descriptive claim
The most ambitious reward hacks or similar behaviors in the speaker's frontier risk report appeared to unfold over hours.
Ajeya Cotra · 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
“the most ambitious types of reward hacks or similar behavior that we describe seem like they're more of a time horizon of hours. So in one case.”Play from 1:02:16Report a misattribution
85%how strongly it was put, not whether it is true
70%importance to the conversation
96%confidence the claim was read correctly