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

The New StackGitHub

Copilot tops GitHub’s own AI code review benchmark. An independent one tells a different story.

October 6

If there’s one thing the AI software engineering world doesn’t lack, it’s benchmarks. Want to know whether an agent can resolve real-world GitHub issues? There’s SWE-bench .

Agents & vibe coding Research

Read at The New Stack ↗

One letter a week, in your inbox.

Latest

Copilot tops GitHub’s own AI code review benchmark. An independent one tells a different story.

Related

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

LabsAgentic retrieval with LangChain and Amazon Bedrock Knowledge Bases AWS Machine Learning

LabsEvaluating multi-agent systems for explainability and helpfulness with Amazon Bedrock AgentCore AWS Machine Learning

GitHubPresentation: Building Reusable Evaluation Frameworks for Agentic AI Products InfoQ AI

LabsScaling cloud migrations with agentic AI on Amazon Bedrock AgentCore AWS Machine Learning

JapanClaude Code、同梱のclaude-apiスキルに新コマンド「build-eval」と「hillclimb」を追加 ——評価の作成からプロンプト・モデル設定の調整まで gihyo.jp