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

Think you need a better reranker? Check your retrieval first.

September 28

You built a search system using the latest, greatest models , and maybe you were thrilled with the outcome. But what happens if the search results were… sort of… bad?

Research

Read at The New Stack ↗

One letter a week, in your inbox.

Latest

Think you need a better reranker? Check your retrieval first.

Related

GitHubClaude Opus 5.5 vs. Opus 5 on reasoning tasks: Cheaper, faster, but not better The New Stack

ValleyOpenAI halts frontier-model training amid string of agent misalignment incidents Ars Technica AI

ResearchRaise Robotics to discuss scaling field robots at RoboBusiness The Robot Report

SiliconNVIDIA Vera SMT Performance Benchmarks Phoronix

ValleyAutoheal raises $7.9M to evaluate and fix AI agents with… AI agents SiliconANGLE

AsiaTonbo Imaging Secures IPO Nod After Refiling Draft Papers Inc42