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

b11889

10.25

cuda : use std::string instead of VLA for archName ( #30463 ) cuda : use std::string instead of VLA for archName Modernize the code (old C style) and fix the following warnings…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11889

Related

Toolsb11879 llama.cpp releases

SiliconAivres NVIDIA Vera Rubin and HGX B300 at OCP Summit ServeTheHome

SiliconSecurity-Aware Layer Mapping Reduces Fault Vulnerability In 3D Compute-In-Memory (ASU, U. of Maryland) SemiEngineering

GitHubPyTorch Conference 2026: Google and Meta Open-Source TorchTPU for Native PyTorch on TPUs InfoQ AI

GitHubGoogle ML Drift Accelerates On-Device AI Inference Across Diverse GPUs InfoQ AI

SiliconNew Linux Tool Brings Resizable BAR to Intel Arc GPUs on Old Motherboards TechPowerUp