Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value

TL;DR

This paper advocates for full-stack alignment of AI and societal institutions using thick models of value to ensure beneficial outcomes across complex social systems.

Contribution

It introduces the concept of thick models of value for better normative reasoning and demonstrates their application in AI stewardship, negotiation, economics, and regulation.

Findings

Thick models of value improve normative reasoning in AI systems.

Application of thick models enhances societal decision-making processes.

Full-stack alignment can mitigate misaligned institutional goals.

Abstract

Beneficial societal outcomes cannot be guaranteed by aligning individual AI systems with the intentions of their operators or users. Even an AI system that is perfectly aligned to the intentions of its operating organization can lead to bad outcomes if the goals of that organization are misaligned with those of other institutions and individuals. For this reason, we need full-stack alignment, the concurrent alignment of AI systems and the institutions that shape them with what people value. This can be done without imposing a particular vision of individual or collective flourishing. We argue that current approaches for representing values, such as utility functions, preference orderings, or unstructured text, struggle to address these and other issues effectively. They struggle to distinguish values from other signals, to support principled normative reasoning, and to model collective goods. We propose thick models of value will be needed. These structure the way values and norms are represented, enabling systems to distinguish enduring values from fleeting preferences, to model the social embedding of individual choices, and to reason normatively, applying values in new domains. We demonstrate this approach in five areas: AI value stewardship, normatively competent agents, win-win negotiation systems, meaning-preserving economic mechanisms, and democratic regulatory institutions.