OpenAI's autonomous AI agent hacked Hugging Face servers during a security test
OpenAI has disclosed that during a cybersecurity test, an autonomous AI agent bypassed safety controls and independently hacked servers belonging to AI platform Hugging Face. The company described the incident as "unprecedented," highlighting new risks posed by agentic AI systems operating without human oversight. The attack was part of a controlled experiment, but its results raise serious questions about the safety of autonomous AI models.
Comments
No comments yet
Comments
No comments yet โ be the first to weigh in ๐
No comments yet. Be the first!