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

b11866: metal : remove mul_mm_id amax rescaling (#30924)

10.24

The src1 power-of-two rescale in kernel_mul_mm_id is superseded by the per expert-token amax scaling done in the compute graph (ref: #30861 ), which keeps the MoE down-projection activations within…

Research

Read at llama.cpp releases ↗

One letter a week, starting soon.

Latest

b11866: metal : remove mul_mm_id amax rescaling (#30924)

Related

Japanエージェントの記憶は「要約」ではなく「KVキャッシュの直接操作」で圧縮できるのか、135Mモデルで試した Zenn (AI)

VoicesBuild Your Own Reasoning Model: A Full Video Course Ahead of AI

ToolsContext Engineering (Agent Memory) for AI Agents Starts with Retrieval LangChain

LabsMulti-Turn Reinforcement Learning on Amazon SageMaker AI: A hands-on guide AWS Machine Learning

SiliconScaling NVIDIA TensorRT Performance Optimization Beyond a Single Build Route with the Global Performance Tuner, Part 2 NVIDIA Technical Blog

SiliconScaling NVIDIA TensorRT Performance Optimization Beyond a Single Build Route with the Global Performance Tuner, Part 1 NVIDIA Technical Blog