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

Nikkei Asia TechnologyJapan

As Muse personal AI agent debuts in Japan, Meta exec says it won't have ads

10.23

AI head Wang explains strategy of keeping some models open to counter China

Agents & vibe coding

Read at Nikkei Asia Technology ↗

One letter a week, starting soon.

Latest

As Muse personal AI agent debuts in Japan, Meta exec says it won't have ads

Related

JapanClaude Code v2.1.309 セキュリティ修正まとめ:サンドボックス脱出・権限チェック・フックfail-openを解説 Qiita (LLM)

JapanPLC の知識はあるけどコードは書けない私が、Claude Code にサーボのシミュレータを作らせた 1 日【非公式】 Zenn (AI)

Japan複数行の指示が2行目以降消えた。Claude Code・CodexとWindowsで踏んだ10の罠 Zenn (AI)

Japan「怠惰なシニア開発者」をClaude Codeに演じさせたら本当にコードは減るのか(ponytail実測) Zenn (AI)

JapanなぜAIは1回の出力上限を超えて巨大コードを書けるのか？コーディングエージェント徹底解剖 Zenn (AI)

JapanBuilding "SAGE" - an AI agent platform for security work - Part 1: Human-in-the-loop design LINE Engineering