Shredlordsupreme (talk) 01:18, 2 June 2025 (UTC)[reply]
We had a medium-sized spike in unique devices views this past month [18], but it's really noticeable on other projects unique devices, pageviews. This has to be some weird statistical artifact (I don't seriously believe Wikibooks has set a record high in readership), but what is going on? Cremastra (u — c) 01:26, 7 June 2025 (UTC)[reply]
Interesting. In a few days, the Foundation should be publishing its monthly "Movement Metrics" report for May, which might shed further light on this (WMF analysts have access to internal data which can be helpful in assessing e.g. whether something might be bot traffic misclassified as coming from humans). For what's it's worth, the preceding April 2025 report, in contrast, reported that User pageviews declined by 3.9% year over year that month. (And also that "Automated pageviews" were down 41.4% YoY, somewhat in contrast to other narratives WMF pushed at the time.) Regards, HaeB (talk) 04:21, 7 June 2025 (UTC)[reply]
Done --Ahecht (TALK
This section is resolved and can be archived. If you disagree, replace this template with your comment. Andy Mabbett (Pigsonthewing); Talk to Andy; Andy's edits 18:38, 2 June 2025 (UTC) 
A question about accessibility. When I watched the demo video, it looks like the default position for the "simple summary" was collapsed. For our visually impaired readers and editors who use screen readers to access Wikipedia, would this summary be available to them/us. Because in order to view and/or hear the summary, it requires interaction (clicking on it to open it), which obviously screen readers are not capable of. And per our guidelines at MOS:COLLAPSE, content in an article (if this summary is to be considered content), should never be collapsed by default. So how would this feature be beneficial to our visually impaired readers/editors if it is not accessible? We have alternative text for images, so has there been any consideration given by the develpers for alt text for this feature if it is to remained collapsed by default? Isaidnoway (talk) 07:47, 5 June 2025 (UTC)
Polygnotus (talk) 04:26, 5 June 2025 (UTC)
View all 20 community-submitted tasks that were resolved last week.
You are invited to join the discussion at Wikipedia:Templates for discussion/Log/2025 May 26 § Template:R from non-preferred capitalisation. Thryduulf (talk) 19:04, 26 May 2025 (UTC). Thryduulf (talk) 19:04, 26 May 2025 (UTC)
_2002.png?lang=en){kind=link}
_2002.png&diff=prev&oldid=1292332449){kind=link}
_2002.png){kind=link}