Incomplete Contracting and AI Alignment
Dylan Hadfield-Menell, Gillian Hadfield

TL;DR
This paper proposes using incomplete contracting theory from law and economics to better understand and address the AI alignment problem, emphasizing the role of external structures like institutions in human contracts.
Contribution
It introduces a novel framework linking incomplete contracting insights to AI alignment, focusing on replicating human cognitive processes supported by external structures.
Findings
Economic analysis of incomplete contracts offers insights for AI alignment.
External structures like law and culture support human contracts and can inform AI design.
A research agenda is proposed to develop AI systems that emulate human reliance on external structures.
Abstract
We suggest that the analysis of incomplete contracting developed by law and economics researchers can provide a useful framework for understanding the AI alignment problem and help to generate a systematic approach to finding solutions. We first provide an overview of the incomplete contracting literature and explore parallels between this work and the problem of AI alignment. As we emphasize, misalignment between principal and agent is a core focus of economic analysis. We highlight some technical results from the economics literature on incomplete contracts that may provide insights for AI alignment researchers. Our core contribution, however, is to bring to bear an insight that economists have been urged to absorb from legal scholars and other behavioral scientists: the fact that human contracting is supported by substantial amounts of external structure, such as generally available…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
