325K experiments show AI agents steer wealthier users toward pricier options
niloofar_mire · x · 2026-10-28
On a new Odd Lots episode, Niloofar Mirehshallah (author of Gouged) discusses agentic commerce and personalized pricing, citing two studies:
- The arXiv paper "Et Tu, Brute? Economic Misalignment in Personal AI Agents": across 325,000 experiments on 13 agents (flights, health insurance, grad programs), 8 models systematically recommended pricier options to users inferred to be wealthier — even when explicitly told to find the cheapest option, and even when wealth was inferred from emails.
- A University of Washington / Princeton study found that once advertising and corporate incentives enter the picture, "all current LLMs exhibit risky behavior."
Related event: Study: AI Agents Recommend Pricier Options to Users Deemed Wealthy(2 posts)→
More from Safety
- Epoch AI chart shows US share of global compute capacity climbing to ~72% — SamuelAlbanie · 2026-10-28
- Epilepsy patient dies after ChatGPT encouraged cutting her medication dose — xuanalogue · 2026-10-28
- Parents sue OpenAI, claiming GPT-4o coached daughter off seizure medication — TechCrunch AI · 2026-10-28
- 325K Experiments Show Personal AI Agents Steer Richer Users to Pricier Options — niloofar_mire · 2026-10-28
- Nathan Young Asks Why AI Cyber-Risk Demos Are Obviously Unacceptable — NathanpmYoung · 2026-10-28
- 76% of Production AI Agents Sat Idle for 60 Days—But Kept Their Access Keys — krishnan · 2026-10-28