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

Ai2Labs

What building Shippy taught us about building agents

July 13

Building Shippy taught us that reliable agents depend less on the model itself than on deterministic tools, explicit guardrails, isolated infrastructure, and evaluations grounded in real-world…

Agents & vibe coding

Read at Ai2 ↗

One letter a week, in your inbox.

Latest

What building Shippy taught us about building agents

Related

ResearchCapturing token IDs during agentic interactions for better reinforcement learning Amazon Science

VoicesBuilding Durable AI Agents Practical AI

ToolsAgentic MapReduce Cognition (Devin & Windsurf)

ToolsAgentic Coding on Supabase with OpenCode Supabase Blog

ToolsAgentic Batch Changes is now in public beta Sourcegraph Blog

ToolsCursor Mobile App for iOS Cursor Changelog