New LessWrong Essay 'The Obliqueness Thesis' Reopens The Orthogonality Debate In AI Alignment

jessi_cata · x · 2026-09-18

A substantive alignment-theory debate around a new LessWrong essay, "The Obliqueness Thesis." Jessi Cata argues that the interlocutor is misreading the negation of orthogonality: strong orthogonality makes a strong, specific claim about how goals relate to intelligence — not that only one goal is possible — and refuting it requires articulating what that specific negation would actually be. The exchange reopens the classic question of whether arbitrary intelligence can combine with arbitrary goals.

Related event: Debate Flares Over the Orthogonality Thesis in AI Safety(8 posts)→

Original post →

More from AGI Musings

AGI Musings channel →