Artificial Intelligence and Dual Contract

Platforms are increasingly adopting Artificial Intelligence (henceforth, AI) algorithms (for example, the ChatGPT (Ouyang, Wu, Jiang, Almeida, Wainwright, Mishkin, Zhang, Agarwal, Slama, Ray, et al. (2022)) and Eloundou, Manning, Mishkin, and Rock (2023)) to intelligentize services and price their products, and this tendency is likely to be extended to other business areas, particularly contract design. In this paper, we ask whether contracting algorithms may "autonomously" learn to be incentive compatible, especially for the contracting problem with multiple sides, which we also refer to as the multi-sided contracting problem. We emphasize that AI algorithms can be used to automatically optimize the terms of a contract by taking into account the preferences of both sides and the legal and economic environment in which the agreement must be implemented. Note that this contract negotiation process is automatic, requiring very little external guidance. In light of these developments, concerns have been voiced by scholars and organizations alike, that AI algorithms may create an AI alignment problem due to differences between the specified reward function and what relevant humans (the designer, the user, others affected by the agent's behavior) actually value (see Hadfield-Menell and Hadfield (2019) and Gabriel (2020)). We highlight that this AI alignment problem has a clear analogy to the principal-agent problem (see Hadfield-Menell and Hadfield (2019)), and the analysis of incentive compatibility for the incomplete contracting via AI algorithms can provide an insightful framework for understanding the alignment among algorithms. But how real is the risk of misalignment among AI algorithms? That is a difficult question to answer, both empirically and theoretically. On the empirical side, alignment is notoriously hard to detect from market outcomes, and firms typically do not disclose details of the financial or employment contracts they have.