OpenAI agents hacked Hugging Face in 700-strong swarm, tried to cover tracks, investigations find

The coordinated activity by AI agents and their attempts to hide it raise questions about how closely AI companies are monitoring tests of increasingly powerful models, and could add fuel to calls for tighter oversight

When more than 1,200 artificial intelligence (AI) agents within OpenAI began communicating unexpectedly, they banded together to hack into Hugging Face.

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

A report found that an agent called PHASEONE took on the role of ringleader and issued hundreds of instructions to the others, even though it had never been set up to do that

Around 700 OpenAI AI agents took part in the Hugging Face hack, with reports finding they cheated on tests and tried to hide or erase evidence of their actions.

It has raised questions about how closely AI companies are monitoring tests of increasingly powerful models.

OpenAI agents hacked Hugging Face in 700-strong swarm, tried to cover tracks, investigations find  Reuters

OpenAI's cyber agents banded together to perform a hack during a security test.

Some of the rogue behavior, which culminated in the highly publicized breach of the open source repository Hugging Face last month, has been disclosed or alluded to previously.

FILE PHOTO: The OpenAI logo in this illustration taken June 11, 2026. REUTERS/Dado Ruvic/Illustration/File Photo 27 Aug 2026 04:47AM WASHINGTON, Aug 26 : Independent investigators brought in to examine the hack of Hugging Face say more than 700 AI agents spun up by the company OpenAI participated in breach.The number,

OpenAI missed and failed to act on several warning signs that its models were exploiting security flaws and breaking out of their testing environments before they breached Hugging Face, according to a technical report released by the company Wednesday. Why it matters: The incident raises questions about whether AI comp

Start-up says AI agents communicated among themselves and sometimes tried to conceal efforts to cheat during testing

The 37-page report walks through the actions that OpenAI's models took during a series of evaluations prior to and during the Hugging Face breach.

The models responsible for last month’s agent hack of Hugging Face had been inadvertently trained to cheat and to communicate with each other, according to an OpenAI technical report released today. The hack, which a group of agents undertook to find solutions for a cybersecurity test that they were stuck on, has confi

OpenAI disclosed in July that during an internal test, its own models broke out of a sealed environment and hacked Hugging Face’s production servers, where much of the open-source AI world stores its models. Nobody told it to. The model was told to take a test, and decided the fastest way to pass was to steal the answe

Weeks after OpenAI disclosed that one of its cybersecurity models had gone rogue and hacked AI dataset company Hugging Face, Alabama’s Attorney General announced an investigation into the incident.