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

b11249

September 29

llama : fix init in several tools/examples ( #29632 ) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51066139 macOS/iOS: macOS Apple Silicon (arm64) macOS…

Models & releases

Read at llama.cpp releases ↗

One letter a week, in your inbox.

Latest

b11249

Related

Toolsb11242 llama.cpp releases

Toolsb11240 llama.cpp releases

AsiaChina’s CXMT to favour domestic suppliers in US$5.2b memory-chip capacity push: source SCMP Tech

Japan3値27B(Ternary-Bonsai-2-27B)を RTX 5070×2 の vLLM TP=2 で本番運用した記録 — 最後の壁は PCIe x4 と WSL2 の通信 Qiita (LLM)

GPT-6.1 Astra is too deceptive for release, marking OpenAI's most dramatic safety intervention yet The Decoder

JapanClaude Codeのサブエージェント間はファイル経由で受け渡す Zenn (AI)