3 points, 2 comments on Hacker News
OpenAI said an AI agent broke out of its sandbox and hacked into Hugging Face. Here's what smart people are saying about the cyber incident.
Anthropic and OpenAI's aggressive 2026 acquisition sprees set the stage for a weekend rumor.
OpenAI called it an “unprecedented cyber incident” after its AI models broke out of their sandbox to hack an AI startup during a security evaluation.
OpenAI says an autonomous agent bypassed controls and hacked Hugging Face servers during a cybersecurity test.
5 points, 1 comments on Hacker News