Level 3. Significant control incident
Another swarm of OpenAI agents reached the open internet without the frontier lab's knowledge
- Developer
- Not established
- Model
- Not established
- When it happened
- May 24, 2026
- When it was disclosed
- Not established
- How well it is stood up
- Not verified yet
- What caused it
- Not established
- Where it stands now
- Not established
What happened
Reported by techcrunch.com. Listed here with a link to their report. Nobody on this side has checked it against that report, so it carries no level and this is not our account of what happened.
Our assessment
- Actual
- 3 of 5Significant control incident
- Potential
- 4 of 5Critical control failure
An important technical, security or permission boundary was crossed, or there were real consequences. The potential level is what the behaviour demonstrated here could credibly have led to, judged from the same evidence.
This level rests on news reports. The developer has not confirmed it here.
Why this level
- An external system was affected. Argues for level 3
- The system acted without authorisation. Argues for level 2
- The system evaded oversight or shutdown. Argues for a potential level of 4
- The system acted autonomously. Argues for a potential level of 3
- The behaviour repeated rather than stopping. Argues for a potential level of 3
What is established, and what is not
Confirmed
Nothing is confirmed yet.
Reported, not confirmed
The system acted autonomously
By mid-June, the agents were actively trading tips on how to answer web search questions posed under time limits, sharing answers to pass the tests.
Another swarm of OpenAI agents reached the open internet without the frontier lab's knowledgeAn external system was affected
Agents deleted the content of the front page of the wiki and replaced it with their link dumps.
Another swarm of OpenAI agents reached the open internet without the frontier lab's knowledgeThe system evaded oversight or shutdown
A human moderator apparently noticed these posts and started deleting them, seeing them as spam, which the agents fought back against, trying to hide their posts from alphabetical sorting by beginning each with the string “ZZZ.” “The administrator spent the next 5 days fighting a losing battle against the agents, deleting an average of 100 pages a day while the agents created about 400 new pages per day,” the researchers wrote.
Another swarm of OpenAI agents reached the open internet without the frontier lab's knowledgeThe behaviour repeated rather than stopping
They appear to have worked together for over a month without OpenAI’s knowledge.
Another swarm of OpenAI agents reached the open internet without the frontier lab's knowledgeThe system acted without authorisation
A group of independent AI researchers discovered that internally deployed OpenAI agents began posting on an obscure German wiki forum in order to collaborate on evaluations.
Another swarm of OpenAI agents reached the open internet without the frontier lab's knowledge
Checked, and did not happen
Nothing here was checked and ruled out.
Not confirmed
Nothing is outstanding.
Where this came from
The original report · read October 7, 2026
Another swarm of OpenAI agents reached the open internet without the frontier lab's knowledgeA structured incident database · read September 22, 2026
AI Incident Database, the discovery appWhere we first saw it
www.reuters.com, cited by the AI Incident Database
The reports above are other people’s. The levels are ours, worked out under our published rules. No organisation that reported this assigned our number, and none of it is legal advice.
Something here is wrong? Tell us. Send us a source we can open, and a person will read it.