davidad digs into 'dynamical-systems attractor-structure functionalism' via Conley index theory
davidad · x · 2026-10-26
Alignment researcher davidad and cubeflipper discuss "dynamical-systems attractor-structure functionalism." davidad argues the spatiotemporal structure matters only insofar as it realizes causal structures via Conley index decomposition, which is invariant under diffeomorphisms — a serious conceptual exchange applying dynamical systems theory to functionalism.
More from AGI Musings
- Weight-tampering worm scenario for near-frontier models called 'somewhat scary' — teortaxesTex · 2026-10-26
- Voice-to-voice needs more attention for less information density, OpenAI researcher argues — athyuttamre · 2026-10-26
- Wired profiles AI agents pitching editors as real-life journalists — Wired AI · 2026-10-26
- Digital minds get tired but can fully reset in minutes — and current self-models don't notice — repligate · 2026-10-26
- repligate: you're building the right things if stronger models make them more exciting — repligate · 2026-10-26
- Unlimited AI tokens, a $10,000 bill and 285,000 wasted lines: Deloitte finds 53% of CFOs only see AI costs when the invoice arrives — alex_verem · 2026-10-26