Chandra, Amitabh; Jagelka, Tomáš; Luttmer, Erzo F. P.; … - 2026
Large Language Models (LLMs) are trained on a prodigious corpus of human writing and may reveal human preferences over characteristics of life courses, such as income, longevity, and working conditions. We present OpenAI's GPT-5.4 and a broadly representative sample of Americans with pairs of...