From First Principles cover image

FFP EP. 21 | Roman Concrete, Brain “Cognitive Legos,” DeepSeek, and Econophysics

From First Principles

00:00

Evidence for Stable, Reusable Neural Subspaces

They discuss classifier transfer tests showing stable geometry: color and shape representations persist across tasks.

Play episode from 55:19
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app