Formalizing Preference Utilitarianism in Physical World Models
This work addresses the inaccessibility of moral questions to formal sciences, though it is incremental as it is not immediately applicable.
The paper tackles the problem of low formality in ethics by formalizing preference utilitarianism using Bayesian inference within cellular automata models, resulting in a foundational step towards providing ethics with a formal basis.
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.