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

The Register AIEurope

Humans in the loop miss a third of dangerous AI coding agent requests

08.06

A browser-based game designed to test humans' ability to safely approve AI coding agent requests suggests humans in the loop aren't as good at spotting dangerous commands as one might hope, with…

Agents & vibe coding ai and ml

Read at The Register AI ↗

One letter a week, starting soon.

Latest

Humans in the loop miss a third of dangerous AI coding agent requests

Related

VoicesModels, Harnesses, and Multi-Agent Systems Practical AI

VoicesThe Terminal as an Agentic Interface Software Engineering Daily

VoicesAI agents can't yet do open-ended AI research AI Snake Oil

ToolsGoogle Workspace Plugins Cursor Changelog

ToolsAre Supabase docs agent-friendly? We didn't know, so we checked Supabase Blog

VoicesReconstructing how OpenAI agents attacked Hugging Face Practical AI