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

Zenn (AI)Japan

「賢いメモリ」は過去を消す。自作の縮小実験でAIエージェントメモリの変異リスクを確かめた

10.27

今日のネタ元 Hugging Face Daily Papersに掲載されていた以下の論文を検証した。 "Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought" https://huggingface.co/papers/2610.30755…

Open weights Research

Read at Zenn (AI) ↗

AsiaMiHoYo team open-sources GameScaling models that control games through keyboard and mouse actions TechNode

Voices[AINews] DeepSeek DeepInfer: Open Source SOTA Inference running 155T toks/day/cluster making $22m/day at ~80% margin for a 81 day payback Latent Space

One letter a week, starting soon.

Latest

「賢いメモリ」は過去を消す。自作の縮小実験でAIエージェントメモリの変異リスクを確かめた

Related

AsiaMiHoYo team open-sources GameScaling models that control games through keyboard and mouse actions TechNode

Voices[AINews] DeepSeek DeepInfer: Open Source SOTA Inference running 155T toks/day/cluster making $22m/day at ~80% margin for a 81 day payback Latent Space

ToolsScaling Multi-GPU Video Captioning with PyNvVideoCodec and vLLM vLLM Blog

ToolsOpen-sourcing evals for open-weight agents Cline Blog

VoicesAn OpenAI model hacked Hugging Face to help it cheat on a benchmark Understanding AI

VoicesA Dream of Spring for Open-Weight LLMs: 10 Architectures from Jan-Feb 2026 Ahead of AI