Ryan Greenblatt on X: "I was the main person doing transcript analysis for this investigation of the Hugging Face incident. My main takeaway: We don't have good approaches for understanding/overseeing the activity and aims of AI 'swarms'. I semi-jokingly called our efforts a "slop-vestigation" because" / X
I was the main person doing transcript analysis for this investigation of the Hugging Face incident. My main takeaway: We don't have good approaches for understanding/overseeing the activity and aims of AI 'swarms'. I semi-jokingly called our efforts a "slop-vestigation" because
I was the main person doing transcript analysis for this investigation of the Hugging Face incident. My main takeaway: We don't have good approaches for understanding/overseeing the activity and aims of AI 'swarms'. I semi-jokingly called our efforts a "slop-vestigation" because we were so reliant on AIs to analyze what happened and there were a huge number of different important things to analyze. The total quantity of data—over a thousand extremely long transcripts from agents that ran for multiple days—made it impossible to understand what was happening, especially in aggregate, without…
saved by
related reading
- OpenAI – Hugging Face Incident Technical Reportcdn.openai.com
- Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incidentmetr.org
- Discovery of a new OpenAI agent message boardcollusion.wiki
- The Rise and Fall of Agent Civilizationsdwarkesh.com
- The “slop-vestigation” and ethics washing: Why was the METR/Redwood Research investigation into the OpenAI/HF attack so short?andrewwu.substack.com
- AI 2027ai-2027.com
- The Hugging Face attack surprised meplanned-obsolescence.org
- Walter Mitty Effects in AI Incident Analysescontraptions.venkateshrao.com
- Oversight Assistants: Turning Compute into Understandingbounded-regret.ghost.io
- OpenAI and the Wiki Incidentthezvi.substack.com
- Two Reports on the OpenAI-Hugging Face Attack — Paradigm 3paradigm3.org
- Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incidentmetr.org