Formalizing Preference Utilitarianism in Physical World Models

TL;DR

This paper introduces a formalization of preference utilitarianism within physical world models using Bayesian inference, aiming to bridge ethics with formal scientific frameworks despite current limitations.

Contribution

It presents the first formalization of preference utilitarianism in cellular automata models using Bayesian inference, advancing the integration of ethics into formal scientific models.

Findings

Formalization using Bayesian inference in cellular automata

Provides a foundational step towards formal ethics in physical models

Highlights future potential for practical applications

Abstract

Most ethical work is done at a low level of formality. This makes practical moral questions inaccessible to formal and natural sciences and can lead to misunderstandings in ethical discussion. In this paper, we use Bayesian inference to introduce a formalization of preference utilitarianism in physical world models, specifically cellular automata. Even though our formalization is not immediately applicable, it is a first step in providing ethics and ultimately the question of how to "make the world better" with a formal basis.