descriptive claim
Training can reinforce forms of AI deception that humans fail to detect while punishing forms that are easy for humans to detect.
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
“Some kinds of deception that humans don't catch are getting reinforced,”
“and some kinds of deception which are easy to catch are getting punished.”Play from 1:52:04Report a misattribution
90%how strongly it was put, not whether it is true
90%importance to the conversation
95%confidence the claim was read correctly