About Me

I'm an assistant professor at TTIC. Previously, I was a faculty fellow at NYU CDS. Before that, I received my PhD from Berkeley EECS, where I was part of the Berkeley NLP Group and advised by Dan Klein. I completed my undergrad at Brown University, where I majored in math and linguistics and was advised by Ellie Pavlick.

Research

I study language and multi-agent interaction. My primary research discipline is natural language processing, but these days I am broadly interested in improving the capabilities and safety of future AI systems.

Recently, I've been thinking about:

• Training models that are optimized to collaborate with humans
• Explaining superhuman AI behavior in a human-interpretable way
• Mitigating reward hacking and deceptive behaviors in LLM training

I'm also interested in computational cognitive science, linguistics, reinforcement learning, human-computer interaction, and AI safety. For a better sense of my current or past research, check out my papers.

Lab

I run a research lab at TTIC focused on natural language processing, interaction, and reinforcement learning. To learn more about my group and current students, please check out my group page or my guidelines for prospective students.