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

Sakana AIJapan

Recursive Self-Improvement through Multi-Agent Self-Supervision

October 11

As AI systems tackle increasingly open-ended research problems, human experts may struggle to assess results and guide further progress.

Agents & vibe coding media

Read at Sakana AI ↗

One letter a week, starting soon.

Latest

Recursive Self-Improvement through Multi-Agent Self-Supervision

Related

Japanいつ会話を捨てて、新しいセッションで始めるか：区切りで切り、正本から再開する Zenn (AI)

JapanGitHubトレンドの動画生成agent skill「video-shotcraft」を実際にレンダリングしてみた Zenn (AI)

Japan「AIの喧嘩の仲裁を人間がする時代が来た」ClaudeとCodexの喧嘩、犯人はどっちだ？OneDriveを殺したやつ、名乗り出ろ Zenn (AI)

JapanWindows版CodexがMXCに対応、セットアップを高速化 ——ChatGPTの全プランでオートレビューを無料化、Pro向けにメッセージ予測機能をベータ提供 gihyo.jp

JapanGoogle、業務向けGemini Agentを発表 ——調査から資料作成まで任せられ、Claudeも選択可能 gihyo.jp

JapanClaude CodeのUIや動作をTypeScriptでカスタマイズできる「Mods」正式リリース gihyo.jp