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

Karpathy skills on OpenClaw: agents don't write better code. But they do it more efficiently.

04.30

We added Karpathy-inspired coding rules to root AGENTS.md and ran three coding agents through 40 OpenClaw PRs.

Agents & vibe coding MCP, skills & tools

Read at Augment Code ↗

One letter a week, starting soon.

Latest

Karpathy skills on OpenClaw: agents don't write better code. But they do it more efficiently.

Related

VoicesEvals Skills for Coding Agents Hamel Husain

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

VoicesBitwarden CLI compromised (News) Changelog

VoicesExploring with agents (Interview) Changelog

ToolsIntroducing Parallel Agents in Zed Zed Blog

ToolsCode Search, Deep Search, or MCP: When to Use Each Sourcegraph Blog