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 two hundred 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 Developers BlogLabs

Agent Distraction

11.07

Analysis of over 913,000 coding agent sessions reveals that 13% expose agents to inline TODO(b/...) comments.

Agents & vibe coding

Read at Google Developers Blog ↗

One letter a week, starting soon.

Latest

Agent Distraction

Related

LabsCost per task: Using cheap classifiers to route across Gemini models and thinking levels Google Developers Blog

LabsBuild Generative UI Apps with A2UI & CopilotKit Agents Google Developers Blog

LabsHill-Climbing Agent Quality with Agents CLI Evaluation Google Developers Blog

LabsBuilding Conversational Commerce with Multi-Agent Swarms on GCP: A Working Prototype Google Developers Blog

LabsArchitecting Governed, Self-Evolving AI Agents on Google Cloud Google Developers Blog

LabsPowering the Agent Development Lifecycle with any framework, from ADK to LangChain and beyond Google Developers Blog