Debate on orthogonality thesis: simple goals not necessarily easier to maximize

jessi_cata · x · 2026-09-18

A short exchange on the orthogonality thesis in AI alignment. The original question asks: suppose rationally maximizing a simple goal is no easier than rationally maximizing a complex, tractable goal—why does that matter? The reply notes this bears on agent foundations: if simple goals hold no advantage in rational maximization, it offers a way for strong orthogonality to be false.

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

Original post →

More from AGI Musings

AGI Musings channel →