References

Re-examining whether, why, and how human-AI interaction is uniquely difficult to design

Qian Yang, Aaron Steinfeld, Carolyn Rosé, & John Zimmerman (2020)

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI '20), 1-13.

DOI: https://doi.org/10.1145/3313831.3376301

Abstract. The reference paper analysing what makes AI products harder to design than conventional software: the AI's behaviour is probabilistic and shifting, capabilities are unclear to users, output is partially generative, and feedback loops are hard to engineer. Required reading for any team designing LLM-powered features.

Tags: ai-usability design-research methodology

This site is currently in Beta. Contact: Chris Paton

Textbook of AI · Textbook of Digital Health

Auckland Maths and Science Tutoring