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

Zenn (AI)Japan

Claude Code のモデル4種に同じ課題を96回解かせた

10.30

Haiku 5.5・Sonnet 5.5・Opus 5.5・Fable 5.1 のどれを使うか。「難しいことは上のモデルに」とよく言われますが、どのくらいの難しさから上が要るのか、そのとき費用と時間はどれだけ変わるのかは、自分で測らないと分かりません。

Models & releases Agents & vibe coding

Read at Zenn (AI) ↗

One letter a week, starting soon.

Latest

Claude Code のモデル4種に同じ課題を96回解かせた

Related

JapanClaude Tool Runnerで「独自ツールを呼ぶAIエージェント」をTypeScriptで実装する Zenn (AI)

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

AsiaDeepSeek Harness Pre-Release Lets Its Main Agent Hand Off Tasks to Local Codex and Claude Code Pandaily

JapanCodex Day 25徹底解説：Pro・Businessの利用枠2倍とPro 200減枠撤回 Zenn (AI)

ValleyWabi, the AI agent that builds mini apps, now valued at $1.25B after latest round TechCrunch AI

ValleyServal raises $150M at $3B valuation to bring its automation agents beyond IT SiliconANGLE