AI Seminar: Designing Interactive AI for Writers

Image
Placeholder for images.
Event Speaker
Ken Arnold, Assistant Professor
Calvin University
Event Type
Artificial Intelligence
Date
Event Location
CRPS 122
Event Description

When AI systems (Gmail, ChatGPT, etc.) suggest words, writers frequently appropriate them as their own. Although this interaction can help writers, it also threatens accuracy, usefulness, and even integrity. I will show empirical results from controlled studies that found that predictive text systems nudge writers to conform both their writing and their opinions to the system’s suggestions. Since I conjecture that these threats are inherent to autocomplete-style predictive interactions, I ask: can large language models help writers without casting doubt on their authorship? I will show prototypes that explore intelligence-augmentation approaches for structuring and revising documents. I hope to spark conversation about what visions and values might shape how we design interactions with emerging AI systems.

Speaker Biography

Ken Arnold (B.S., Cornell; M.S., MIT; Ph.D., Harvard) is an assistant professor of computer science and data science at Calvin University. His research has shown how predictive text interfaces, like those in smartphone keyboards and email apps, can shape the content of what people communicate. He is currently working on intelligence augmentation to help writers craft words that are fully their own. His current research interests include human-AI interaction in communication, creativity, and education.