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

OpenAI NewsLabs

How we detect frontier model misalignment

10.29

OpenAI uses layered monitoring to detect frontier model misalignment and unauthorized agent behavior so responders can intervene before incidents escalate.

Models & releases Research

Read at OpenAI News ↗

One letter a week, starting soon.

Latest

How we detect frontier model misalignment

Related

LabsGemini Robotics Embodied Reasoning 2 is now available on Google Cloud Google Cloud AI

VoicesBuilding Reasoning Models from the Ground Up: A Full Video Course Ahead of AI

LabsGemini 4 Argon for Robotics Google DeepMind

VoicesLast Week in AI #345 - 5 new models, 9 misalignment incidents, some Dots Last Week in AI

VoicesClaude’s new auto eval tool Hamel Husain

VoicesGPT-6 Astra, Looped Transformers, and Hidden Reasoning Ahead of AI