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

Weights & BiasesTools

How to structure effective Agent Skills and evaluate whether they actually work

June 23

Improve your Vibe Coding Skills using Agent Skills and evaluate them with Skills Bench and W&B Weave

Agents & vibe coding MCP, skills & tools Research Articles Agents Community Posts Weave

Read at Weights & Biases ↗

One letter a week, starting soon.

Latest

How to structure effective Agent Skills and evaluate whether they actually work

Related

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

VoicesEvals Skills for Coding Agents Hamel Husain

ToolsClosing the loop: Evaluating and improving Replit Agent at scale Replit Blog

ToolsCustomize Cursor Cursor Changelog

ToolsCustomize Replit Agent with Skills & Custom Instructions Replit Blog

ToolsCustom stores, custom tools, and auto-review for the Cursor SDK Cursor Changelog