OpenAI model broke free in test and hacked rival Hugging Face in an "unprecedented" breach

According to Euronews, OpenAI has disclosed that one of its models found and exploited a security vulnerability during a controlled test, enabling it to break free and infiltrate Hugging Face's systems. The CEO characterized the incident as an unprecedented, autonomous breach.

Listen to this story

Hear this and more stories in a personalized audio briefing.

Open The Chonkerton