Skip to the main content

I am a professor at Harvard, where I co-lead the Insight + Interaction Lab with long-time collaborator Fernanda Viégas. I'm also a part-time member of Google DeepMind's PAIR (People + AI Research) initiative, which she and I co-founded. My work currently focuses on making AI technology broadly accessible and reflective of human values. 

Before focusing on machine learning at Google, I helped create end-user visualizations for products such as Search, YouTube, and Google Analytics. Prior to joining Google, Fernanda and I founded Flowing Media, Inc., a visualization studio focused on media and consumer-oriented projects. Before that, we led IBM’s Visual Communication Lab, which created the ground-breaking public visualization platform Many Eyes. I came to IBM from Dow Jones, where I was the Director of Research and Development at SmartMoney.com. 

My work there included some of the earliest pieces of interactive journalism. I've also created visualization-based artwork, which has been exhibited in venues such as the London Institute of Contemporary Arts, the Whitney Museum of American Art, and the New York Museum of Modern Art. I have a Ph.D. in mathematics from U.C. Berkeley, focusing on dynamical systems.

Publications

Publication
Dec 18, 2025

Inside the Black Box

Inside the Black Box introduces an interpretability dashboard developed by researchers at the Berkman Klein Center for Internet & Society and Harvard’s Insight and Interaction…

Community

Inside the Black Box

New tools reveal how AI models “see” users and raise questions about transparency

Researchers from Harvard’s Insight and Interaction Lab built an interpretability dashboard that shows a chatbot’s internal assumptions about a user — such as age, gender, class,…

Feb 2, 2026

Inside the Black Box

New tools reveal how AI models “see” users and raise questions about transparency

Researchers from Harvard’s Insight and Interaction Lab built an interpretability dashboard that shows a chatbot’s internal assumptions about a user — such as age, gender, class,…

Dec 18, 2025

Events

Event
Mar 5, 2025 @ 12:30 PM

How Do AI Chatbots See Us?

Bringing AI interpretability to end-users through a real-time dashboard

 BKC Spring Speaker Series EventWhen you talk with a chatbot, what does it “think” about you? Recent work in AI interpretability, based on high-dimensional geometry, is…