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

AI Alignment ForumResearch

Automating subtle emergent misalignment research

11.03

Authors: Oscar Balcells Obeso, Richard Qi, Monte MacDiarmid, Evan Hubinger Abstract Red-teaming by humans is a vital part of model safety testing, but it may struggle to keep up as models improve.

Research

Read at AI Alignment Forum ↗

One letter a week, starting soon.

Latest

Automating subtle emergent misalignment research

Related

ResearchMonitorability evaluations and policy proposals AI Alignment Forum

ResearchThe Alignment Problem: Computer Science Meets Analytic Philosophy AI Alignment Forum

GitHubPresentation: Beyond the Harness: Canvas for AI Agents InfoQ AI

ValleyEnterprise architecture: Dell and Microsoft integrate hybrid AI SiliconANGLE

LabsTransformers Model Integration Contracts Hugging Face Blog

LabsBuild efficient agents with knowledge distillation on Amazon SageMaker AI AWS Machine Learning