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

b11388

October 4

imatrix: calculate activation-based statistics for new format (GGUF) imatrices ( #14891 ) Use activations to calculate the stats Determine calculation mode Compute entropy for activations Compute…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, in your inbox.

Latest

b11388

Related

Toolsb11382 llama.cpp releases

SiliconAMD Sends In More New GPU Hardware Enablement For Linux 7.4, Bug Fixes Phoronix

ValleyRural Data Centers Are in for a Big Federal Tax Break Wired AI

AsiaTianjin University Lab Unveils 3-Gram Non-Invasive Brain-Computer Interface That Hides in Hair Pandaily

Japan「4GB GPUで8Bモデルを学習できる」というSoupの主張をRTX 5060 Tiで検証したら、学習は本当に動いたがアダプタが空だった Zenn (AI)

GitHubThe work by Valve's Timur Kristóf on improving old AMD GPUs on Linux Hacker News (front)