Legible Normativity for AI Alignment: The Value of Silly Rules

@article{HadfieldMenell2019LegibleNF,
  title={Legible Normativity for AI Alignment: The Value of Silly Rules},
  author={Dylan Hadfield-Menell and McKane Andrus and Gillian K. Hadfield},
  journal={Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society},
  year={2019}
}
It has become commonplace to assert that autonomous agents will have to be built to follow human rules of behavior--social norms and laws. But human laws and norms are complex and culturally varied systems; in many cases agents will have to learn the rules. This requires autonomous agents to have models of how human rule systems work so that they can make reliable predictions about rules. In this paper we contribute to the building of such models by analyzing an overlooked distinction between… Expand

References

Ontology of the self and material culture: Arrow-making among the awÃą hunter
  • Journal of Anthropological Archaeology
  • 2011