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

What Kubernetes’ “monolith” lesson means for AI agent harnesses

October 2

Welcome to another edition of Road to KubeCon , your source for everything Kubernetes and cloud-native as we count down the days to KubeCon + CloudNativeCon NA , happening November 9-12 in Salt Lake…

Agents & vibe coding

Read at The New Stack ↗

GitHub“No reason why everyone should have an identical Claude experience”: Anthropic’s mods let you change Claude Code’s look and behavior The New Stack

One letter a week, in your inbox.

Latest

What Kubernetes’ “monolith” lesson means for AI agent harnesses

Related

GitHub“No reason why everyone should have an identical Claude experience”: Anthropic’s mods let you change Claude Code’s look and behavior The New Stack

GitHubOpenAI’s always-on agents are free, until one specific thing happens The New Stack

GitHubCloudflare brings paid access to MCP tools — who controls the agent’s spending? The New Stack

GitHub“No human wants to look at billions of traces”: Dynatrace bought Arize because agents need a new kind of observability The New Stack

GitHubAI coding agents leaked 13,000 screenshots, and nobody hacked them. The New Stack

GitHubAI agents speed up development — data access slows them down The New Stack