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

Claude Code releasesTools

v2.1.294

October 8

What's changed Fixed prompt and agent hooks written as instructions (such as "Block commands that...") allowing what they should block Improved how prompt hooks on Stop and SubagentStop written as…

Agents & vibe coding

Read at Claude Code releases ↗

One letter a week, in your inbox.

Latest

v2.1.294

Related

JapanあなたのAIが、システム保守に強くなる Zenn (AI)

JapanClaude Code を止まらせない Stop フックの作り方——公式仕様と、実運用で5回誤作動した話 Zenn (AI)

ToolsManaged Deep Agents delivers a better user experience for agents in production LangChain

ValleyAt WebexOne, Cisco’s Jeetu Patel argues the agent era will be won on context, cost and control SiliconANGLE

JapanCodex の既定が GPT-6.1 Sol に変わった週: 単価・再接続・無人運用の確認点 Zenn (AI)

Japan富士通では「Copilot」10万ライセンスの利用率が“9割超え” 「導入したけど使われない」をどう防いだ？ ITmedia AI+