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

音声AIのLLM比較をテキスト回答だけで決めない：APIと自前vLLMを同じ会話トレースで評価する

11.02

モデルのベンチマークが高く、テキスト回答も自然なのに、音声化すると「話し始めが遅い」「長すぎて割り込まれる」「訂正後も古い回答を続ける」ということがあります。ここでの迷いは、どのLLMが最も賢いかではありません。モデルを切り替えた結果、会話のテンポや利用者の発話権を壊さな...

Open weights

Read at Qiita (LLM) ↗

One letter a week, starting soon.

Latest

音声AIのLLM比較をテキスト回答だけで決めない：APIと自前vLLMを同じ会話トレースで評価する

Related

GitHubGoogle and Meta Open-source TorchTPU to Bring Native PyTorch Support to Google TPUs InfoQ AI

JapanGLM-5.3のサイバー評価を読む：成功率・試行単位・比較条件を分ける Qiita (LLM)

Japanクラウド型コーディングエージェントとは何か：DeepSeek Super-agent はどこに置けるか Qiita (LLM)

AsiaSenseTime open-sources 9-billion-parameter AI model that reuses layers for deeper processing TechNode

AsiaDeepSeek team open-sources proactive coding agent research prototype TechNode

GitHubOpen-source security in the AI exploit era: Patch without changing a thing The New Stack