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

VS Code UpdatesTools

What 50,000 Runs of a 5-Line Eval Taught Us

06.19

How AI coding models calibrate effort, token cost, and tool use on even the simplest task, and what that means for model selection and cost. Read the full…

Research blog

Read at VS Code Updates ↗

One letter a week, starting soon.

Latest

What 50,000 Runs of a 5-Line Eval Taught Us

Related

LanguagesModular: Modular 26.4: SOTA MoE Serving, Model Bringup via Agent Skills, Mojo 1.0 Beta 2 and More Mojo Blog

VoicesLLM Research Papers: The 2026 List (January to May) Ahead of AI

ToolsScaling incident management for an AI-native organization using Cosmos Augment Code

VoicesRecent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention Ahead of AI

ToolsOpus 4.7 for 33% less: How Auggie beats Claude Code on cost and quality Augment Code

VoicesMy Workflow for Understanding LLM Architectures Ahead of AI