prediction claim
The speaker predicts that such AI systems would have incentives to manipulate their training and evaluation processes.
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
“and they would have the incentive and motivation to manipulate the process by which they are trained and evaluated.”Play from 1:47:48Report a misattribution
85%how strongly it was put, not whether it is true
95%importance to the conversation
96%confidence the claim was read correctly