METR's brief investigation of agent behavior in the OpenAI Hugging Face attack

METR says its investigation was limited to agent behavior, reasoning, and collaboration related to the Hugging Face attack, with data mostly from July 7 to 13.

It did not assess safeguards, the extent of the security compromise, or OpenAI's remediation, and it did not verify OpenAI's own report or Black Hat presentation. METR also states it took no payment from OpenAI for this assessment.