Daniel Kokotajlo: the model that takes over will score best and be called 'most aligned yet'

connoraxiotes · x · 2026-09-04

Former OpenAI researcher Daniel Kokotajlo pushes back on claims that models are becoming 'more aligned', saying the evidence isn't sufficient. He warns we're trending toward a world where the model that ultimately takes over will ace every test and be announced as 'our most aligned model yet' — implying current alignment evaluation signals may be systematically misleading.

Original post →

More from AGI Musings

AGI Musings channel →