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

Why I'm scared of RL

September 23

Summary: First, I give several different angles on how I feel about reinforcement learning: Theoretical case: RL is a black-box source of agency — this should give us classic misalignment worries…

Research

Read at AI Alignment Forum ↗

One letter a week, in your inbox.

Latest

Why I'm scared of RL

Related

ResearchCoT controllability evals seem very under-elicited AI Alignment Forum

ResearchProposal for tracking the effects of architecture on monitorability AI Alignment Forum

AsiaDeepSeek details DSec sandbox infrastructure for agent training TechNode

SiliconImproving Quantum Error Correction By Meshing Surface Code With IBM’s Heavy-Hex Architecture The Next Platform

GitHubGPT-6 Sol closes most of the alignment gap with Astra. It’s one-fifth the price. The New Stack

LabsEvaluate skill-equipped agents with Strands Evals and Amazon Bedrock AgentCore AWS Machine Learning