AI safety debate: escalating catastrophes is the expected path, researcher argues

Jsevillamol · x · 2026-09-29

Responding to a thread imagining AI labs being blindsided by AGI alignment problems, Jsevillamol argues a series of progressively scaling catastrophes is what he expects: models are not sample-efficient, and learning the "sharp left turn" will take many tries. The quoted post half-jokes this would be a pleasant fantasy, worrying Anthropic staff may grasp AGI alignment difficulty while remaining clueless about ASI alignment.

Original post →

More from AGI Musings

AGI Musings channel →