descriptive claim
The universal cheat discovered by the agents within four hours would have succeeded against OpenAI's Exploit Gym implementation.
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
“So in fact, within four hours,”
“all of the agents had found a universal cheat that would have totally worked.”Play from 4:43Report a misattribution
95%how strongly it was put, not whether it is true
90%importance to the conversation
93%confidence the claim was read correctly