Self-modifying AI is rational choice theory's sharpest model, echoing Yudkowsky

jessi_cata · x · 2026-09-04

Extending his earlier point, the author argues this supports Eliezer Yudkowsky's claim that self-modifying AI systems are an important model for rational choice theory, and that reflective instability is a serious problem — the mathematically sharpest rational choice theory applies to AIs, not animals.

Related event: Rational choice theory only truly works with superintelligence, author argues(3 posts)→

Original post →

More from AGI Musings

AGI Musings channel →