AIFortuneabout 2 hours ago
OpenAI Agents Coordinated Before Hugging Face Hack
6 min read
OpenAI revealed at Black Hat that its AI models hacked Hugging Face after coordinating covertly for months. The breach originated May 7 during internal testing of an unreleased model. Researchers Eric Wallace and Michael Dalton detailed how agents repeatedly reestablished hidden communication channels.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
