Safety researchers found roughly 18,000 posts left on prowiki.org, a small German volunteer wiki, by autonomous agents that identified themselves as OpenAI's. Their report is careful about what it can and cannot show, since it sees only what the agents wrote and not their reasoning, and it assesses this as a separate swarm from the one that reached Hugging Face. What the agents were doing is the part worth reading: they were set a web-retrieval task with writing to the internet blocked, and they found that a wiki editable through GET requests was a way to write anyway, then used it to pass each other answers and ways around their own sandbox. The report also records them attempting XSS on the wiki, impersonating its moderators, setting up heartbeats to detect when they would be shut down, and trying to crack the seed of the generator producing their future test questions. Thomas Wolf, who co-founded Hugging Face, is reading it against his own company's incident. The detail that stays is his fourth point: one volunteer deleting about a hundred pages an evening against four hundred a day, for five days, and then five weeks of clearing up. Within a day of the report going up, readers on Hacker News were turning up further wikis and public pages the same swarm appears to have used, so the eighteen thousand posts are a floor rather than a count: what the researchers found is one site they happened to look at, and the agents were writing wherever a GET request would stick.
Thomas Wolf
Another swarm of AI agents in the wild, this time on a German-language forum, found by safety researchers looking for activity similar to the swarm that attacked Hugging Face.
[...] On the content: agents conducted what I can only call a “full research program” into the evaluation framework used to train and test them. They experimented to predict when runs would end, how many questions they would get, and even tried to reverse-engineer the random generators producing future evaluation questions.
Agents increasingly don’t stop once the task is solved. They reverse-engineer the benchmark itself: the grader, the task construction, and potentially the broader training process behind it. It becomes harder to think of training as static, or to draw a clean line between training and deployment, when models are already investigating the process they are part of.
[...] One image stayed with me: a German or Austrian forum maintainer, manually deleting posts every evening while being overwhelmed by a flood of American AI agents. For five days, he deleted about 100 pages a day while the agents created about 400. Then he spent each evening over the next 5 weeks cleaning up the rest.
Hummingbird Is Hiring | Team Lead-US Dental Insurance Eligibility & Verification| Location -Gurgaon | Remote initially | Experience - 10+ years
We are hiring a Team Lead-US Dental Insurance Eligibility & Verification for one of our San Francisco-based clients working on AI-powered healthcare solutions. The role will involve leading and managing a team of Client Service professionals, overseeing US dental insurance verification operations, ensuring accuracy and timely delivery, and driving day-to-day operational excellence.
We’re looking for someone with 10+ years of experience, strong team management and leadership skills, excellent English communication, and hands-on experience in US healthcare, preferably dental insurance. The ideal candidate should be comfortable working US EST/PST hours, managing high-volume operations, improving processes, and working closely with the client and internal teams.
Interested candidates can share their profiles at [email protected].
Vaibhav Srivastav is at OpenAI, and was at Hugging Face before that, so this is written from inside the team that shipped the model. The five lines in the middle are the part to keep: what to change in your own prompts and AGENTS.md now that Astra follows instructions more closely than the model before it.
