This paper looks at philosophical questions that arise in the context of AI alignment. It defends three propositions. First, normative and technical aspects of the AI alignment problem are interrelated, creating space for productive engagement between people working in both domains. Second, it is important to be clear about the goal of alignment. There are significant differences between AI that aligns with instructions, intentions, revealed preferences, ideal preferences, interests and values. A principle-based approach to AI alignment, which combines these elements in a systematic way, has considerable advantages in this context. Third, the central challenge for theorists is not to identify 'true' moral principles for AI; rather, it is to identify fair principles for alignment, that receive reflective endorsement despite widespread variation in people's moral beliefs. The final part of the paper explores three ways in which fair principles for AI alignment could potentially be identified.

中文翻译：

---

人工智能、价值观和一致性

本文着眼于人工智能对齐背景下出现的哲学问题。它为三个命题辩护。首先，人工智能对齐问题的规范和技术方面是相互关联的，为在这两个领域工作的人们之间的生产性参与创造了空间。其次，明确对齐的目标很重要。与指令、意图、显示偏好、理想偏好、兴趣和价值观相一致的人工智能之间存在显着差异。在这种情况下，以系统方式结合这些元素的基于原则的 AI 对齐方法具有相当大的优势。第三，理论家面临的主要挑战不是确定人工智能的“真正”道德原则；相反，它是确定对齐的公平原则，尽管人们的道德信仰存在广泛差异，但仍获得反思性认可。论文的最后部分探讨了可能确定 AI 对齐公平原则的三种方式。