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

LangChainTools

How Numan Built an Eval-First AI Health Coach with LangGraph and LangSmith

10.19

How Numan built Nu, an AI health coach, on LangGraph and LangSmith with per-category evals, simulated conversations, and safety gates on a regulatory line.

Research Regulation & safety

Read at LangChain ↗

One letter a week, starting soon.

Latest

How Numan Built an Eval-First AI Health Coach with LangGraph and LangSmith

Related

AI companies want to embed safety evaluators, but countries need their own Rest of World

ToolsThe Most Common Questions About Agent Evals, Answered LangChain

ToolsJev is now available in LangSmith Evals LangChain

SiliconAgentic AI Explores Heterogeneous Chip and Interconnect Architectures (Argonne, UIUC) SemiEngineering

LabsWho judges the judge? Three helpful ways to audit your LLM evaluators Google Cloud AI

ValleyDisney found a way to buy Character.AI without buying its lawsuits Ars Technica AI