Eugene Yan

5 stories

Eugene YanVoicesPatterns for Building Cybersecurity Evals A sandboxed target, inputs that influence task difficulty, tools, and a grader.

06.21

Eugene Yan

Eugene YanVoicesUsing LLMs to Secure Source Code Build a threat model, discover vulnerabilities, verify, triage, and patch.

05.27

Eugene YanVoicesHow to Work and Compound with AI Context as infra, taste as config, verification for autonomy, scale via delegation, closing the loop.

05.03

Eugene YanVoices2025 Year in Review An eventful year of progress in health and career, while making time for travel and reflection.

2025.12.14

Eugene YanVoicesProduct Evals in Three Simple Steps Label some data, align LLM-evaluators, and run the eval harness with each change.

2025.11.23

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