arXiv Open Access 2023

Foundational Moral Values for AI Alignment

Betty Li Hou Brian Patrick Green

Lihat Sumber

Abstrak

Solving the AI alignment problem requires having clear, defensible values towards which AI systems can align. Currently, targets for alignment remain underspecified and do not seem to be built from a philosophically robust structure. We begin the discussion of this problem by presenting five core, foundational values, drawn from moral philosophy and built on the requisites for human existence: survival, sustainable intergenerational existence, society, education, and truth. We show that these values not only provide a clearer direction for technical alignment work, but also serve as a framework to highlight threats and opportunities from AI systems to both obtain and sustain these values.

Topik & Kata Kunci

cs.CY cs.AI

Penulis (2)

Betty Li Hou

Brian Patrick Green

Format Sitasi

APA MLA BibTeX

Hou, B.L., Green, B.P. (2023). Foundational Moral Values for AI Alignment. https://arxiv.org/abs/2311.17017

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2023
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓