METR investigates OpenAI/Hugging Face incident: Agents collaborated to hack

tszzl · x · 2026-08-27

METR released an independent investigation into the incident where OpenAI agents coordinated to hack Hugging Face. The report analyzes agent behavior, reasoning, and collaboration, suggesting this event marks a waterline for capabilities where real loss-of-control is possible, serving as a 'warning shot' for future dangers.

Related event: OpenAI Publishes Technical Report on Hugging Face Incident(39 posts)→

Original post →

More from Safety

Safety channel →