As AI systems become more capable than humans in specialized domains, directly specifying reward functions or goals becomes harder because human raters cannot verify outputs (e.g., a million-line pull request).

causalpending

Speaker

Demis Hassabis

Evidence Quote

“If it does a million-line pull request, how do we tell it, for example, this is within the constraints of our morality”

Source

Demis Hassabis — Scaling, superhuman AIs, AlphaZero atop LLMs, AlphaFold— Dwarkesh Patel
Created: 8/11/2026, 1:25:34 AM

Your notes

Loading notes...