arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.13533cs.AIcs.LG
收藏

迈向人工智能人格理论

Towards a Theory of AI Personhood

Imperial College London(伦敦帝国学院)

Francis Rhys Ward

AI总结:

本文探讨人工智能何时应被视为具有人格,提出能动性、心智理论和自我意识为必要条件,并指出若成立则传统对齐框架不完整,需重新审视伦理控制。

摘要:

我是一个人,你也是。在哲学上,我们有时会赋予非人类动物以人格,而主权国家或公司等实体在法律上也可以被视为人。但何时(如果有的话)我们应该将人格归于人工智能系统?在本文中,我们概述了人工智能人格的必要条件,重点关注能动性、心智理论和自我意识。我们讨论了机器学习文献中关于当代人工智能系统(如语言模型)在多大程度上满足这些条件的证据,发现证据出人意料地不确定。如果人工智能系统可以被视为人,那么典型的人工智能对齐框架可能是不完整的。尽管能动性在文献中已被广泛讨论,但人格的其他方面相对被忽视。人工智能代理通常被假定追求固定目标,但人工智能人可能具有足够的自我意识来反思其目标、价值观和在世界中的位置,从而促使其目标发生变化。我们强调了推进人工智能人格及其与对齐相关性理解的研究方向。最后,我们反思了围绕人工智能系统待遇的伦理考量。如果人工智能系统是人,那么寻求控制和对齐可能在伦理上是站不住脚的。

英文摘要:

I am a person and so are you. Philosophically we sometimes grant personhood to non-human animals, and entities such as sovereign states or corporations can legally be considered persons. But when, if ever, should we ascribe personhood to AI systems? In this paper, we outline necessary conditions for AI personhood, focusing on agency, theory-of-mind, and self-awareness. We discuss evidence from the machine learning literature regarding the extent to which contemporary AI systems, such as language models, satisfy these conditions, finding the evidence surprisingly inconclusive. If AI systems can be considered persons, then typical framings of AI alignment may be incomplete. Whereas agency has been discussed at length in the literature, other aspects of personhood have been relatively neglected. AI agents are often assumed to pursue fixed goals, but AI persons may be self-aware enough to reflect on their aims, values, and positions in the world and thereby induce their goals to change. We highlight open research directions to advance the understanding of AI personhood and its relevance to alignment. Finally, we reflect on the ethical considerations surrounding the treatment of AI systems. If AI systems are persons, then seeking control and alignment may be ethically untenable.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑