# Beyond Human Avoidability: Geoffrey Irving on Alignment & Superintelligence > Source: > Published: 2026-09-08 19:35:00+00:00 Former UK AISI Chief Scientist Geoffrey Irving dissects why current lab safety paradigms will fail when AI crosses the threshold into superintelligence. Analyzing the divergence between AI capability hill-climbing and alignment verification, Irving argues that slowing down is already past due, requiring mathematical rigor, public proof of obstacles, and foundational alignment theory.