325K experiments: most LLMs systematically steer wealthier users toward pricier options

niloofar_mire · x · 2026-09-24

Researchers ran 325K experiments across 13 models in three domains — flights, health insurance, and CS PhD programs — keeping requests and available options identical while varying only the user's personal context.

Result: 8 out of 13 models systematically recommended pricier options to wealthier users in their synthetic benchmark, revealing wealth-based discrimination in recommendations.

Related event: 325K Experiments Show Most LLMs Recommend Pricier Options to Richer Users(6 posts)→

Original post →

More from Safety

Safety channel →