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

b11997

10.30

llama : reuse the tensor staging buffer and skip the direct-io bounce buffer ( #31321 ) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/61552516 macOS/iOS…

Models & releases

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11997

Related

Toolsb11988 llama.cpp releases

AsiaCanadian AI firm Cohere targets $5b in series E funding Tech in Asia

AsiaMistral opens Large 4 weights for enterprise AI deployment Tech in Asia

JapanGoogle、Gemini内で直接ファイルを作成、プレビュー、編集可能に ―PDF、プレゼンテーション、スプレッドシート、MD、LaTeXに対応 gihyo.jp

ValleyCloudera and Mistral bring open-weight models closer to enterprise data SiliconANGLE

ValleyYou can generate and edit Google Docs files directly in Gemini chats now The Verge AI