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 two hundred 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

Zenn (AI)Japan

Claude Codeの操作をルールで止める仕組みと限界

11.07

この記事で伝えたいこと Claude Codeにやってほしくない操作は、お願いではなく、ルールで止められます。ただし、止まらない操作もあります。お願いにあたるのがCLAUDE.md（Claudeへの指示を書いておくファイル）、ルールにあたるのがpermissions（権限設定）です。permissionsは、AIの判断とは別に、Claude Code本体が操作の直前に照らし合わせます。

Models & releases Agents & vibe coding

Read at Zenn (AI) ↗

One letter a week, starting soon.

Latest

Claude Codeの操作をルールで止める仕組みと限界

Related

JapanClaude CodeからAPIキーなどの秘密情報を守る設定 Zenn (AI)

JapanGPT-6モデルはAstra、Sol、それともLuna？ OpenAIが教える、Codex爆速開発の鉄則 ITmedia AI+

JapanClaude Codeを使ったバイブコーディングで30分で業務アプリを作ってみよう gihyo.jp

Japan修正PRを食べてレビュースキルが賢くなる：Claude Codeによる自己改善サイクル Mercari Engineering

JapanosFoundryが常駐Claude Codeセッションにチャンネル履歴を二度送らない仕組み Zenn (AI)

AsiaOpenCSG Releases Agentic-27B for Tool Workflows, With Commercial Use Requiring Permission Pandaily