What’s Inside a Generative Artificial-Intelligence Model? And Why Should We Care?

A presentation from 2023–2024 Sally Starling Seaver Professor Fernanda Viégas

During her fellowship, Viégas is excited to explore new modes of human/AI interaction that draw from her roots in data visualization and human-computer interaction. She is interested in the possibility of leveraging advances in AI interpretability (usually aimed at experts) to help drive improvements in lay user agency and control of AI systems. She looks forward to working with colleagues from various departments at Harvard to uncover creative and useful ways of empowering a wide range of users.

A Dashboard for Artificial Intelligence (Harvard Magazine, 11/9/23)

Harvard Computer Science Professor Fernanda Viégas Addresses AI Bias in Radcliffe Institute Talk (Harvard Crimson, 11/9/23)

Event Video