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

b11734

10.19

cann : refactor #ifdef blocks to avoid unreachable code after return ( #25273 ) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/57413259 macOS/iOS: macOS…

Models & releases

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11734

Related

Toolsb11732 llama.cpp releases

Toolsb11729 llama.cpp releases

Toolsb11735: metal : fix moe_reduce fusion race when dst aliases its inputs (#30795) llama.cpp releases

JapanClaude Code設定ファイルの3層設計（グローバル/プロジェクト/ディレクトリ） Qiita (LLM)

JapanClaude Code が『ファイルを消させない仕組み』を作っている最中に、Mac のファイルが消えた Zenn (AI)

JapanClaude Code で採点係を別のサブエージェントにしたら、14回中6回不合格を出した Zenn (AI)