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

b11927

10.27

metal : add GGML_OP_TOP_K_MASK ( #31230 ) metal : add GGML_OP_TOP_K_MASK Port the fused top-k mask from the CUDA backend: a grid-stride kernel fills the output with -inf, then one threadgroup per row…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11927

Related

ValleyNvidia backs Indian startup helping companies run AI models with fewer GPUs TechCrunch AI

SiliconNvidia is bankrolling AI accelerator supply chain buildout to reserve production capacity Tom's Hardware

VoicesAnthropic S-1 & Datacenters are Politically Unsustainable in 2026 AI Supremacy

ValleyData center backlash is uniting America The Verge AI

Meta gets $3 billion from Nvidia and plans to spend more on Nvidia chips The Decoder

SiliconData center gear is being hijacked in transit to the tune of hundreds of millions Tom's Hardware