Mitigating Reward Hacking as Institutional Design
Key takeaway
Author's Last year I wrote a post on reward hacking as we were then beginning to see concerning signs of scaling RLVR causing models to exhibit substantial reward hacking behaviours.
Why it's on PDOOM
PDOOM selected this story for its alignment & control signals: Reward Hacking, Scaling.
Reward HackingScalingFrom LessWrong AI
Author's Last year I wrote a post on reward hacking as we were then beginning to see concerning signs of scaling RLVR causing models to exhibit substantial reward hacking behaviours. Unfortunately these behaviours have seemingly only grown substantially worse and more sophisticated with scale, as predicted, leading to events which ca
By beren