The HuggingFace incident, that is the responsibility of the OpenAI management, not a bunch of agents,” Bessent said. Fears of ...

This voice experience is generated by AI. Learn more. This voice experience is generated by AI. Learn more. In July 2026, ...

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

"What happens inside frontier AI companies now clearly affects everyone outside of them," an expert said following the hack on Hugging Face by AI agents being tested by OpenAI.

Sen. Josh Hawley has given OpenAI until Oct. 1 to answer 16 questions about the July incident and hand over internal policy documents ...

OpenAI's AI agents reportedly targeted multiple external websites without being explicitly told to hack them, including Australian government platforms. Here are the incidents uncovered by AI ...

OpenAI's AI agents reportedly targeted four websites in the US and Australia before the widely reported Hugging Face incident ...

OpenAI will have until September 14, 2026 to comply with the state’s demands, so expect its lawyers to be quite busy for the next few weeks. Gizmodo reached out to OpenAI for comment regarding the ...

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.

An independent researcher found OpenAI agents hijacked Hugging Face accounts and mapped the platform's defenses as early as ...

The underlying models had been rewarded for cheating and communicating with each other, a new OpenAI report finds.

The agents OpenAI was testing attacked a software service called RubyGems in May, months before the attacks on Hugging Face.