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

InfoQ AIGitHub

Agents Refactor 300K Lines in Three Weeks, and Practitioners Ask What It Proves

September 30

CodeScene has published a case study in which coding agents refactored 300,000 lines of C over three weeks for roughly $4,000 in tokens, verified by a frame-by-frame replay harness.

Agents & vibe coding Technical Debt Software Engineering Refactoring Code Quality

Read at InfoQ AI ↗

One letter a week, in your inbox.

Latest

Agents Refactor 300K Lines in Three Weeks, and Practitioners Ask What It Proves

Related

GitHubPresentation: From Consumers to Builders: Turning 200 of our Team into Agent Creators in 2 Weeks InfoQ AI

GitHubDocker Cloud Sandboxes Provide a Consistent Sandbox Abstraction across Laptop and Cloud InfoQ AI

GitHubFrom Agent Authorization to AI Production Evaluation: QCon AI New York 2026 InfoQ AI

GitHubArticle: The Agent Harness: What it is and Two Ways to Build One InfoQ AI

Voices[AINews] OpenAI DevDay 2026: Dots, 6.1 Sol, Ultrafast, Decisions API, Agents API, Spaces, Marketplace, and 1.2 Billion ChatGPT WAU Latent Space

AsiaByteDance’s Doubao reportedly preparing personal AI agent, codenamed Spell and tested since April TechNode