Results
4 articlesSort
1:50:48EN
Y Combinator· Oct 24, 2026Why Inference Matters 12× More Than TrainingFrançois Chaubard, Dan Fu, Jeff Morgan, Joe Fioti, Liangsheng Yin · Y CombinatorYC Paper Club walks the inference stack from an API request down to GPU kernels. Four talks from Together AI, Ollama, Luminal, and SGLang argue that serving quality, not just training FLOPs, is where most of the compute and the money now sit.
0:22EN
Matthew Berman· Oct 18, 2026DeepSeek's Memory Use: A Short Claim About KV CacheMatthew Berman · Forward FutureMatthew Berman links lower cache memory use to serving more tokens, but the excerpt does not state the comparison behind its figures.
31:30EN
Theo - t3․gg· Jun 30, 2026Why Some AI Models Use Fewer Tokens to Solve a TaskTheoTheo explains input, output, caching and reasoning tokens, then explores a hypothesis about terse internal reasoning.
1:22:52ENMatthew Berman· May 7, 2026Richmond Alake on Agent Memory, Context Engineering and the Cost of RecallMatthew Berman, Richmond Alake · Forward FutureIn a livestream with Matthew Berman, Oracle’s Richmond Alake explains how agents store, retrieve and consolidate information, and where memory design trades off with caching and latency.