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

PydanticTools

The best Langfuse alternatives in 2026, honestly compared

08.26

An agent gives a wrong answer at 2am. The Langfuse trace is right there: prompt, model call, tool call, tokens, cost. Nothing in it looks broken.

Pydantic Logfire

Read at Pydantic ↗

One letter a week, starting soon.

Latest

The best Langfuse alternatives in 2026, honestly compared

More from Pydantic on Accept All

ToolsThe 7 best LLM evaluation tools in 2026 Pydantic

ToolsThe best OpenTelemetry backends in 2026, honestly compared Pydantic

ToolsThe best prompt management tools in 2026 Pydantic

ToolsYour Pydantic AI agents just gained a voice Pydantic

ToolsThe best Sentry alternatives in 2026, honestly compared Pydantic

ToolsFeature flags for production AI Pydantic