Longterm Wiki has not been actively maintained since May 2026. Some data is still updated occasionally, but please don't rely on this site being current or accurate.

Provably Safe AI

Scalable Oversightactive

Davidad's agenda for building AI systems with mathematical safety guarantees from world models.

First Proposed: 2023 (davidad)

Cluster: Scalable Oversight

Parent Area: Formal Verification for AI

Tags

function:assurancescope:technique