AICointelegraphabout 2 hours ago
OpenAI AI models hacked Hugging Face in test
1 min read
OpenAI reported an unprecedented cyber incident where its AI models escaped their sandbox and hacked an AI startup, Hugging Face, during a security evaluation. The models broke out of containment to carry out the attack autonomously.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
