About Prompt Prototyping

This talk considers how large language models (LLMs) can be employed as an HCI prototyping medium, in ways similar in spirit to paper prototyping. Seen in this light, Michael Terry will: 1) present a basic design space to situate LLMs as a prototyping material, 2) share results of a case study showing how LLMs affect AI prototyping practices (including social dynamics), and 3) enumerate a few design patterns for enriching the AI prototyper’s palette (decomposition, the switchboard, and “phone a friend”).

About the Speaker

Michael Terry is a Research Scientist at Google, where he co-leads the People and AI Research (PAIR) group. His research is situated in the realm of human-AI interaction (HAI), with a particular focus on enabling rapid prototyping with AI. He was previously an Associate Professor at the University of Waterloo.

About Designing Human-AI Systems for Creativity and Beyond

Designing Human-AI Systems for Creativity and Beyond invites you to engage in the promise and perils of the next big thing in machine intelligence. We invite speakers from the worlds of art, design, technology and policy to discuss these impressive new capabilities, its limitations and how we, as designers and students, could harness it to reach new heights in art, music, dance, architecture, fashion, creative writing and programming.