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

GitHub Copilot BlogTools

ReviewBench: An open benchmark for AI code review

10.05

Agentic code review is becoming an essential piece of how development happens. It helps you inspect pull requests, catch issues, and decide what deserves attention before code ships.

Research

Read at GitHub Copilot Blog ↗

One letter a week, starting soon.

Latest

ReviewBench: An open benchmark for AI code review

Related

VoicesLast Week in AI #345 - 5 new models, 9 misalignment incidents, some Dots Last Week in AI

VoicesClaude’s new auto eval tool Hamel Husain

ResearchHow Diffusion Controller unifies and simplifies AI image generation Google Research

SiliconQualcomm’s System Level Architecture in the Snapdragon X2 Elite Chips and Cheese

VoicesChroma and Agentic Retrieval Software Engineering Daily

ToolsHigh-volume AI scoring with Jev and Pydantic Evals Pydantic