I’m a research scientist and co-founder of OpenAI. I co-lead the post-training team, where we fine-tune the models that get deployed in ChatGPT and the OpenAI API. Besides developing the models that power these products, my interests include:

• The science of language model alignment (2023 Berkeley talk on truthfulness, 2023 ICML talk on proxy objectives)
• Advancing our thinking about how models should behave and increasing transparency with the public (see the Model Spec)

Previously, I received my PhD in Computer Science from UC Berkeley, where I had the good fortune of being advised by Pieter Abbeel where I worked on robotics and reinforcement learning. Before that, I did a brief stint in neuroscience at Berkeley, and before that, I studied physics at Caltech.

• Blog
• Publications
• Presentations
• Code
• Awards