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

Phil SchmidVoices

Practical Guide to Evaluating and Testing Agent Skills

03.04

Learn how to systematically test and improve agent skills using deterministic checks and a real-world Gemini API example.

Agents & vibe coding MCP, skills & tools Research

Read at Phil Schmid ↗

One letter a week, starting soon.

Latest

Practical Guide to Evaluating and Testing Agent Skills

Related

VoicesEvals Skills for Coding Agents Hamel Husain

VoicesNew Paper: Towards a science of AI agent reliability AI Snake Oil

Voices#490 – State of AI in 2026: LLMs, Coding, Scaling Laws, China, Agents, GPUs, AGI Lex Fridman Podcast

VoicesWriting a Good AGENTS.md Phil Schmid

VoicesOpus 4.5 changed everything (Interview) Changelog

VoicesA Dream of Spring for Open-Weight LLMs: 10 Architectures from Jan-Feb 2026 Ahead of AI