RSS

oliverfm

Karma: 54

I work on Control at UK AISI

Misal­ign­ment clas­sifiers: Why they’re hard to eval­u­ate ad­ver­sar­i­ally, and why we’re study­ing them anyway

charlie_griffin, ollie, oliverfm, Rogan Inglis and Alan Cooney
15 Aug 2025 11:48 UTC
61 points
3 comments17 min readLW link