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

ChangelogVoices

MCP on Code Mode (Interview)

05.15

This week I’m talking with Matt Carey about Code Mode and how most of us have been thinking about MCP all wrong.

MCP, skills & tools

Read at Changelog ↗

One letter a week, starting soon.

Latest

MCP on Code Mode (Interview)

Related

VoicesBitwarden CLI compromised (News) Changelog

VoicesSelling SDKs in the era of many Claudes (Interview) Changelog

ToolsIntroducing Cline SDK: the upgraded agent runtime, and we rebuilt Cline upon it Cline Blog

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

EuropeWorkflows for work that runs the business Mistral AI

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