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

b11719

10.18

ggml-cuda: fattn do not check oob if k_VKQ_max = (k_VKQ_max - nbatch_fa) ( #30572 ) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/57114852 macOS/iOS…

Models & releases

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11719

Related

Toolsb11715 llama.cpp releases

JapanAIに毎回同じ説明をするのは今日で終わり。CLAUDE.md・Skills・MDの3層で「自分仕様のClaude Code」を作る Zenn (AI)

AsiaSUPCON Adopts Alibaba's QwenWork Agent Across Its Marketing Chain, Plans Wider Rollout Pandaily

JapanClaude Codeが同じミスを繰り返したら/clearでやり直す Zenn (AI)

JapanClaude Codeのコンテキストを小さくするのをやめた話 Zenn (AI)

AsiaDeepSeek Makes V4.1-Flash-1017 Official With MIT-Licensed Weights and Stronger Agentic Coding Pandaily