My research brings together social sciences and machine learning to develop the best AI for humans. The applications that I am most interested in are 1) scientific discoveries, 2) healthcare, and 3) governance and democratic processes (ordered by random coin flips).
The central question of my current interest lies in how we can build an effective communication protocol between humans and AI. Here are some example problems that I think will contribute to this question:
Specification: How can we help AI understand human goals and help humans specify their goals? Prompting and reinforcement learning from human feedback are the main paradigms right now, but what about goals that cannot be easily described or elicited through human preferences? Examples include data-driven hypothesis generation and decision-focused summarization.
Complementary AI: How can we develop AI that accounts for human intuitions/biases and complement human intelligence/enable humans to supervise powerful AI that outperforms humans (“scalable oversight”)? This requires us to model human intuitions/biases and address them constructively. We have done some prior work on the important role of human similarity judgments in case-based explanations and generally machine explanations. But we will need fundamental breakthroughs in behavioral sciences, which in turn inform AI modeling/inference.
Interpretability: How can we make sense of (powerful) AI that is much better than humans? I am most interested in interpretability for expanding human knowledge (e.g., in scientific discoveries) and for improving the controllability of AI. It is important to explore opportunities in the absence of identifiability.
In general, goals matter more to me than the specific problem or method. If you are interested in seeing how my research description has evolved, you can check this page.
the Data Science Instituite Postdoctoral program (If you applied to the DSI postdoc program and mentioned me as an advisor, please send me an email because I can potentially support you with my own funding).
I also have a postdoc opening on novel intelligence that can start any time. Please email me your CV and names of references. I am particularly open to students who have background in medicine and policy (e.g., MD/PhD and PhD students in economics).
I am always looking for motivated masters and undergraduate students who are interested in
Human-centered AI, Communication & Intelligence, AI & Scientific Discovery, and AI alignment.
Please read this FAQ before contacting me.
