
Jiayi Weng
@trinkle23897
Research Engineer @openai
ID: 2593208798
https://trinkle23897.github.io/cv 28-06-2014 14:53:28
7 Tweet
430 Followers
106 Following




Harmony format is finally open-sourced. I still remember 3 years ago (before ChatGPT release) Shengjia Zhao, Daniel and I were brainstorming about the right abstraction for RL training, and that is the start point of the entire harmony library. github.com/openai/harmony

As GPT-5 launches today, it's hard to forget the first ChatGPT-4 model called 0915-gpt4 internally at 2022. Shengjia Zhao did RM, I did PPO and deployed it that Friday for John Schulman to test. First prompt was tic-tac-toe, and it played surprisingly well. Time flies!