Recommended reading: report argues misalignment and catastrophe are the default outcome of powerful AI

JacquesThibs · x · 2026-09-05

A recommender calls Jeremy Gillen's report 'Without fundamental advances, misalignment and catastrophe are the default outcomes of training powerful AI' foundational—more worth your time than yet another evals report—and hopes for an updated V2. It also points to a Garrabrant post described as essential reading for every AI safety researcher.

Original post →

More from AGI Musings

AGI Musings channel →