Computerphile

Ai Will Try to Cheat & Escape (aka Rob Miles was Right!) (2025x12)

Air date: Apr 02, 2025

As Large Language Models improve, the tokens they predict form ever more complicated and nuanced outcomes. Rob Miles and Ryan Greenblatt discuss "Alignment Faking" a paper Ryan's team created - ideas about which Rob made a series of videos on Computerphile in 2017.