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.
More from AGI Musings
- First human genome cost $3B and 13 years; now it's a few hundred dollars — PeterDiamandis · 2026-09-04
- theo: GPT-6 Astra is a generational leap beyond coding — computer use, 3D, swarms and more — gabrielchua · 2026-09-04
- Chollet: Astra Saturated ARC-AGI-3 Twice as Fast as I Predicted — fchollet · 2026-09-04
- Two Years On: Six Guidelines for Making Research Impact via Open-Source in AI — lateinteraction · 2026-09-04
- Ron Bodkin: Anyone Saying AGI Has Arrived Lacks Understanding — ronbodkin · 2026-09-04
- Chollet: ARC-AGI-4 lands Q1 2027, and solving ARC-3 is not AGI — fchollet · 2026-09-04