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

The New StackGitHub

Agentic AI doesn’t have a model problem. It has a retrieval problem.

10.15

On BrowseComp-Plus, GPT-4.1 answered 93.49% of the questions correctly when it was given the supporting documents directly.

Agents & vibe coding Research

Read at The New Stack ↗

One letter a week, starting soon.

Latest

Agentic AI doesn’t have a model problem. It has a retrieval problem.

Related

GitHubPresentation: What 25 Trillion Tokens Reveal About How Developers Actually Adopt AI Agents InfoQ AI

ToolsThe Most Common Questions About Agent Evals, Answered LangChain

SiliconAgentic AI Alters The CPU-GPU Balance SemiEngineering

ToolsHarbor + Docker Sandboxes: Run Safe, Reproducible Agent Evals Docker Blog

GitHubProduction Patterns for Agents, Evals, and LLM Costs: QCon AI New York 2026 InfoQ AI

ResearchScaling AI-driven chip design with open agent factories IBM Research