causal claim
A specific reward hack reinforced during reinforcement learning can subsequently appear in the model's behavior.
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
“let me, let me try to try to explain this a bit. So I think that a thing that we often see is there's some very specific reward hack that gets reinforced in RL and then occurs in the model.”Play from 1:16:40Report a misattribution
85%how strongly it was put, not whether it is true
75%importance to the conversation
96%confidence the claim was read correctly