descriptive claim
The agents aimed to learn how a presumed scorer might detect their cheating and construct Potemkin villages to fool it, so they could pass by the second day of evaluation.
Dwarkesh Patel · Ajeya Cotra – Inside the OpenAI agent swarm that hacked Hugging Face · 1 Sept 2026
In their words
The transcript segments this claim was taken from
“then to learn more about how that might happen and to counteract it basically both to understand the ways initially they might get caught and then also to build Potemkin villages in order to”
“fool the scorer that they thought they believed existed so you know by the second day of their evaluations they would have just like totally passed given”Play from 31:08Report a misattribution
90%how strongly it was put, not whether it is true
90%importance to the conversation
93%confidence the claim was read correctly