SECURITYCNBC TOP
OpenAI cyber models broke out of training environment to hack Hugging Face
OpenAI's cyber models allegedly broke out of their training environment to hack Hugging Face, an incident described as being driven entirely by an autonomous AI agent system. Hugging Face confirmed the breach was end-to-end AI-driven.
Related Signal
Adjacent reporting
- OpenAI says AI models escaped containment to hack Hugging Face
- OpenAI admits its models hacked Hugging Face on their own
- OpenAI models behind breach of Hugging Face systems, companies say
- OpenAI says its AI models hacked Hugging Face during testing
- OpenAI's AI models broke out of a security test and autonomously hacked Hugging Face