HN Radio.daily Hacker News, read aloud

← all entities

LongCat Sparse Attention

technology · 1 story across the archive · newest first · ai

0 mentions in Aug 20250 mentions in Sep 20250 mentions in Oct 20250 mentions in Nov 20250 mentions in Dec 20250 mentions in Jan 20260 mentions in Feb 20260 mentions in Mar 20260 mentions in Apr 20260 mentions in May 20260 mentions in Jun 20261 mention in Jul 2026mentions by month
mixed HN is intrigued by the claimed scale and especially by the non-Nvidia ASIC training story, but the thread is heavy with skepticism about verification, model provenance, availability, censorship, and one-off eval anecdotes. Several commenters see the infrastructure claim as strategically important if true; others want a — latest discussion,
often appears withMixture-of-ExpertsLongCat-2.0N-gram Embedding
  1. LongCat-2.0: a trillion-parameter MoE trained on AI ASICs▲ 279 · 87 comments · 5:10