Safety without alignment

• Published in: arXiv.org
• Main Authors: Kornai, András, Bukatin, Michael, Zombori, Zsolt
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 18.03.2023
• Subjects: Alignment; Ethics; Safety; Theorem proving

Currently, the dominant paradigm in AI safety is alignment with human values. Here we describe progress on developing an alternative approach to safety, based on ethical rationalism (Gewirth:1978), and propose an inherently safe implementation path via hybrid theorem provers in a sandbox. As AGIs ev...