Last Week in AI cover image

#227 - Jeremie is back! DeepSeek 3.2, TPUs, Nested Learning

Last Week in AI

00:00

Sparse Attention and Indexer Trick

Jeremie explains DeepSeek's sparse-attention indexer, token pruning and why retaining ~2,000 tokens works.

Play episode from 06:10
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