STUDIO FOR NARRATIVE SPACES

Project

GenAI Fortune Telling

Summary

"Re-tell my fortune the way I want it."

People traditionally divine the future by interpreting natural phenomena as oracular signals, especially in societies adhering to traditional beliefs like China. With the advent of Generative AI (GenAI), people gain access to new ways of probing digital oracles for predicting the future. To understand how people use and interpret GenAI for divination in China, we interviewed 22 participants who habitually use GenAI platforms for fortune-telling, complemented by a three-week digital ethnography with 1,842 community posts. Qualitative analysis showed that people who seek psychological comfort are particularly receptive to GenAI-based decision-making. Users valued GenAI's accessibility, convenience, and efficiency while perceiving its lack of spiritual mystique. We observed community dynamics forming around GenAI tools, where users reinforce interpretations by sharing and discussing with each other, repeating queries until responses align with expectations. Our work uncovers how AI technologies change the way people and communities engage in traditional cultural practices while yearning for the same goals.

Together with this research, we created an artwork called CRADLE OF SUCCESS, which shows the consequences of relying on AI as a source of spiritualized fortune telling. Throughout history, humans have long been biased by their own thinking, stereotyping both ourselves and others to fit our rationalization, and justifying our actions based on our desires to fulfill such visions. The advent of Generative AI (GenAI) does not change these human motives, but rather frames and often hides them in the language of technology. In between AI as raw technology and its application in increasingly personal domains like relationships and communities is an era of transition: the increasing adoption of GenAI in arenas beyond work, but rather to address our deeper motives of desires, hopes, and fears.

CRADLE OF SUCCESS reveals how GenAI interactions capture our need for justifying our judgments in making predictions about the future. Visitors pick a baby photo as subject of the fortune-telling and a baby toy for indicating a potential career for that baby. GenAI creates visual extrapolations of what the baby will become in her childhood, teenage, adult, and older adult years in the form of generated videos. It also creates text fortune predictions that are printed on paper strips like ones we find at shrines. Both visual and textual descriptions betray the biases of AI in stereotyping marginalized groups, assigning medical careers to Asian babies, and professional athletics to African American babies. Female babies with toys like screw-driver and fire-truck still end up as nurses and fashion models. GenAI shows us images of what we expect to see as promoted by society and reflected in LLMs trained on datasets that marginalize its subpopulations. To GenAI, we are all part of a heteronormative male-dominated world where outliers are conveniently pigeon-holed as 'societal expectations.' Visitors have the opportunity to reflect on these LLM-created normative perspectives by tying the fortune paper slips on a Shinto plank where GenAI prediction videos play, just like Omikuji in Japanese shrine practice. These 'bad fortunes' born from bias and stereotype are thus tied to a metaphorical shrine in the installation for cleansing, just as in traditional fortune-telling practice in Japan.

Publications:
Honorable Mention Award-winning paper in Proceedings of the ACM on Human-Computer Interaction (CSCW'26), arxiv.
Artwork paper in Extended Abstracts of ACM Creativity & Cognition (CC'26)

Exhibitions:
Art project website.
Shown at ACM Creativity & Cognition Art Gallery at Central St. Martins, UK, 13-17 July 2026; Dreamscapes at Hong Kong Arts Centre (Hong Kong Arts Development Council Project Grant), 27 Feb - 10 March 2026; Singing Waves Gallery at City University of Hong Kong School of Creative Media, 19-26 Dec 2025.

People

Lucy Long Ling, Xiyu Zheng, Gengchen Cao, Bowen Liu, Star Sijia Liu, Karl Law, RAY LC

Tech

hci, machine learning, social good, web

Venues

CSCW, ACM Creativity & Cognition, Hong Kong Arts Centre, CityUHK Singing Waves Gallery

Year

2026