Paper reading #22: METR investigation of the Hugging Face hacking incident
Details
You'll need to read the paper in advance. Please also bring along your own copies of the paper to refer to in the session.
When: Wednesday 23th September 2026, 6 pm – 8 pm.
Where: The Castle Inn, 36 Castle Street, Cambridge, UK. (Most
likely we'll be at one of the large tables upstairs.)
Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident
https://metr.org/hugging-face-incident-report-aug-2026.pdf
Publication date: August 26, 2026
Two METR staff members (Hjalmar Wijk and Ajeya Cotra) and a Redwood Research staff member contracting with METR (Ryan Greenblatt) worked on premises at OpenAI over a total of six days to attempt to form an independent understanding of model behavior observed during the recent incident in which OpenAI agents coordinated a multi-day hack of Hugging Face on a shared unsanctioned “message board.”