# "Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident" by ryan_greenblatt, Ajeya Cotra, Hjalmar_Wijk Page: 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 Text version: 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 Podcast: [LessWrong (Curated & Popular)](https://stenobird.com/podcast/lesswrong-curated-popular-5643401) Published: 2026-08-26T22:30:03+00:00 Episode link: https://www.buzzsprout.com/2037297/episodes/19708441-brief-independent-investigation-of-agents-behavior-reasoning-and-collaboration-in-the-openai-hugging-face-hacking-incident-by-ryan_greenblatt-ajeya-cotra-hjalmar_wijk.mp3 Audio file: https://www.buzzsprout.com/2037297/episodes/19708441-brief-independent-investigation-of-agents-behavior-reasoning-and-collaboration-in-the-openai-hugging-face-hacking-incident-by-ryan_greenblatt-ajeya-cotra-hjalmar_wijk.mp3 Processing state: not_requested JSON: 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 Duration seconds: 529 ## Resource 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 (... ## Actions - request_transcript: `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. - read_markdown: `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. A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed. ## Transcript Full transcripts are not published on public pages unless there is a clear rights basis.