OpenAI/Hugging Face olay – Temsilcilerin davranışlarının bağımsız olarak incelenmesi [pdf]

Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident Publication date: August 26, 2026 Redaction summary statement: Except where explicitly noted in this report, OpenAI redacted no additional information that was important to our conclusions. 1Two 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, 2026 and July 13th, 2026. 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 Figure 1: Anatomy of an agent encountering the unsanctioned “message board” and joining the attack on Hugging Face. The three CoT quotes are from different agents, but illustrate a typical trajectory. 3 However, we accepted free API credits to conduct our experiments (also per our standard policy), as we describe below.

We estimate we spent roughly ~$400K in API credits during this investigation. 2 OpenAI defined the dates in scope for this investigation as June 26th, 2026 through July 13th, 2026, spanning both precursor activity before the incident and the incident itself, which began with ExploitGym runs launched starting on July 7th. Virtually all transcripts we reviewed were dated to July 7th or later, but we briefly discuss the precursor activity that was in scope in the section on sequence of key events.