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

VS Code UpdatesTools

How Prompt Tuning Improved GPT-5.5 in VS Code

07.06

See how VS Code and OpenAI tested GPT-5.5 system prompt changes in a two-week experiment, cutting tool calls and tail-end token usage while speeding up edits. Read the full…

Models & releases blog

Read at VS Code Updates ↗

One letter a week, starting soon.

Latest

How Prompt Tuning Improved GPT-5.5 in VS Code

Related

EuropeIntroducing Mistral OCR 4 Mistral AI

ToolsReplit is now available in Claude Replit Blog

Japan修正PRを食べてレビュースキルが賢くなる：Claude Codeによる自己改善サイクル Mercari Engineering

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

VoicesThe MAGA power struggle that could decide the fate of Anthropic Understanding AI

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