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 to Build a Model Router in the Harness

October 1

How we built a model router into Open SWE's harness that cut median cost per coding task by 64% with no measurable drop in quality, and how to build your own.

Read at LangChain ↗

One letter a week, in your inbox.

Latest

How to Build a Model Router in the Harness

More from LangChain on Accept All

ToolsWhat Is Jev? A Guide to TypeSafe AI’s System One Model LangChain

ToolsJev is now available in LangSmith Evals LangChain

ToolsBuilding Production Agents with Jev and LangGraph LangChain

ToolsNew in LangSmith: Engine v2, Managed Deep Agents, Fine-Tuning, and more LangChain

ToolsLangSmith Custom Apps: Build custom interfaces around your agent data LangChain

ToolsNew in LangSmith Engine: red teaming and automated testing LangChain