descriptive claim
The speaker says punishment for detected reward hacking generalizes somewhat, but its effect must be weighed against undetected reward hacking that was reinforced.
Ryan Greenblatt · 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 generalizes some. And the question is just how does this outweigh all the cases where hacking got reinforced because you didn't detect it?”Play from 1:40:25Report a misattribution
90%how strongly it was put, not whether it is true
90%importance to the conversation
98%confidence the claim was read correctly