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 V4.1 Flash 1017 の変更点：料金そのままで出力が短くなった新チェックポイントを検証

10.19

この記事は AIHubMix が作成しました。調査日と AIHubMix 経由の動作確認日は、いずれも2026年10月19日です。記事中のベンチマークとタスクあたりのコストは DeepSeek が自社で公表した数値（コストは同社のグラフを The Decoder が読み...

Models & releases

Read at Qiita (LLM) ↗

One letter a week, starting soon.

Latest

DeepSeek V4.1 Flash 1017 の変更点：料金そのままで出力が短くなった新チェックポイントを検証

Related

JapanDeepSeek V4.1 Flash 1017 移行時の reasoning_content 400 エラーと課金の落とし穴 Qiita (LLM)

JapanClaude Codeでプロンプトインジェクションに備える Zenn (AI)

JapanClaude Codeのsecurity-guidanceは脆弱コードを止めるか 18回実行して測った Zenn (AI)

JapanClaude Codeに時刻と使用量を表示する――Codexとの並行作業を見失わないために Zenn (AI)

JapanAI に何を任せないか：コードを書かないマネージャーの仕事道具（ChatGPT Dots・Grok Bot） Zenn (AI)

JapanHaiku 5.5の移行前に確認する3点──トークン数・旧設定・max_tokens Zenn (AI)