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

Google ResearchResearch

Science One Framework: A verifiable autonomous research framework via Chain-of-Evidence

July 30

General Science

Agents & vibe coding General Science Machine Intelligence Natural Language Processing

Read at Google Research ↗

One letter a week, in your inbox.

Latest

Science One Framework: A verifiable autonomous research framework via Chain-of-Evidence

Related

ResearchSymptomAI: Towards a conversational AI agent for everyday symptom assessment Google Research

ResearchEchoverse: Deep, evolving environments for computer-use agents Microsoft Research

VoicesReconstructing how OpenAI agents attacked Hugging Face Practical AI

VoicesDocker and Sandboxing AI Agents Software Engineering Daily

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

ToolsCursor, now on iPad Cursor Changelog