Reproduce “Simulating Life Paths with Digital Twins: AI-Generated Future Selves Influence Decision-Making and Expand Human Choice” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Rachel Poonsiriwong, Chayapatr Archiwaranguprok, Constanze Albrecht, Peggy Yin, Nattavudh Powdthavee, Hal Hershfield, Monchai Lertsutthiwong, Kavin Winson and 1 more
The system lets young adults explore consequential choices by conversing with personalized simulations of themselves 30 years older, each imagining a different path, and can generate a value-linked third option. In a randomized study of 192 US adults aged 18–28, 20.0% offered three avatars chose that option, versus 2.7% in guided imagination (p = 0.019); this measured immediate stated choices, not follow-through.
Key insights
- AI-generated future selves can exert directional persuasive influence, with single-sided presentations doubling the likelihood of decision shifts towards the presented option.
- The AI system effectively expands human choice architecture by introducing novel alternatives, with participants selecting system-generated 'Option C' at a rate over seven times higher than control.
- For high-stakes decisions, users prioritize cognitive (evaluative vividness) and meaning-making (eudaimonic vividness) aspects of future self simulations significantly more than emotional connection (affective vividness) or visual realism.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.