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

How distributed inference keeps large AI models moving

10.12

Distributed inference serving is an air traffic control tower for AI traffic, and agentic workflows make it more necessary than ever.

AI AI for Code Explainer Generative AI

Read at IBM Research ↗

One letter a week, starting soon.

Latest

How distributed inference keeps large AI models moving

More from IBM Research on Accept All

ResearchWhat's new at IBM Quantum Q3 2026 IBM Research

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

ResearchDirected execution: same performance, more control IBM Research

ResearchPonder This Challenge - October 2026 - The Ultimate Ultimate Tic-Tac-Toe Game IBM Research

ResearchWhy are silicon wafers round? IBM Research

ResearchFrom error mitigation to fault-tolerant quantum computing IBM Research