How do AI chatbots see us? (BKC Speaker Series)

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. Join an interactive workshop for those interested in the ethics and future of chatbots.

Lunch will be served!