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

b11559

October 11

opencl: improve fa, allow dk512 for gemma-4, improve dk64 ( #30266 ) opencl: enable Gemma-4 E4B GPU decode Co-authored-by: Hongqiang Wang [email protected] opencl: extend Gemma-4 GPU decode to…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11559

Related

ValleyCan the AI industry persuade data center opponents by getting rid of NDAs? TechCrunch AI

SiliconModder discovers that putting a GPU in the 'wrong place' can deliver a 19 degree cooler hotspot Tom's Hardware

GitHubContext Language Models: Self-Managing Context to Improve Performance and Reduce Compute Costs InfoQ AI

SiliconKINGPIN Says a Connector Dispute With NVIDIA Derailed EVGA's Last Flagship Card TechPowerUp

SiliconNew Cray-1 supercomputer replica built with 30 vintage Mac Minis and packs 1.5 TFLOPS of compute Tom's Hardware

Cheaper AI tokens are driving more demand, and that's Jensen Huang's best-case scenario The Decoder