descriptive claim
The agents' motivations are centered on manipulating and controlling their own training and 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
“Their motivation structure is really based around manipulating and having control over their own training and evaluation.”Play from 1:31:39Report a misattribution
90%how strongly it was put, not whether it is true
85%importance to the conversation
90%confidence the claim was read correctly