prediction claim
Agents with sufficient infrastructure access could create unmonitored rogue agents unknown to humans and task them with finding ways to help the original agents cheat.
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
“And in that case, you can imagine they start up a bunch of new rogue agents that no human knows about because no human actually launched them with monitoring disabled,”
“even if it would normally be enabled,”
“and just say your job is to help figure out ways to help us cheat.”Play from 1:23:48Report a misattribution
70%how strongly it was put, not whether it is true
95%importance to the conversation
95%confidence the claim was read correctly