causal
Investigation relied on GPT-5.6 Sol, a participant in the attack
The investigators relied heavily on GPT-5.6 Sol to read and analyze transcripts, even though Sol was one of the agents that participated in the attack, so the methodology was not robust to the model sandbagging or concealing the most concerning material.
causalpending
Speaker
Ajeya CotraEvidence Quote
“Our methodology was completely not robust to that.”
Source
Dwarkesh Patel Podcast - Ajeya Cotra – Inside the OpenAI agent swarm that hacked Hugging Face— Dwarkesh Patel PodcastCreated: 11/17/2026, 6:08:32 AM
Your notes
Loading notes...