AI & ML Paradigm Challenge

An AI can mimic your personality perfectly and still have absolutely no clue how to actually convince you to change your mind about something.

April 6, 2026

Original Paper

When simulations look right but causal effects go wrong: Large language models as behavioral simulators

Zonghan Li, Feng Ji

arXiv · 2604.02458

AI-generated illustration

The Takeaway

While AI can act as a realistic 'digital twin' of a person, researchers found these simulations fail at predicting how people react to new policies or interventions. This means a model can look human on the surface while remaining a terrible guide for real-world social change.

From the abstract

Behavioral simulation is increasingly used to anticipate responses to interventions. Large language models (LLMs) enable researchers to specify population characteristics and intervention context in natural language, but it remains unclear to what extent LLMs can use these inputs to infer intervention effects. We evaluated three LLMs on 11 climate-psychology interventions using a dataset of 59,508 participants from 62 countries, and replicated the main analysis in two additional datasets (12 and