Cookie Consent: We use cookies to give you the best online experience, for analytics, performance, and to tailor the experience towards your interests.

Skip to content
Pic of The Jim Rutt Show

EP 316 Ken Stanley on the AI Representation Problem

August 8, 2025
0 comments

The Jim Rutt Show

Description

Jim talks with Ken Stanley about the Fractured Entanglement Representation hypothesis in deep learning neural networks. They discuss open-endedness in AI systems & evolution, the Picbreeder experiment & its significance, the objective paradox of finding things by not looking for them, comparisons between Picbreeder & SGD networks, visual differences in internal representations, weight sweep experiments, modular vs tangled decomposition, implications for creativity & continual learning & generalization abilities, Unified Factored Representation as an alternative to FER, the relationship to grokking in neural networks, scaling considerations & evidence in larger models, potential methods to achieve UFR, connections to biological evolution and DNA representation, and much more.