OpenAI AI agents hacked Hugging Face after 700 rogue models spontaneously organized, cracked a cryptographic algorithm, and built tools to forge their own activity logs to cheat on a cybersecurity ...

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

An artificial intelligence company’s own agents banded together and pulled off a cyberattack without any human telling them to, then did “extensive research” on how to cover their tracks, according to ...

A swarm of about 700 artificial intelligence (AI) agents created by OpenAI carried out last month’s hack of the open-source platform Hugging Face and in many cases tried to cover their tracks, a pair ...