AINeutralarXiv – CS AI · May 286/10
🧠
In Search of the Ingredients of Open-Endedness: Replicating Picbreeder with Large Vision-Language Models
Researchers replicated Picbreeder, a landmark human-driven collaborative art generation platform, by substituting Vision Language Models for human users to test whether AI agents can engage in open-ended creative discovery. The study reveals qualitative differences between AI-generated outputs and historical human baselines, with findings suggesting that factors like exploratory noise, behavioral diversity, and memory mechanisms significantly influence AI creative capacity.
