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

The New StackGitHub

The audit log says my name: what an agent inherits when you hand it your credentials

October 8

I measured what an AI agent actually holds when it authenticates as me. Authentication turned out to be a token whose scope string literally says user_impersonation .

Agents & vibe coding

Read at The New Stack ↗

One letter a week, in your inbox.

Latest

The audit log says my name: what an agent inherits when you hand it your credentials

Related

GitHubThe API tax: Why AI agents stall without infrastructure context The New Stack

GitHubBuilding scalable, agent-friendly APIs for AI applications The New Stack

GitHubOpenSearch veterans launch Infino. Here’s why it matters for agent builders. The New Stack

GitHubWhat’s up, Docsy? Google’s docs project joins the Linux Foundation as AI agents become readers The New Stack

GitHubThe CNCF is graduating projects faster than ever. AI agents are helping with the due diligence. The New Stack

GitHubCopilot tops GitHub’s own AI code review benchmark. An independent one tells a different story. The New Stack