HN Radio.daily Hacker News, read aloud

← all entities

GLM-5.2

product · 5 stories across the archive · newest first · ai · security

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 20261 mention in Jun 20268 mentions in Jul 2026mentions by month
mixed The HN mood is broadly impressed by the hack and its systems-engineering ambition, but many commenters question the practicality at very low tokens per second and worry about RAM, NVMe capacity, and SSD wear. Several people are comparing notes on related local-inference experiments, Apple Silicon builds, mmap approache — latest discussion,
often appears withAnthropicClaude CodeOpenAIAMDMixture-of-ExpertsNVIDIA
  1. Colibrì gets a 744B-parameter model crawling on consumer hardware▲ 871 · 215 comments · 3:49
  2. Open-weight AI models threaten the inference-margin story▲ 690 · 468 comments · 0:39
  3. AMD inference gets cheaper per token, but HN wants the watt bill▲ 358 · 136 commentsin 5 episodes: · 1:33 · 1:34 · 1:32 · 2:45 · 1:40
  4. Z.ai launches ZCode, a GLM-5.2 coding-agent harness▲ 509 · 355 comments · 0:29
  5. Open-weight GLM 5.2 surprises Semgrep on AI bug hunting▲ 1108 · 514 comments · 6:21