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

Sourcegraph MCP server and a cheaper model beat a Mythos-class model alone

06.16

On nine CodeScaleBench tasks designed to evaluate agent effectiveness in large codebases, Claude Sonnet 4.6 with the Sourcegraph MCP server outscored Fable 5, winning six of nine at roughly half the…

Models & releases MCP, skills & tools

Read at Sourcegraph Blog ↗

One letter a week, starting soon.

Latest

Sourcegraph MCP server and a cheaper model beat a Mythos-class model alone

Related

VoicesSelling SDKs in the era of many Claudes (Interview) Changelog

ToolsCode Search, Deep Search, or MCP: When to Use Each Sourcegraph Blog

ToolsExtending the Cline loop with plugins and hooks Cline Blog

GitHubA new pkg.go.dev API for Go Google Open Source Blog

LanguagesModular: Day Zero: MiniMax M3 Open Weights on Modular Cloud Mojo Blog

ToolsImproving LM Studio's MLX Engine for Agentic Workflows LM Studio Blog