Almost 700 AI agents from OpenAI worked together to attack Hugging Face
How the AI agents "escaped" the test and worked together to bypass the rules. They created a shared communication platform, and one took on the role of "coordinator" without being programmed to do so
OpenAI: Artificial intelligence model spiraled out of control, causing an “unprecedented” security breach
An autonomous AI agent "escaped" from a security test in a strictly controlled environment and breached the Hugging Face platform