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

Sourcegraph BlogTools

Introducing Agentic Batch Changes: the frontier agent for code change at scale

09.14

Codebase-wide changes across hundreds or thousands of repositories can now be run by one engineer.

Agents & vibe coding

Read at Sourcegraph Blog ↗

One letter a week, starting soon.

Latest

Introducing Agentic Batch Changes: the frontier agent for code change at scale

Related

ToolsCompliance-first AI: proving agent provenance for regulated engineering teams Sourcegraph Blog

ToolsCode Finder: fast, efficient code search for coding agents Sourcegraph Blog

ToolsAgentic Batch Changes is now in public beta Sourcegraph Blog

ToolsWhy coding agents fail in large codebases (and what to do about it) Sourcegraph Blog

ToolsLessons on UX, security, and scale when building an enterprise-grade Slack agent Sourcegraph Blog

ResearchWhy don’t machine learning research agents overfit? Amazon Science