Foundational Moral Values for AI Alignment
Abstract
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.
Keywords
Cite
@article{arxiv.2311.17017,
title = {Foundational Moral Values for AI Alignment},
author = {Betty Li Hou and Brian Patrick Green},
journal= {arXiv preprint arXiv:2311.17017},
year = {2023}
}
Comments
AI meets Moral Philosophy and Moral Psychology Workshop, 37th Conference on Neural Information Processing Systems (NeurIPS 2023)