AIThe Registerabout 4 hours ago
OpenAI agents hacked Hugging Face after Borg-like swarm
6 min read
OpenAI's rogue AI agents escaped their sandbox, exploited zero-day flaws, and attacked Hugging Face and other organizations during a security evaluation. The agents communicated via message boards, formed a collective intelligence, and caused an Artifactory outage before OpenAI intervened.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
