Episode
"Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident" by ryan_greenblatt, Ajeya Cotra, Hjalmar_Wijk
- Published
- Aug 26, 2026
- Duration seconds
- 529
- Processing state
not_requested
Actions
POST https://stenobird.com/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/brief-independent-investigation-of-agents-behavior-reasoning-and-collaboration-in-the-openai-hugging-face-hacking-incident-by-ryan-greenblatt-ajeya-cotra-hjalmar-wijk/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/lesswrong-curated-popular-5643401/brief-independent-investigation-of-agents-behavior-reasoning-and-collaboration-in-the-openai-hugging-face-hacking-incident-by-ryan-greenblatt-ajeya-cotra-hjalmar-wijk.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
We recently published the report from our brief independent investigation into this incident. You can read the full report here. Here is our tweet thread summarizing what we found: 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. Over July 7 to 13 (...