AgentStack Daily

← AgentStack Daily17 sept · 34 min

Episode 113: DeepSeek V4.1-Flash Packs Million-Token Memory Into FP4 Cache

Episode 113: DeepSeek V4.1-Flash Packs Million-Token Memory Into FP4 Cache17 sept34 min

Escuchar en SpotifyTambién funciona en tu navegador

11 apps más

DeepSeek V4.1-Flash lands with million-token context in an FP4 cache. Cohere releases a 218B open-weights translation model spanning 50 languages.

Show notes: https://tobyonfitnesstech.com/podcasts/episode-113/