Reproduce “Aggregated knowledge from a small number of debates outperforms the wisdom of large crowds” 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

Joaquin Navajas, Tamara Niella, Gerry Garbulsky, Bahador Bahrami, Mariano Sigman

The authors test whether small-group discussion can improve crowd estimates of general-knowledge quantities. At a live Buenos Aires event, five players discussed some questions and produced one consensus estimate, which was pooled across groups. Four group estimates had 49.2% less error than averaging the 1,400 initial estimates from complete groups; the finding concerns accuracy, not time or cost.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.