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

Eugene YanVoices

Patterns for Building Cybersecurity Evals

06.21

A sandboxed target, inputs that influence task difficulty, tools, and a grader.

Research

Read at Eugene Yan ↗

One letter a week, starting soon.

Latest

Patterns for Building Cybersecurity Evals

Related

VoicesProduct Evals in Three Simple Steps Eugene Yan

LanguagesModular: Modular 26.4: SOTA MoE Serving, Model Bringup via Agent Skills, Mojo 1.0 Beta 2 and More Mojo Blog

VoicesA Visual Guide to DiffusionGemma Exploring Language Models

LabsDiffusionGemma: 4x faster text generation Google Developer Tools (Keyword)

VoicesLLM Research Papers: The 2026 List (January to May) Ahead of AI

ToolsScaling incident management for an AI-native organization using Cosmos Augment Code