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

Quail: Speeding up AI-SQL by jointly optimizing query planner and inference engine

09.24

Maximizing perf on AI-SQL queries with the KV-optimal left-deep join

Read at Modal ↗

One letter a week, starting soon.

Latest

Quail: Speeding up AI-SQL by jointly optimizing query planner and inference engine

More from Modal on Accept All

ToolsHow to serve trillions of tokens for trillion-parameter coding agents Modal

ToolsProduct updates: Sandbox Sidecars, new models, a refreshed dashboard, and more Modal

ToolsOne compute platform for end-to-end training at Markov Robotics Modal

ToolsModal is expanding in Europe with our new London office Modal

ToolsHow Botika runs full-stack generative AI on Modal Modal

ToolsQwen3.8-2.4T-A95B now available on Modal Modal