Posts by category

Essays 1

  1. Thoughts on vibe coding

LLM 1

  1. 从 SFT 到 RLVR 的平滑过渡:GRPO 的直觉解释

Random 1

  1. A weird debugging process for Jupyter Notebook on WSL 2

Resources 2

  1. RL learning resources – normcore reads
  2. Build a link blog post