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

ModalTools

Scaling to 1 million concurrent sandboxes in seconds

July 16

How (and why) we built a scheduling system that can scale to 1 million concurrent sandboxes (per workspace) in seconds.

Research

Read at Modal ↗

One letter a week, in your inbox.

Latest

Scaling to 1 million concurrent sandboxes in seconds

Related

ToolsReinforcement learning is an infrastructure problem Modal

ResearchTowards demystifying the creativity of diffusion models Google Research

ResearchCapturing token IDs during agentic interactions for better reinforcement learning Amazon Science

ToolsAgentic MapReduce Cognition (Devin & Windsurf)

ToolsEvaluating Security Swarm Cognition (Devin & Windsurf)

LabsDiScoFormer: One transformer for density and score, across distributions Ai2