Reproduce “An Experimental Method to Study Opinion Diffusion in Human-AI Hybrid Societies” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Léna Gaubert, Rémi Devaux, Elif Çelen, Raja Marjieh, Diana Mangalagiu, Antoine Jardin, Nori Jacoby
The authors test a method for measuring how opinions change as people and AI agents revise statements in a network. They revised neighbors’ statements on red meat and health. After eight rounds, the single hybrid network showed lower opinion variation and higher neighbor alignment than the single human-only network; each ran once, so this does not establish a general effect.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.