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

IBM ResearchResearch

A new plugin can enable fast runtime monitoring and control

10.21

IBM's vLLM-Hook MIA lets developers inspect and edit the AI generation process with hardly any delay.

MCP, skills & tools Languages & runtimes AI AI Transparency Distributed Inference Generative AI

Read at IBM Research ↗

One letter a week, starting soon.

Latest

A new plugin can enable fast runtime monitoring and control

Related

ResearchQiskit beyond Python: Fortran, C++, and Julia IBM Research

LanguagesDiscontinuing Swift Language IDE Support in the Kotlin Multiplatform Plugin Kotlin Blog

ToolsMigrating the GitHub Copilot runtime to Rust, using Copilot GitHub Copilot Blog

ToolsThe 2026-07-28 Specification MCP Blog

LanguagesModular: Modular 26.4: SOTA MoE Serving, Model Bringup via Agent Skills, Mojo 1.0 Beta 2 and More Mojo Blog

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