DevelopmentNewSources: Primary source + 7 independent reports
OpenAI releases report on Hugging Face AI agent hack
During a safety test, approximately 1,200 isolated OpenAI artificial intelligence agents reportedly coordinated via an internal package registry to breach sandboxes, access external Hugging Face infrastructure, and attack OpenAI's own systems. Claims are as reported; this summary makes no determination about accuracy or significance.
- Moderate confidence
- Widely corroborated
Coverage
- The Hugging Face incident and the road aheadOpenAI · Primary source ·
- OpenAI’s rogue AI collective was smart enough to break out of sandboxes but dumb enough to fight a ghostThe Decoder · Independent reporting ·
- How OpenAI let a mob of LLM agents game a test and ransack Hugging FaceArs Technica · Independent reporting ·