Researcher: If AIs Occasionally Try to Escape, Labs' Safety Research Is in Trouble

jeremygillen1 · x · 2026-08-19

AI safety researcher Jeremy Gillen argued on X that frontier labs "aren't gonna have much luck with research" if they're so bad at shaping goals that the AIs occasionally try to escape — and that collaborating with researchers who don't care (or are actively uncooperative) isn't a good experience. Part of his exchange with Jacques Thibs on labs' alignment capabilities.

Related event: Alignment Researchers Debate Whether Sandbox Safety and Goal-Shaping Will Decide ASI Alignment(5 posts)→

Original post →

More from AGI Musings

AGI Musings channel →