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

Microsoft ResearchResearch

Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses

10.07

At a glance Harnessed Agentic RL: Microsoft Research Asia introduces a training paradigm in which the same agent harness used in deployment participates directly in reinforcement learning, removing…

Agents & vibe coding

Read at Microsoft Research ↗

One letter a week, starting soon.

Latest

Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses

Related

ToolsDeepSeek-V4.1-Flash on vLLM: 5x Agentic Throughput Since Day 0 vLLM Blog

ToolsRemote control for local agents Cursor Changelog

ResearchOpen and Emergent Problems in Agentic Privacy and Security: A Contextual Angle Google Research

VoicesWhy agent swarms could be the next “scaling law” Understanding AI

SiliconAttempts to Keep Humans in the AI Loop May Actually Push Them Out IEEE Spectrum AI

ToolsWould you deploy an agent you don't control? Pydantic