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

b12081

11.03

cuda: potential fix for Q8_1 correction sum ( #31247 ) cuda: potential fix for Q8_1 correction sum Update ggml/src/ggml-cuda/quantize.cu Co-authored-by: Gaurav Garg [email protected] addressed…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b12081

Related

Toolsb12080 llama.cpp releases

ValleyData centers are turning to old jet engines as the wait for power grows TechCrunch AI

SiliconMarvell Cuts To The Front Of The Datacenter Optics Line With Lumentum Deal The Next Platform

SiliconAMD Reports Third Quarter 2026 Financial Results AMD Newsroom

SiliconGPU Prices Up Again in October, RTX 5090 Now Sells for 262% Over MSRP Worldwide TechPowerUp

SiliconMassive Four-GPU RX 470 Card Surfaces, Probably Built for Crypto Miners TechPowerUp