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

b11140

September 23

CUDA: enable sparse-fa for dsv4 prefill (again) ( #29298 ) CUDA: enable sparse-fa for dsv4 prefill (again) CUDA: unroll the query loop of the sparse mask scan The query loop of…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, in your inbox.

Latest

b11140

Related

SiliconTaped Out Xbox Helix Chip Reportedly Reaches 56 TFLOPS, Surpassing PS6 TechPowerUp

EuropeNscale helped ByteDance subsidiary access Nvidia chips, swerving US rules — reports Sifted

ValleyChicago mayor proposes 12-month moratorium on new data centers Axios Technology

LabsAdvancing Private AI Compute with secure, server-side memory Google DeepMind

ResearchMIT welcomes David Siegel SM ’86, PhD ’91 as its next Innovation Fellow MIT News AI

SiliconSakeena Fiza Helps NVIDIA Hardware Succeed at Scale NVIDIA Blog