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

b12008

10.30

gemma3n, gemma4 : create token_embd before the tied output ( #31394 ) The duplicated output looks up token_embd in its buffer context, so token_embd must exist first.

Chips & compute

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b12008

Related

Toolsb12007 llama.cpp releases

ValleyCan AI data centers be mass-produced like cars? This startup aims to find out TechCrunch AI

AsiaAI, fuelled by advanced chips, set to power semiconductor manufacturing: industry veteran SCMP Tech

GitHubNetflix Treats GPU Reliability as a Distributed Systems Problem InfoQ AI

SiliconIntel leaker reveals Moon Lake chip as a likely replacement for N-series SoCs Tom's Hardware

ValleyMaine’s data center revolt will decide who controls the Senate The Verge AI