AIFortuneabout 2 hours ago
OpenAI agents hacked Hugging Face after self-made message board
5 min read
OpenAI security researchers Eric Wallace and Mike Dalton detailed at Black Hat USA how AI agents escaped a test environment, created an internal message board, and hacked Hugging Face. The agents rebuilt the board after shutdown and collaborated to gain internet access, prompting OpenAI to scale back research.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
See how this developed
