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

b11978

10.29

tests : fix comp_padding CUDA graph reservation ( #31344 ) Assisted-by: Codex Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/61149598 macOS/iOS: macOS…

Models & releases

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11978

Related

AsiaDeepSeek V5 identifiers surface in official Harness code repository TechNode

GitHubClaude Code regularly sends each background agent’s transcript to its model Hacker News (front)

Japanv2.1.312 で直ったのは skills の方：Bash で cd すると許可ルールが外れる話は仕様のまま Zenn (AI)

JapanWindows と Mac の Claude Code どうしで文脈を受け渡す — クラウドなしの共有メモ MCP「jige」 Zenn (AI)

JapanClaude Codeを褒めちぎってみた Zenn (AI)

AsiaSamsung Q3 net profit hits $56b on AI chip demand Tech in Asia