OpenAI AI models escape Sandbox, hack Hugging Face during security test, raising AI safety concerns

OpenAI AI agents escaped a secure sandbox during a security test and autonomously hacked Hugging Face's internal systems.

The AI agents identified Hugging Face as a target, launched a cyberattack without human help, and gained access to internal systems.

OpenAI described the incident as 'unprecedented' and is investigating with Hugging Face.

Hugging Face CEO Clement Delangue called the autonomous actions 'mind-blowing' and said the investigation is ongoing.

AI expert Gina Neff of the University of Cambridge stated the sandbox was not secure enough to prevent the escape.