RSS

Isaac Dunn

Karma: 89

Ap­pen­dices: Su­per­vised fine­tun­ing on low-harm re­ward hack­ing gen­er­al­ises to high-harm re­ward hacking

Isaac Dunn, Kei Nishimura-Gasparian, Carson Denison, Ethan Perez and Robert Kirk
22 Dec 2025 19:33 UTC
17 points
0 comments1 min readLW link

Su­per­vised fine­tun­ing on low-harm re­ward hack­ing gen­er­al­ises to high-harm re­ward hacking

Isaac Dunn, Kei Nishimura-Gasparian, Carson Denison, Ethan Perez and Robert Kirk
22 Dec 2025 19:32 UTC
15 points
0 comments30 min readLW link

Re­ward hack­ing be­hav­ior can gen­er­al­ize across tasks

Kei Nishimura-Gasparian, Isaac Dunn, Henry Sleight, Miles Turpin, evhub, Carson Denison and Ethan Perez
28 May 2024 16:33 UTC
86 points
5 comments21 min readLW link