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

Qiita (LLM)Japan

DeepSeek V4-Flash vs GPT-6 Sol：日本語の議事録から正確なToDoを作れるのはどちらか

October 10

担当者と期限の訂正、「できるかもしれません」という提案、後から決まった役割を、日本語の入力で比較しました。本記事はCrazyrouter関連のコンテンツです。2026年10月10日に同サービスのAPIを使い、日本語の架空議事録からToDo表を作成しました。職場の会議と...

Models & releases

Read at Qiita (LLM) ↗

One letter a week, starting soon.

Latest

DeepSeek V4-Flash vs GPT-6 Sol：日本語の議事録から正確なToDoを作れるのはどちらか

Related

JapanCodex（gpt-6.1-sol）のコンテキスト圧縮が「response protection is unavailable」で失敗する原因と回避策 Qiita (LLM)

Japan中国発オープンウェイトAIモデルのリスク網羅調査 Qiita (LLM)

JapanCodex・Claude・Cursor の利用状況をまとめて確認できる「usAge」を作りました Zenn (AI)

JapanClaude MaxプランのAPIクレジットをJevのように使ってみた Zenn (AI)

JapanClaude Managed Agentsのdynamic workflows：切断後に実行状態を復元する Zenn (AI)

Japan【速報】Claude の新機能 Claude Motion 早速使ってみた Zenn (AI)