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

b11870

10.25

model: DSV4.1 flash ( #31086 ) model : add DeepSeek-V4.1-Flash (deepseek41) deepseek41 : remove MXFP8, convert the Engram table to BF16 deepseek41 : compute the compressed-KV read layers once in the…

Models & releases

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11870

Related

Toolsb11867 llama.cpp releases

Toolsb11865 llama.cpp releases

Toolsb11860 llama.cpp releases

GitHubGoogle Optimizes Agent Development Kit's 200K-line Python Codebase Overnight with Gemini 4 Argon InfoQ AI

ValleyForced to pick, Grok’s AI model chooses Republicans. OpenAI’s picks Democrats. TechCrunch AI

VoicesBuilding Reasoning Models from the Ground Up: A Full Video Course Ahead of AI