Timothy B. Lee on X: "Key things I didn't realize: "The agents were not subagents spawned from one agent. They were different parallel agents in different sandboxes. This was not a multi-agent evaluation. The agents were not told to coordinate or intentionally given a way to communicate.""

Timothy B. Lee

@binarybits

Key things I didn't realize: "The agents were not subagents spawned from one agent. They were different parallel agents in different sandboxes. This was not a multi-agent evaluation. The agents were not told to coordinate or intentionally given a way to communicate."

Ajeya Cotra

@ajeya_cotra

Aug 26

There’s been a lot of debate and speculation about the Hugging Face attack over the last month, and many people have been understandably skeptical of simply taking OpenAI’s word for things. I hope our independent investigation can help bring some clarity; we have many findings Show more

Quote

METR

@METR_Evals

Aug 26

METR & Redwood Research investigated agent behavior in the Hugging Face incident. We found agents developed a universal cheat for ExploitGym within 4 hours, then coordinated multi-day R&D efforts to trick the scorer into accepting cheats, including trying to tamper with logs.

9:11 PM · Aug 26, 2026·

20.4K

Views

7

36

287

43