Morality, Machines and the Interpretation Problem: A Value-based, Wittgensteinian Approach to Building Moral Agents

TL;DR

This paper explores the inherent challenges of instilling morality in machines due to the Interpretation Problem, proposing a Wittgensteinian, value-based approach to develop virtuous artificial moral agents.

Contribution

It introduces a novel framework combining Wittgensteinian philosophy, game theory, and explicit moral reasoning to address the Interpretation Problem in AI morality.

Findings

Identification of the Interpretation Problem as a fundamental obstacle.

Categorization of mistakes into Mistakes of Intention and Instrumental Mistakes.

Proposed methods for aligning machine interpretation with external moral values.

Abstract

We present what we call the Interpretation Problem, whereby any rule in symbolic form is open to infinite interpretation in ways that we might disapprove of and argue that any attempt to build morality into machines is subject to it. We show how the Interpretation Problem in Artificial Intelligence is an illustration of Wittgenstein's general claim that no rule can contain the criteria for its own application, and that the risks created by this problem escalate in proportion to the degree to which to machine is causally connected to the world, in what we call the Law of Interpretative Exposure. Using game theory, we attempt to define the structure of normative spaces and argue that any rule-following within a normative space is guided by values that are external to that space and which cannot themselves be represented as rules. In light of this, we categorise the types of mistakes an artificial moral agent could make into Mistakes of Intention and Instrumental Mistakes, and we propose ways of building morality into machines by getting them to interpret the rules we give in accordance with these external values, through explicit moral reasoning, the Show, not Tell paradigm, the adjustment of causal power and structure of the agent, and relational values, with the ultimate aim that the machine develop a virtuous character and that the impact of the Interpretation Problem is minimised.