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

b11268

September 30

opencl: fix get_tensor for q5_K adreno gemm_nonshuffle kernel ( #29555 ) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51311810 macOS/iOS: macOS Apple…

Models & releases

Read at llama.cpp releases ↗

One letter a week, in your inbox.

Latest

b11268

Related

Toolsb11267 llama.cpp releases

JapanOpenAI、AIとチームで作業する「ChatGPT Space」と、継続的に動作するクラウドエージェント「dots」を発表。GPT-6.1 Solも提供開始 gihyo.jp

ValleyOpenAI’s GPT-6.1 Sol delivers Astra-like performance at a dramatically lower price SiliconANGLE

AsiaOpenAI launches GPT-6.1 Sol, says it nears Astra Tech in Asia

GitHubLivenerf: Has Opus 5.5 been nerfed yet? Hacker News (front)

ValleyElon Musk’s AI-powered Grokipedia is updating again The Verge AI