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

b11907

10.26

models : replace ggml_tensor** out-params with output structs ( #31142 ) The hyper-connection and DSA graph builders wrote their extra outputs (post / comb gates, carried top-k selections, inject…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11907

Related

GitHubA faster way to compute signed 64-bit floor division by constants Lobsters

LabsFleet-wide computer vision lifecycle at the edge with SageMaker SDK v3 AWS Machine Learning

ValleyHighway thieves are spoofing GPS to steal millions in data center-bound cargo Ars Technica AI

SiliconTSMC A14 Node to Break Eight Years of SRAM Scaling Stagnation TechPowerUp

ValleySpaceX locks in $40B GPU financing deal with Apollo TechCrunch AI

SiliconHow NVIDIA Minerva Turns Telemetry Chaos Into Peak GPU Yield NVIDIA Technical Blog