How Strong Is the Evidence for the Artificial Hivemind? Reevaluating Evidence for the Open-Ended Homogeneity of Language Models
The paper concludes that inference-time interventions are inadequate for combating the Artificial Hivemind, and shows that more generalizable solutions are needed at the model training level, and that an inference-time intervention (prompting) reliably raises measured response diversity.
Rylan Schaeffer, Brando Miranda, Joshua Kazdan et al.
· 0 citations