Princeton CS 2027
Diversity of Generation in LLMs, Pluralistic Alignment, RL, Augmented LLMs
Research @
Reinforcement Learning Lab
Let’s talk about research or ideas for making adaptive intelligent systems that align with humanity. I also create art and write humor focused on the tech world, AI, and the tension between humans and machines.
Two people communicate without words just with their hand gestures without seeing each other. They can only control volume and intensity of sound that can move toward harmony or confrontation, accompanied by a changing sound landscape and visuals of the tones.
Visitors begin with control over digital avatars and gradually lose that control. The familiar assumption that an interface faithfully obeys its user begins to break down.
The viewer initially controls the image through mouse movement, creating the expectation that the system will respond predictably. Gradually, that relationship breaks down. The image begins to distort and move independently until the viewer loses agency over it.
I created large-scale projections that transform the wooden interior of Genomics Café and the facade of Princeton University's Robertson Hall into ephemeral digital canvases, exploring AI-generated identities and virtual avatars.