princi/pal

a moral dilemma tamagotchi

NeurIPS Creative AI 2025

princi/pal explores the anxiety of raising a responsible, good-natured child, with an AI twist. Based in a Tamagotchi-like virtual pet game, the pet in princi/pal grows based on the player's guidance on moral dilemmas. Scenarios can range from "Should I pick up trash?" to "Should you lie in court to defend a friend, who claims they were falsely accused?".

Players articulate their reasoning in natural language, which the system "internalizes" to update the pet's personality and moral stats. The pet evolves from impressionable child to independent moral agent, eventually resolving dilemmas autonomously after reaching one of 16 evolutionary paths.

Public deployment collected 80k+ moral reasoning inputs, revealing how AI systems (mis-)interpret human values. Released a filtered moral reasoning dataset for publication with NeurIPS 2025.

Sixteen evolutionary paths, from stage-one pets to stage-two forms

System design

The system uses gpt-4o-mini to internalize the player's moral reasoning, update the pet's personality and moral stats, and generate questions or overrides after maturity.

System diagram: a dilemma and the player's advice go to an LLM, which updates the pet's personality, morals, and evolution

Citation

@inproceedings{wang2025principal,
  title={princi/pal: A Moral Dilemma Tamagotchi Game},
  author={Wang, Tiffany},
  booktitle={Proceedings of the Thirty-Ninth Conference on Neural Information Processing Systems, Creative AI Track},
  year={2025},
  url={https://openreview.net/pdf?id=ElaELqeFt8}
}