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

Latent reasoning architectures would undermine CoT, our strongest oversight tool

September 23

Summary: Currently, “chain of thought” (CoT) is our most valuable tool for understanding the reasoning and cognition of AI systems.

Research

Read at AI Alignment Forum ↗

One letter a week, in your inbox.

Latest

Latent reasoning architectures would undermine CoT, our strongest oversight tool

Related

ResearchWhy I'm scared of RL AI Alignment Forum

ResearchWorkspaceBench: Evaluating Interpretability Methods for the Global Workspace AI Alignment Forum

ResearchCoT controllability evals seem very under-elicited AI Alignment Forum

SiliconHow SWE-Serve Exposes the Gap Between Local Tests and Live Serving NVIDIA Technical Blog

GitHubPresentation: APIs for Agents: Rethinking API Programs in the MCP Era InfoQ AI

AsiaDeepSeek details DSec sandbox infrastructure for agent training TechNode