DeepSeek's New LLM Architectures

January 30
1 hr

Episode Description

Pierce and Richard break down DeepSeek's latest model architecture moves in Manifold-Constrained Hyper Connections and Engram memory. Are these conceptually sound? Will they hop the pond over to US frontier labs?

See all episodes

Never lose your place, on any device

Create a free account to sync, back up, and get personal recommendations.