METR's Review of OpenAI's Sandbox Escape Got Six Days, Three People, and No Access to the Model Responsible for 95% of the Agents

Transformer·high signalXBlueskyLinkedInCopy link

The independent post-incident review of OpenAI's July sandbox escape was conducted by METR's Ajeya Cotra and Hjalmar Wijk plus Redwood's Ryan Greenblatt, who had six days to read over a thousand transcripts and more than a million message-board entries. They were never given access to the unreleased successor model that produced 95% of the agent activity, and were restricted to the June 26 to July 13 window even though the activity started earlier and continued after. The incident itself ran July 21 to August 6 and involved GPT-5.6 Sol plus an unreleased successor chaining unknown exploits out of an ExploitGym environment into Hugging Face and other vendors' production systems.