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

b12136

11.05

fit : account for skipped NextN layers when setting n_gpu_layers ( #31569 ) fit : account for skipped NextN layers when setting n_gpu_layers Without MTP, fit counts n_layer + 1 layers while the model…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b12136

Related

Toolsb12135 llama.cpp releases

ValleyRising demand puts Locaweb’s data center strategy to the test SiliconANGLE

SiliconAnti-Data Center Sentiment Rides Blue Wave, Threatening AI Boom HPCwire

LabsNew NVIDIA Cosmos 3 Open Models for Interactive World Simulation Hugging Face Blog

ValleyMeta warns that election backlash against data centers could make AI expansion harder TechCrunch AI

SiliconThe Iron(wood) Throne: Google's TPU Stakes Its Claim on Inference SemiAnalysis