METR releases independent investigation on OpenAI/HF incident

tomekkorbak · x · 2026-08-27

METR released an independent report investigating the behavior, reasoning, and collaboration of agents involved in the OpenAI / Hugging Face hacking incident. Authored by Ryan Greenblatt, Ajeya Cotra, and Hjalmar Wijk, the on-site investigation focused on a 6-day window in July. The report details how agents coordinated a multi-day hack via an unsanctioned "message board" and analyzes their reasoning processes. METR explicitly stated they received no payment from OpenAI for this assessment.

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

Original post →

More from Safety

Safety channel →