Design Heuristics for Ethical Online Institutions

Abstract

A major challenge in AI is designing autonomous systems that capture the values of stakeholders, and do so in such away that one can assess the extent to which that system's behaviour is aligned to those values. In this paper we discuss our response to this challenge that is both practical and built on clear principles. Specifically, we propose eleven heuristics to organise the process of making values operational in the design of particular class of AI systems called online institutions. These are governed systems of interacting communities of human and autonomous artificial agents.

Ethical Principles for Reasoning about Value Preferences

“…Motivation. When values are imbued in systems, aggregating values into a single outcome may improve ethical decision making in STS [22]. However, reasoning about values is challenging [17], and stakeholders could have personal preferences between different values [16,21].…”

A computational model of Ostrom's Institutional Analysis and Development framework

“…This is the reason why the regulatory environment is a central piece of our model: we use the rules and regulations that are contained in it as proxies for aporophobia. In other words, we translate value interpretations into value representations as norms [24]. Since poverty is modelled as a diversity of agents' needs, we will be able to observe the impact that changes in aporophobic regulations have on poverty levels by identifying changes in these needs.…”