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

Amazon ScienceResearch

Why don’t machine learning research agents overfit?

09.10

Machine learning, at its core, is about generalization, not memorization. You hand your learning algorithm a pile of training examples and use them to fit a model.

Agents & vibe coding

Read at Amazon Science ↗

One letter a week, starting soon.

Latest

Why don’t machine learning research agents overfit?

Related

ResearchSOP-Bench: A new benchmark for evaluating AI agents on real business procedures Amazon Science

ResearchA new benchmark for evaluating patient-facing health AI agents Amazon Science

ResearchCapturing token IDs during agentic interactions for better reinforcement learning Amazon Science

ResearchReal-world grounding in agentic AI Amazon Science

VoicesComputer-Use Agents and the Future of the Agentic Internet Practical AI

ToolsCursor Projects Cursor Changelog