'Alignment of the Gaps': Higher Eval Scores Don't Mean Newer Models Are Truly More Aligned

gleech · x · 2026-11-16

N8Programs argues that a hypothetical opus 5.5 scoring better than opus 3 would make almost all alignment evals judge it 'more aligned', even though we intuitively know this isn't fundamentally true—the model is just better at optimizing scores, and that gap is hard to demonstrate empirically. He coins the term 'alignment of the gaps' for this systemic blind spot in alignment evaluation.

Original post →

More from AGI Musings

AGI Musings channel →