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