Dynamics of collective creativity in AI art competitions

TL;DR

This paper investigates how collective creativity unfolds in AI-assisted art competitions, revealing patterns of convergence, user preferences, and the impact of group size on novelty and complexity.

Contribution

It provides the first large-scale analysis of human-AI co-creation dynamics in online art remix communities, highlighting how novelty and thematic convergence evolve.

Findings

Images tend to become simpler and converge on common themes.

More novel parent images generate more novel and complex children.

Users prefer remixing less novel and complex images despite attraction to novelty.

Abstract

Creativity is a fundamental aspect of how culture evolves, yet the mechanisms by which groups produce novelty are notoriously difficult to infer from the historical record. Iterated learning experiments have shown that cultural transmission reliably distorts artifacts toward the inductive biases of learners, but most of this work uses linear chains between human participants, leaving open how these dynamics play out in the networked, human-AI systems that increasingly shape cultural production. In this study, we leverage one such system, Artbreeder, which hosts daily "remix parties" where users iteratively build on each other's work from a single seed image, producing branching lineages of human-AI co-created images. We analyze a dataset of 130,882 images from 368 remix parties over 13 months and find that images become simpler and converge toward common thematic "attractors" (e.g., steampunk scenes, alien architecture). We also find that while more novel "parent" images produce more novel and complex "children" that attract more likes, users paradoxically prefer to remix images that are less novel and complex. Finally, larger remix parties produce more novelty at the cost of lower complexity.