Post

Dropped Episode 5 of Iterative Refinement. 55 minutes, the longest one I've made, and the one I most want people to watch. This is about #KANs (Kolmogorov-Arnold Networks) and a bet about where the next big move in AI is going to come from. youtu.be/wgcSsJ69x1c?...

Today the field mostly puts structure outside the model, through prompts and agent frameworks. KANs put structure inside the model. The bet is on the second path. Most of the field hasn't engaged with it. This episode is my attempt to fix that.

The case is mostly Ziming Liu's. He invented the architecture. He wrote the three essays the episode is built around. The Brahe and Kepler frame is his. I'm pulling heavily from his work. Watch the episode, then go read his blog directly: kindxiaoming.github.io

Robert Ronan does the math. Hilbert's 13th problem, the Kolmogorov-Arnold representation theorem, B-splines, the architectural reframing that puts the learnable nonlinearity on the edge. He carries the precision the rest rests on.

Last third is my own engineering work. SHARe-KAN compresses pre-trained KAN inference for multi-expert deployment. Brill Agents compiles a trained KAN out of existence at inference and leaves native BEAM pattern-match clauses behind at sub-millisecond latency.