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

b11592

October 13

cuda : add GGML_CUDA_GRAPH_DEBUG and read env vars once ( #30327 ) ggml-cuda: gate CUDA graph debug logs behind GGML_CUDA_GRAPH_DEBUG ggml-cuda: cache env var lookups in static const instead of…

Chips & compute

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11592

Related

SiliconNVIDIA RTX Spark Game Ready for Dozens of AAA Titles at Launch, Including DLSS 5 and Anti-Cheat Support TechPowerUp

LabsMeta’s Generative Ads Model (GEM): Scaling the Central Model and Compute Engine for Frontier Ads AI Meta Engineering

GitHubGemini 4 Argon debuts with a unified 1M input/output token limit The New Stack

Silicon(PR) Bolt Graphics Achieves Silicon Bring-up of Zeus Test Chip, Opens Taipei Office TechPowerUp

AsiaMeitY invites AI compute providers to supply 10,000 GPUs under IndiaAI Mission MediaNama

SiliconChinese AI companies buy 1 million Nvidia GPUs in a single year, report claims Tom's Hardware