Revealing Life Preferences Through LLMs

·Marginal Revolution··

Here is some Weberian verstehen (or is it?), but from unexpected quarters: 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 life stories and ask them to choose the life they would prefer for themselves. A person’s choice is better predicted by the LLM’s c...

Read full article →

Related Articles

UK Fuel Price Intelligence – Market analytics from reporting stations
theazureguy · Hacker News · 6mo ago
Show HN: The bottom 50% of U.S. households are short after essentials (BLS data)
pwmglenn · Hacker News · 2mo ago
Character.ai's Bankruptcy Documents Show the Economics of AI Don't Work
Luc · Hacker News · 1mo ago
Microsoft filings suggest "around 70%" of its AI revenue is on OpenAI
speckx · Hacker News · 3mo ago
The iPhone explains 33–52% of fertility decline among women aged 15–44
delichon · Hacker News · 5mo ago