Alignment as Jurisprudence
Authors: Nicholas Caputo
Summary
This essay draws parallels between alignment (getting AI to follow human values) and jurisprudence (how judges should decide cases), arguing both fields use language specification and interpretation to shape future decisions by powerful actors. The author discusses Constitutional AI and case-based reasoning as alignment approaches that mirror legal theories like Dworkin's principle-based interpretivism and Sunstein's analogical reasoning, suggesting the two fields can inform each other.
Main takeaways:
- Alignment and law both try to predict and constrain powerful decision-makers (AI vs. judges) using language-based rules
- Constitutional AI parallels principle-based legal interpretation; case-based reasoning mirrors how judges use precedent
- Lessons from what works/fails in law could improve alignment, and vice versa
- Both should aim to empower people rather than just constrain actors
Relevance
Tangential to my persona and behavioral installation work. The essay discusses Constitutional AI as a fine-tuning approach, but focuses on high-level philosophy rather than mechanisms. Potentially relevant if I need to think about how rule-based vs. example-based training affects persona installation, but no direct connection to markers, leakage, or installation paths.
Abstract
arXiv:2605.08416v1 Announce Type: new Abstract: Jurisprudence, the study of how judges should properly decide cases, and alignment, the science of getting AI models to conform to human values, share a fundamental structure. These seemingly distant fields both seek to predict and shape how decisions by powerful actors, in one case judges and in the other increasingly powerful artificial intelligences, will be made in the unknown future. And they use similar tools of the specification and interpretation of language to try to accomplish those goals. The great debates of jurisprudence, about what the law is and what it should be, can provide insight into alignment, and lessons from what does and does not work in alignment can help make progress in jurisprudence. This essay puts the two fields directly into conversation. Drawing on leading accounts of jurisprudence, particularly Dworkin's principle-oriented interpretivism and Sunstein's positivist account of law as analogical reasoning, and on cutting-edge alignment approaches, namely Constitutional AI and case-based reasoning, it illustrates the value of a more sophisticated legally-inspired approach to the interplay of rules and cases in finetuning alignment and points to ways that AI can provide a better understanding of how the law works and how it can be improved by the introduction of AI. AI systems and the law should operate to empower people to act in the world, helping to expand their capabilities and the extent to which they are able to achieve their goals. As AI continues to improve in capacity, and as the constraints that legal theory places on human judges seem be coming undone, the conversation between these two fields will become increasingly essential and may help point to a better version of both.