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

Practical AIVoices

Abundant Intelligence at the Midwest AI Summit

10.29

In this special episode, we bring you highlights from three talks at the Midwest AI Summit. Heidi Porter explores how to build reliable AI-augmented workflows using the right tools, evaluations, and…

Read at Practical AI ↗

One letter a week, starting soon.

Latest

Abundant Intelligence at the Midwest AI Summit

More from Practical AI on Accept All

VoicesExploit Development, Agentic Vulnerability Discovery, and Fake PoCs Practical AI

VoicesIs Education Failing our Students in this AI-Driven World? Practical AI

VoicesNarrative intelligence and the human advantage Practical AI

VoicesOpen models and the future of Physical AI with NVIDIA Practical AI

VoicesFrom AGENTS.md to Enterprise Deployment Practical AI

VoicesHow to get discovered in AI search Practical AI