The Creative AI-Land: Exploring new forms of creativity

Abstract

This study examines generative artificial intelligences (GAI), as popularised by ChatGPT, in standardised creativity tests, uncovering what we called the “creative AI-Land”. As the study of creativity was metaphorically seen as a trip across the seven seas (C’s) by Lubart, we conceptualise AI creativity as uncharted territory in the creativity field. Benchmaking GAI against human performance, results show that ChatGPT demonstrates remarkable fluency in content generation, though the creative output is average. The random nature of AI creativity and the dependency on the richness of the training database require a reassessment of traditional creativity metrics especially for AI. Our findings highlight the integral role humans play in guiding AI to foster genuine originality, suggesting the need for future research in human-AI co-creation and the development of robust AI creativity measurement mechanisms.