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 Cloud AILabs

Introducing Physical-Engineering’s Last Exam for agents

11.03

Authors: Burak Gokturk, VP Research & Development; Rujun Han, Research Scientist; George Lee, Product Manager.

Agents & vibe coding AI & Machine Learning

Read at Google Cloud AI ↗

One letter a week, starting soon.

Latest

Introducing Physical-Engineering’s Last Exam for agents

Related

LabsScale agents securely with IAM Helper Agent Skills and MCP Tools Google Cloud AI

LabsIntroducing Gemini for government services Google Cloud AI

LabsGoogle named a Leader in the 2026 IDC MarketScape for Agentic AI Platforms Google Cloud AI

LabsArchitecting autonomy: A design pattern for high-compute, governed agents in biotech Google Cloud AI

LabsFour evaluation engineering lessons learned from building agent plugins Google Cloud AI

LabsWhat the Gemini agent means for startups Google Cloud AI