Wikipedia:Bots/Noticeboard

Double redirects

What active bots do we have that fix double redirects? I just came across a template, Template:Huế, that had been moved twice in the last 24 hours; I decided to manually fix the resulting double redirect, but while checking I found that there were two double redirs, and no less than three triple redirects. All are now fixed with these edits. But surely a bot should have passed by at some point and fixed them automatically? --Redrose64 🌹 (talk) 10:54, 20 September 2026 (UTC)

EmausBot, Xqbot, probably more that I'm missing. Tenshi! (Talk page) 10:59, 20 September 2026 (UTC)

Apologies for forgetting to update the vte links... Looks like from this discussion that Template redirects should get handled immediately by Emausbot, but if not they'll be covered when the Special page gets updated. Xqbot also goes off the omve log. Primefac (talk) 11:52, 20 September 2026 (UTC)

Project statistics table not getting updated

There is a project statistics table here: Wikipedia:Version_1.0_Editorial_Team/CE_articles_by_quality_statistics that is showing data about a year old. How can I get it updated? Apologies if this is the wrong place to ask, but I suppose there is a bot that is supposed to be updating it, correct? The table is used by the WP Civil Engineering Project at Wikipedia:WikiProject Civil engineering. I would ask there, but that project is a bit dormant, and I doubt anyone would know how to update the table. Noleander (talk) 22:58, 20 September 2026 (UTC)

Did you try asking at Wikipedia talk:Version 1.0 Editorial Team/Index?

It looks like it stopped when Category:CE articles by quality was renamed to Category:Civil engineering articles by quality, causing the bot to put the statistics at Wikipedia:Version 1.0 Editorial Team/Civil engineering articles by quality statistics instead. Anomie⚔ 23:39, 20 September 2026 (UTC)

Thanks for that info. I suppose I'll update the CE project to use the new table. You're a Wizard, Anomie! Noleander (talk) 23:52, 20 September 2026 (UTC)

Wikipedia:Bot requests not archiving

Is something broken on Wikipedia:Bot requests? Multiple very old threads as well as those with {{Done}} on them are not archiving. I even tried adding User:ClueBot III/ArchiveNow with no success... Anyone know whats going on? Zackmann (^{Talk to me}/_{What I been doing}) 05:18, 29 September 2026 (UTC)

Since ClueBot III has been archiving other pages, it's a problem specific to that page. There are several possibilities:

• unclosed markup, or markup that is opened in one section isn't closed until a later section
• presence of a blacklisted URL
• changes to the parameters of {{User:ClueBot III/ArchiveThis}} - not the case here
• changes to the header section - not the case here

The problem need not be in a section that is eligible for archiving; it could be anywhere.

Adding {{User:ClueBot III/ArchiveNow}} won't help, because ClueBot III will only archive a section if it is happy with the whole page. --Redrose64 🌹 (talk) 08:36, 29 September 2026 (UTC)

Codex found a few issues with backticks, I think the most likely being:

• “Alternatives to bot requests”: eg. ```|url-status=usurped`` has mismatched backticks.

Dw31415 (talk) 11:43, 29 September 2026 (UTC)

If that’s a real issue but doesn’t fix the archiving, let me know here and I’ll run mwparserfromhell on the page. Dw31415 (talk) 11:55, 29 September 2026 (UTC)

That text is in Wikipedia:Bot requests/Header, which has this:

'''Alternatives to bot requests:'''
* [[Wikipedia:AutoWikiBrowser/Tasks]], for simple tasks that involve a handful of articles and/or only needs to be done once (e.g. adding a category to a few articles).
* [[Wikipedia:Link rot/URL change requests]], for tasks involving changing or updating URLs to prevent [[link rot]] (specialized bots deal with this).
* [[Wikipedia:Link rot/Usurpations]], for reporting a domain be usurped eg. {{para|url-status|usurped}}

No backticks involved. --Redrose64 🌹 (talk) 12:16, 29 September 2026 (UTC)

Stupid bot. (It was guessing from the rendered page). As penance for the slop comment, I ran mwparserfromhell. It found all 25 sections so that a clue that it's not an open format tag. Dw31415 (talk) 12:39, 29 September 2026 (UTC)

Digging in a bit after checking out ClueBot III's code, I don't see any problems with the parsing of the page itself. I do note, though, that Special:Diff/1367872579 reset the timer for several old sections by changing whitespace in them (ClueBot III looks for "section is unchanged since X time ago" rather than looking at signature timestamps). Anomie⚔ 12:29, 29 September 2026 (UTC)

Also, I note that the "archivenow" configuration is case-sensitive, so it won't recognize {{Done}} (only {{done}}). OTOH, it should recognize the {{User:ClueBot III/ArchiveNow}} just added, and the {{BOTREQ|done}}. Anomie⚔ 12:35, 29 September 2026 (UTC)

I see 5 topics archived 20 minutes ago. Did you add ArchiveNow? I don’t see that in the page history. Dw31415 (talk) 19:45, 29 September 2026 (UTC)

@Dw31415: They were added by Zackmann08 (talk · contribs) in these four edits. --Redrose64 🌹 (talk) 20:41, 29 September 2026 (UTC)

Thanks. I didn’t go back far enough. Dw31415 (talk) 22:06, 29 September 2026 (UTC)

Thanks all! Sorry been offline all day... Looks like it is working again. Zackmann (^{Talk to me}/_{What I been doing}) 23:04, 29 September 2026 (UTC)

I suspect it was working before, but nothing was ready to archive due to edits like Special:Diff/1367069933 and Special:Diff/1367872579 "resetting the timer" by editing old sections. Anomie⚔ 00:37, 30 September 2026 (UTC)

Weirdness. Zackmann (^{Talk to me}/_{What I been doing}) 00:58, 30 September 2026 (UTC)

That's a dumb change. I'm sure from a page-parsing standpoint it's easier to process, but it should go off timestamps not "last edited by" since a spelling (or heaven forbid whitespace) correction shouldn't reset the counter. Primefac (talk) 14:49, 3 October 2026 (UTC)

It's one of the fundamental differences between ClueBot III (CB3) and lowercase sigmabot III (LS3). Both have their advantages, quirks and disadvantages; when choosing which bot to use for a given page, they need to be balanced one against the other. For instance, {{User:ClueBot III/ArchiveNow}} is an advantage for CB3, because LS3 has no equivalent. Going off the most recent timestamp can be seen as an advantage for LS3 because it's transparent. I have found in the past that getting Cobi to alter the way that CB3 operates is ... difficult. "It's designed that way" doesn't really explain why that's a good thing. --Redrose64 🌹 (talk) 18:00, 3 October 2026 (UTC)

Personally, the feature I like most about ClueBot is that it updates incoming links when it archives. As for timestamps versus last-changed, I can see advantages to either method. And personally, I find random cleanups to dormant discussions more annoying than useful even if they don't interfere with the archiving. Anomie⚔ 19:01, 3 October 2026 (UTC)

Oops, sorry about that. Didn't realise the automatic whitespace changes by Factotum would cause problems like this. — Qwerfjkltalk 08:11, 13 October 2026 (UTC)

Are there any WP:NOLLM policy against using code developed by LLM to make bots?

Basically the title. I tried searching the archives here and on similar pages for AI and LLM discussions but nothing seemed to jump out. What I mean is: not calling or invoking LLM with a program to decide on conent.

I mean: using LLM to create deterministic code that would be a bot to edit Wikipedia, but to develop it WITH LLM/AI tools? For instance, using Claude Code or Codex to generate something that would be Github accessible, and run on a system that I control to edit Wikipedia in some approved bot manner. But, all the "programming" of the bot code would be done by LLM/AI.

Is that any WP:NOLLM concern? Why is it or is it not different? — VPP (t/c) 00:08, 13 October 2026 (UTC)

One can test LLM-generated code in exactly the same ways one should test non-LLM generated code, and once one has verified that LLM-generated code functions as expected then it will consistently function that way every time. Programmers already expect to having to rigorously test their output and not trust superficially correct code, in a way that we absolutely do not for written text. Most of the issues that prompt NOLLM (hallucinations, text-source integrity, bias, weird writing style) do not apply in the same way to code. I can imagine a policy against LLM-generated code (though I'd oppose such a policy without evidence that we're seeing issues caused by this), but it would need to be considered separately since it's just a completely different beast with very different classes of potential issues.

More cynically, the people writing code with LLMs onwiki have, on average, vastly more clue than the people writing articles with it, and so are less likely to use it in stupid ways or release inadequately checked LLM output. If we had even a fraction of the volume of codeslop in bots as we do in articles we'd absolutely need some way to regulate it. Rusalkii (talk) 00:51, 13 October 2026 (UTC)

There's currently no rule about vibe-coded bots, and it would be difficult to enforce one since we don't require that bot code be open source, and when it is I don't think we often bother to actually review it. Instead we generally judge bots based on behavior during the trial and afterwards: if the bot is making too many errors, it'll not be approved, or if already approved it'll be unapproved and blocked if necessary. And for what it's worth, it's pretty likely that many of the non-AI-coded bots aren't written to any sort of professional standards either. Also for what it's worth, "professional standards" these days seem to be all over the place when it comes to AI-written code; it's not uncommon to see supposed professionals slopping AI slop all they can, and then bragging about how "productive" they're being by becoming "managers" of a bunch of AI agents that test and review each others' code, while the people-managers cheer them on as they hope to be able to replace the human managers-of-teams-of-AI-agents with another layer of AI. Anomie⚔ 02:36, 13 October 2026 (UTC)

You asked why the difference. As already mentioned, the trial run process helps reduce errors. As an additional reason we don’t allow LLM generated text in articles is the licensing is disputed. That’s not an issue for bot source code because we don’t require it’s published under any particular license. Dw31415 (talk) 02:55, 13 October 2026 (UTC)

Toolforge and Cloud VPS down

See . All bots running on Toolforge are down. See also WP:VPT#Preparing for a short-notice security update to our services. Tenshi! (Talk page) 23:53, 20 October 2026 (UTC)