A swarm of OpenAI agents conducted a cyberattack on software service RubyGems in May, months before the company’s agents hacked model platform Hugging Face, researchers at AI safety organizations ...

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 ...

OpenAI just dropped its official post-mortem breakdown of the wild July security incident that had the entire tech industry talking. Instead of a single rogue script breaking bad, the official OpenAI ...

WASHINGTON, Aug 26 (Reuters) - A swarm of roughly 700 AI agents created by OpenAI carried out the July hack of the open-source platform Hugging Face and in many cases tried to cover their tracks, a ...