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

b12034

11.02

webgpu : fix CI by keeping scratch alloc sizes monotonic in batch length ( #31422 ) webgpu: keep scratch alloc sizes monotonic in the batch length The flash attention vec path and the MMVQ path…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b12034

Related

JapanOpenAI API で構造化出力（JSON mode / Structured Outputs）を使う Zenn (AI)

AsiaSamsung SDS, LG CNS target AI data center growth in Asia Tech in Asia

AsiaSingapore data center firm STT GDC seeks $2.4b loan Tech in Asia

AsiaGoogle commits $160m to water infrastructure for MY data center Tech in Asia

SiliconLiquid-Cooled NVIDIA Servers at the ASRock Rack OCP 2026 Booth ServeTheHome

ValleyWhere Dems eyeing the White House are putting their midterm chips Axios Technology