New Substack Details Contravariance Theory Linking AI Models and Brains
Reactions from ranked influencers
2 posts
The blogpost exposition on our "zippering theorems" in Section 4 from our recent Contravariance Theory paper is now out! These zippering theorems explain why end-to-end optimization for downstream tasks often seems to strongly constrain upstream representations.
New substack alert! We present the mathematical theory showing how Contravariance (probably) explains convergent evolution between AI models and brains. https://danyamins.substack.com/p/the-theory-of-contravariance-part2 The zippering theorems put pretty strong guarantees on such convergence. 1/