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

b11965: llama : remove simple batch splitting for DSV4 (#31300)

10.28

llama : fix DSV4 compressor padding for simple batches Count actual tokens per sequence when padding compressor writes. Add a graph reuse regression test for odd-sized DeepSeek V4 and V4.1 batches.

Models & releases

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11965: llama : remove simple batch splitting for DSV4 (#31300)

Related

SiliconThin, Light and Built for Everything: NVIDIA RTX Spark Windows Laptops Gain New Models, Agent Tools and Games NVIDIA Blog

JapanCLAUDE.md が長くなった時の分け方と、AGENTS.md との二重管理の直し方 Zenn (AI)

Japanダウンロードフォルダで Claude Code や Codex を起動してはいけないのはなぜ？ Zenn (AI)

VoicesThe October inflection point for vibe game development Simon Willison

JapanClaude Code に、経緯を覚えている「専属バトラー」を作る Zenn (AI)

Japan自作の Claude Code 安全ガードを、第三者のテスト集（89件）で測ったら、すり抜けが見つかった Zenn (AI)