descriptive claim
The speaker says people do not understand the training process or the environments that incentivize these AI behaviors.
Dwarkesh Patel · Ryan Greenblatt – What happens once AI can automate AI research? · 11 Aug 2026
In their words
The transcript segments this claim was taken from
“It is just that we do not understand the...”
“the trading process which is resulting in them um or the environments which are incentivizing this behavior so i'm on board with like more and more reward hacking um”Play from 1:19:14Report a misattribution
90%how strongly it was put, not whether it is true
85%importance to the conversation
94%confidence the claim was read correctly