Register and share your invite link to earn from video plays and referrals.

Jiayi Weng
@Trinkle23897
MTS @openai, author of the entire post-training RL infra, core contributor of ChatGPT/GPT4/GPT4o etc. 30U30
177 Following    11.7K Followers
One small subset for ImageNet, one giant leap for Heuristic Learning. A clean dunk on my “pure-code HL hits ImageNet wall” take. This isn’t “no learning.” It’s learning where the representation lives in code instead of weights.
Show more
Codex iterated a pure NumPy + cv2 closed-loop heuristic policy for VizDoom D3 Battle. No neural network training, no map, no object coordinates, no seed-specific routes. Just screen pixels plus public game variables, roughly the same signals a human player gets. It works surprisingly well. Notes and videos are now in the blog:
Show more
Codex grew programmatic policies with no neural nets: max score on Breakout, and SOTA-level scores on MuJoCo. Maybe heuristics were not too weak. Maybe they were just too expensive to maintain. Maybe it's the next paradigm.
Show more
Codex grew programmatic policies with no neural nets: max score on Breakout, and SOTA-level scores on MuJoCo. Maybe heuristics were not too weak. Maybe they were just too expensive to maintain. Maybe it's the next paradigm.
Show more
0
59
1.4K
230
Forward to community
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 @johnschulman2 to test. First prompt was tic-tac-toe, and it played surprisingly well. Time flies!
Show more
GPT-5 is here. Rolling out to everyone starting today.
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.
Show more
0
34
1.5K
151
Forward to community
Finally... OAI internally talked about releasing open-source model since 2022 and we got close a few times since then. Now it is.
Our open models are here. Both of them.
Alignment has been achieved internally
About 650 / 770 signed at this moment. As people start waking up, more will come. All the efforts started after 1:30 AM, 500+ within two hours and all of this after 2 crazy days with very little sleep.
Show more
OpenAI is nothing without its people
Hello Twitter! I wrote a ChatGPT app to help remote teams stay in the loop. Basically it will summarize your team’s GitHub activities and send them to Slack. Check it out! (First 100 sign-ups will get 1-year free trial) #ChatGPT# #AI# #OpenAI# #remotework#
Show more