BKC Spring Speaker Series Event
When you talk with a chatbot, what does it “think” about you? Recent work in AI interpretability, based on high-dimensional geometry, is beginning to provide some intriguing answers. In this talk Fernanda Viégas and Martin Wattenberg describe an interface that translates the complicated geometry of an AI language model into a simple, understandable dashboard. This dashboard allows end-users to see—and control—how a chatbot perceives them.
The speakers argue that this type of transparency can help people work with AI more effectively, safely, and enjoyably.
Speakers
Fernanda Viégas and Martin Wattenberg are Gordon McKay Professors of Computer Science at Harvard, where Fernanda is also Sally Starling Seaver Professor at the Radcliffe Institute for Advanced Study. Viégas and Wattenberg are also Principal Scientists at Google, where they co-founded the PAIR (People+AI Research) initiative. Their work in artificial intelligence focuses on transparency and interpretability, as part of a broad agenda to improve human/AI interaction. They are well known for their contributions to social and collaborative visualization, and the systems they’ve created are used daily by millions of people. Viégas and Wattenberg are also known for visualization-based artwork, which has been exhibited in venues such as the Museum of Modern Art in New York, London Institute of Contemporary Arts and the Whitney Museum of American Art.
