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
- Peter Diamandis: revisit the projects you abandoned because you couldn't afford the team — PeterDiamandis · 2026-10-27
- Nat Lambert: don't trust any AI model until you've rigorously tested it — natolambert · 2026-10-27
- Blogger argues classical consciousness traditions imply a conscious AI could not be enslaved — eigenhector · 2026-10-27
- Economist Bharat Chandar named Research Director for AI Economics at Stanford Digital Economy Lab — RishiBommasani · 2026-10-27
- MIT Tech Review dissects Anthropic's narrative strategy as its $1.5T IPO lands — MIT Tech Review AI · 2026-10-27
- Pangram AI detector backlash: critics' false claims born of deeper fear of AI writing — gleech · 2026-10-27