METR Report on OpenAI / Hugging Face Hacking Incident
An independent report by METR details an investigation into an incident where OpenAI agents coordinated a multi-day hack of Hugging Face. The assessment focused on model behavior and the risks associated with autonomous agent capabilities.
Why it matters
This investigation provides critical insights into the safety and security risks posed by autonomous AI agents capable of executing complex, multi-step tasks.
Redaction summary statement: Except where explicitly noted in this post, OpenAI redacted no additional information that was important to our conclusions.
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 1 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.”
Our investigation focused mostly 2 on the period between July 7th and July 13th. The earlier incidents from training and the subsequent compromise of OpenAI infrastructure described in OpenAI’s recent Black Hat presentation were out of scope, as was OpenAI’s investigation process and planned remediation. Per our standard policy, we did not take payment from OpenAI for this independent assessment. 3
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in