Mimetic Models: Ethical Implications of AI that Acts Like You

  title={Mimetic Models: Ethical Implications of AI that Acts Like You},
  author={Reid McIlroy-Young and Jon M. Kleinberg and Siddhartha Sen and Solon Barocas and Ashton Anderson},
  journal={Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society},
An emerging theme in artificial intelligence research is the creation of models to simulate the decisions and behavior of specific people, in domains including game-playing, text generation, and artistic expression. These models go beyond earlier approaches in the way they are tailored to individuals, and the way they are designed for interaction rather than simply the reproduction of fixed, pre-computed behaviors. We refer to these as mimetic models, and in this paper we develop a framework… 

Learning Models of Individual Behavior in Chess

This work demonstrates a way to bring AI systems into better alignment with the behavior of individual people, which could lead to large improvements in human-AI interaction.



Aligning Superhuman AI with Human Behavior: Chess as a Model System

Maia is developed and introduced, a customized version of AlphaZero trained on human chess games, that predicts human moves at a much higher accuracy than existing engines, and can achieve maximum accuracy when predicting decisions made by players at a specific skill level in a tuneable way.

Implicit Communication of Actionable Information in Human-AI teams

In a user study with 904 completed games and 246 completed surveys, human players randomly paired with an implicature AI are 71% more likely to think their partner is human than players paired with a non-implicatureAI.

Fairness and Abstraction in Sociotechnical Systems

This paper outlines this mismatch with five "traps" that fair-ML work can fall into even as it attempts to be more context-aware in comparison to traditional data science and suggests ways in which technical designers can mitigate the traps through a refocusing of design in terms of process rather than solutions.

Your Gameplay Says It All: Modelling Motivation in Tom Clancy’s The Division

It is suggested that gameplay features are strong predictors of player motivation as the best obtained models reach accuracies of near certainty, from 92% up to 94% on unseen players.

Avatar Ethics: Beyond Images and Signs

Emmanuel Levinas argues that moral responsibility is enacted in the encounter between two people. Increasingly, however, encounters take place online and, rather than between two people, are mediated

Algorithmic Fairness from a Non-ideal Perspective

A connection is demonstrated between the recent literature on fair machine learning and the ideal approach in political philosophy, and it is shown that some recently uncovered shortcomings in proposed algorithms reflect broader troubles faced by the Ideal approach.

Modeling Strong and Human-Like Gameplay with KL-Regularized Search

This work introduces a novel regret minimization algorithm that is regularized based on the KL divergence from an imitation-learned policy, and shows that using this algorithm for search in no-press Diplomacy yields a policy that matches the human prediction accuracy of imitation learning while being substantially stronger.

Fairness in Machine Learning

It is shown how causal Bayesian networks can play an important role to reason about and deal with fairness, especially in complex unfairness scenarios, and how optimal transport theory can be leveraged to develop methods that impose constraints on the full shapes of distributions corresponding to different sensitive attributes.

The Proteus Effect

Together, these two studies show that their virtual bodies can change how the authors interact with others in actual avatar-based online communities as well as in subsequent face-to-face interactions.

Friend, Collaborator, Student, Manager: How Design of an AI-Driven Game Level Editor Affects Creators

The design of the Morai Maker intelligent tool is discussed, which developed a game level design tool for Super Mario Bros.-style games with a built-in AI level designer and found that level designers vary in their desired interactions with, and role of, the AI.