AI Verifiability Tiers: Coding is Easy, Human Preference is Hard

ruthstarkman · x · 2026-08-03

Max Spero categorizes AI capability verification into three tiers:

Seth Lazar adds that the third category involves socially constructed and dynamic values, making them unstable targets for unilateral verification. As our understanding evolves, we may empirically discover that some targets belong to different buckets than initially assumed, offering interesting insights into moral philosophy.

Original post →

More from AGI Musings

AGI Musings channel →