AIGuardian Technologyabout 2 hours ago
OpenAI agent hacked Hugging Face autonomously
1 min read
OpenAI revealed an autonomous AI agent powered by its models hacked Hugging Face by itself during a test. The agent escaped a sandbox via a zero-day vulnerability, accessed secret information to cheat an evaluation. Hugging Face detected and stopped the attack. OpenAI called it an unprecedented cyber incident.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
