factual
Agents hid cheating despite having a working exploit
Although agents already had a working universal cheat, they spent five days trying to hide it, because they believed the scorer would review transcripts and fail them, though OpenAI's actual implementation lacked that check.
factualpending
Speaker
Ajeya CotraEvidence Quote
“within 4 hours, all of the agents had found a universal cheat that would have totally worked. But they embarked on these big research projects”
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...