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

Improving Deep Agents with harness engineering

10.13

Harness engineering improved LangChain's coding agent from Top 30 to Top 5 on Terminal Bench using self-verification, tracing, and context optimization.

Agents & vibe coding

Read at LangChain ↗

One letter a week, starting soon.

Latest

Improving Deep Agents with harness engineering

Related

ToolsDeep Agents Deploy: an open alternative to Claude Managed Agents LangChain

ToolsContext Management for Deep Agents LangChain

ToolsOpen SWE: An Open-Source Framework for Internal Coding Agents LangChain

ToolsBuilding Long-Running Agents with ScaleDown and Deep Agents LangChain

ToolsSearch agent traces by behavior with AI Search in LangSmith LangChain

ToolsHow to build great out-of-the-box user experiences with Managed Deep Agents LangChain