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

Augment CodeTools

A good AGENTS.md is a model upgrade. A bad one is worse than no docs at all.

04.22

We pulled dozens of AGENTS.md files from across our monorepo and measured their effect on code generation.

Agents & vibe coding

Read at Augment Code ↗

One letter a week, starting soon.

Latest

A good AGENTS.md is a model upgrade. A bad one is worse than no docs at all.

Related

ToolsIntroducing Parallel Agents in Zed Zed Blog

JapanWhy ID-JAG is the future of AI agent security LINE Engineering

LanguagesModular: How Frontier Coding Agents Built a Video Diffusion Pipeline on MAX Mojo Blog

ToolsCline mobile: how to vibe code from your phone Cline Blog

ToolsThree AIs enter. One survives. What a SIGKILL race reveals about inference speed Cline Blog

VoicesPost-Mortem of Anthropic's Claude Code Leak Practical AI