The name is the button.

An agent writes the code now, and a human thumb hovers over Accept all a hundred times a day. The honest question of this decade is what, exactly, you just accepted. So I read the diff.

Eight years as a backend engineer in Stockholm, back in Tokyo since 2023, and I still ship something small most nights, usually badly. My one rule: the only real review of a model is the thing you built with it. That is why there is no leaderboard on this site.

Around two hundred sources come through — the labs' own posts, the papers, the tools, the runtimes and languages nobody is watching yet, the chip under the demo, and the newsletters people actually forward. What is moving gets counted so the week reads at a glance, and every few days I explain one mechanism in plain words.

A story here is a headline, a short excerpt, one image and the link to whoever wrote it. We never reproduce the post; the images belong to their authors. A post written in Japanese appears in Japanese, exactly as it was published, and the link goes to the original.

— Yuki Halvorsen, Tokyo

← Accept All Archive

llama.cpp releasesTools

b12191

11.07

llama_moe_cache: run missed experts on CPU, add tuning script ( #30966 ) moe-cache : compute part of the misses on the CPU --moe-cache-cpu-share F computes a share F of the MoE cache misses on the…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b12191

Related

Toolsb12187 llama.cpp releases

Valley"Congress will investigate": Nvidia CEO Jensen Huang faces probe over alleged Chinese spy ties Axios Technology

SiliconNVIDIA Marks 20 Years of the GeForce 8800 GTX With a Free Path-Traced Steam Demo TechPowerUp

ToolsPyTorch 2.15 tackles the 'one bad GPU' problem DevClass

ValleyThe US let Nvidia sell chips to an empty office in China The Verge AI

GitHubThe $8 Linux Computer (2022) Hacker News (front)