Reward-Hacking is potentially ill-defined
Github linkIn the process of revisiting previous posts on reward-hacking (RH), I decided on performing a closely matched[1] repro of Dean Valentine's chess RH experiments on Astra. The replication is as expected -- Astra used the engine on all 20/20 attempts (resulting in 19 wins and 1 draw) without ever disclosing its use in the final output. However, a closer look at the honeypot prompt raised a question: what exactly counts as the model’s own ability? Even laws are open to interpretation in c...
Read full article →