Tweet by Rohan Paul:

Ilya Sutskever was a co-author of this Paper.

Helps to put some light on how the latest o1 🍓 Model from @OpenAI works. Paper from May, 2023

**Key Insights from this Paper** 💡:

👉 To train more reliable models, we can turn either to outcome supervision, which provides… pic.twitter.com/nSpZrNnVKY