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 a hundred and forty 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

b11895

10.26

metal : stop overflow from happening in large matrix output offsets ( #30072 ) Metal : stop overflow from happening in large matrix output offsets Assisted-by: Codex metal : widen batch offsets and…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11895

Related

Toolsb11889 llama.cpp releases

JapanMacao casinos chip in $1.1bn to back city's economic diversification Nikkei Asia Technology

JapanIndia's chip design startups struggle with final commercial hurdle Nikkei Asia Technology

JapanSingapore-linked data center projects face growing rejection in Indonesia Nikkei Asia Technology

Wall Street's fastest traders are building data centers and backing chip startups to stay ahead in AI The Decoder

SiliconNVIDIA Cuts HBM4 Speed and NVLink Bandwidth Targets for "Vera Rubin" TechPowerUp