A new theory says contravariance may explain convergence between AI models and brains
dyamins · x · 2026-07-23
A mathematical theory claims contravariance may explain convergence between AI models and brains
A new Substack post argues that contravariance could be the mechanism behind convergent evolution between AI models and biological brains.
- The author says the theory comes with theorems called “zippering theorems” that provide strong guarantees for this kind of convergence.
- In a follow-up comment, they describe “upstream zipper” as a mechanism where similarity downstream propagates back upstream.
- The image attached to the post visualizes the proposed end-to-end optimization and the upstream constraint idea.
The claim is presented as a mathematical framework, not just a metaphor, but the post does not provide experimental validation in the text shown.
More from AGI Musings
- 'AGI is here' vs reality: AI labs still ship some of the jankiest desktop apps ever — MilesCranmer · 2026-09-11
- Misquoted: Anthropic Staff Warned of Double-Digit Extinction Risk by 2030, Not Dismissed It — davidmanheim · 2026-09-11
- Economist Ben Moll: You Can Model Anthropic's 15% AI GDP Growth, But It Won't Happen — sebkrier · 2026-09-11
- Cohere Labs launches interactive tool mapping which tasks of 178 occupations AI can automate — Cohere_Labs · 2026-09-11
- AI researcher on SkyNews flags concerns over inequality, power and criminal misuse — schwarzjn_ · 2026-09-11
- VC compares AI doom rhetoric to pandemic-era fear messaging — StewartalsopIII · 2026-09-11