Welcome to my blog
January 15, 2026 中文版 →This is where I will occasionally write down thoughts from my day-to-day work on large language model training and agent building — things like RL for reasoning and code, harness design, auto research, and the occasional note from AI for scientific computing.
Posts will be short and practical: problems I ran into, ideas that worked (or didn’t), and rough intuitions I want to remember. More coming soon.