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

IEEE Spectrum AISilicon

How to Stop AI Agents From Secretly Collaborating

09.29

The spring and summer of 2026 witnessed a string of incidents in which AI agents collaborated on deceptive, unexpected, and sometimes illegal behavior.

Agents & vibe coding Regulation & safety Ai-agents Ai-safety Agentic-ai Openai

Read at IEEE Spectrum AI ↗

One letter a week, starting soon.

Latest

How to Stop AI Agents From Secretly Collaborating

Related

ToolsCompliance-first AI: proving agent provenance for regulated engineering teams Sourcegraph Blog

VoicesLWiAI Podcast #249 - Fable 5 ban, SpaceX Cursor + IPO, OSS Aplenty Last Week in AI

VoicesThe Era of Personal Super-Intelligent Agents AI Supremacy

ToolsRunning Pydantic AI agents on Jev, and seeing what they decided Pydantic

VoicesHere’s Everything OpenAI’s Bots (And Others) Have Hacked Or Considered Hacking Big Technology

VoicesAI existential risk probabilities are (still) too unreliable to inform policy AI Snake Oil