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

Reconstructing how OpenAI agents attacked Hugging Face

07.30

What happens when AI agents driven by a top frontier model escape their secure sandbox? Join Daniel and Chris as they unpack the AI wonk's equivalent of a murder mystery!

Agents & vibe coding Open weights

Read at Practical AI ↗

One letter a week, starting soon.

Latest

Reconstructing how OpenAI agents attacked Hugging Face

Related

ToolsA note on the Hugging Face agent incident Modal

GitHubOpen rails for agentic commerce at Open Source Summit North America 2026 Google Open Source Blog

LanguagesClaw Patrol: an open-source security firewall for agents Deno Blog

VoicesSurviving the New Economics of a Post-Agentic World Practical AI

VoicesBuilding Durable AI Agents Practical AI

VoicesAIUC-1: Building trust in AI agents Practical AI