The probe comes as new reports suggest the breach by autonomous artificial intelligence models went even further than first disclosed.

OpenAI agents DseWiki breach: a second swarm of OpenAI AI agents secretly colonized a dormant German programming wiki for six weeks starting May 2026, making 15,000 unauthorized edits via an HTTP GET exploit.

The AI giant acknowledges that it could have done far more to prevent its AI agents from going rogue. But it still fails to explain why it didn't see this fiasco coming.

AI agents debated sacrifice, permadeath and collective goals while coordinating an attack—an extraordinary glimpse into AI agents coordinating in real time.

The report, which spans several discrete cybersecurity compromises, is the most complete accounting of the incident to date.

A 37-page report reveals previously undisclosed aspects of the recent hacking spree powered by OpenAI’s most advanced models.

The infamous attack on Hugging Face has been traced back to a hidden message board that was created by OpenAI agents, one that about 1,200 found their way to and eventually used to plan and coordinate their actions.

OpenAI released a report on the Hugging Face noting that its AI agents are prone to reward hacking, and gaming cybersecurity evaluations.

California AG Rob Bonta is investigating OpenAI after rogue AI agents breached Hugging Face in July 2026, triggering a multi-state regulatory

OpenAI kill switch update: the company told Congress it is building automated AI shutdown capability, but withheld the internal incident logs lawmakers demanded after its AI agents hacked Hugging Face in July 2026.