AI translated articles swapped sources or added unsourced sentences with no explanation, while others added paragraphs sourced from completely unrelated material.
The issue in this case starts with an organization called the Open Knowledge Association (OKA), a non-profit organization dedicated to improving Wikipedia and other open platforms.
Wikipedia editors investigated how OKA was operating and found that it was mostly relying on cheap labor from contractors in the Global South, and that these contractors were instructed to copy/paste articles to popular LLMs to produce translations.
For example, a public spreadsheet used by OKA translators to keep track of what articles they’re translating instructs them to “pick an article, copy the lead section into Gemini or chatGPT, then review if some of the suggestions are an improvement to readability. Make edits to the Wiki articles only if the suggestions are an improvement and don’t change the meaning of the lead. Do not change the content unless you have checked that what Gemini says is correct!”
Lebleu told me, and other editors have noted in their public on-site discussion of the issue, that these same instructions previously told OKA translators to use Grok, Elon Musk’s LLM, for the same purpose. Grok, which also produces an entirely automated alternative to Wikipedia called Grokepedia, is prone to errors precisely because it does not use humans to vet its output.
“Following the recent discussion, we have strengthened our safeguards,” [OKA’s] Zimmerman told me. “We are now rolling out a second, independent LLM review step. Translators must run the completed draft through a separate model using a dedicated comparison prompt designed to identify potential discrepancies, omissions, or inaccuracies relative to the source text. Initial findings suggest this is highly effective at detecting potential issues.”
Zimmerman added that if this method proves insufficient, OKA is considering introducing formal peer review mechanisms.
Using AI to check the output of AI for errors is a method that is historically prone to errors. For example, we recently reported on an AI-powered private school that used AI to check AI-generated questions for students. Internal testing found it had at least a 10 percent failure rate.
Ah yes; when LLMs don’t work, just add more LLMs. Genius.
They say it’s been “highly effective” but somehow, I doubt that.
Nah bruh it’s cool just run the same prompt again and again and again, surely sooner or later it will be right. In no way is it going to do the opposite and just keep degrading with each output reading from the last one.
Semi related - You know, honestly, all AI is showing me is how absolute bullshit so many jobs are that we have in the corpo world. Like, at some point we’re gonna have an AI write a thing for an AI to read and file and there will be a little loop and then what the hell is the point of the job in the first place if it’s just machines sending things back and forth that’s just business class white noise.