Bounding the impact of AGI

Kornai, András (2014) Bounding the impact of AGI. JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE, XX (X). pp. 1-22. ISSN 0952-813X

[img] Text
Kornai_2602158_ny.pdf

Download (331kB)

Abstract

Humans already have a certain level of autonomy, defined here as capability for voluntary purposive action, and a certain level of rationality, i.e. capability of reasoning about the consequences of their own actions and those of others. Under the prevailing concept of artificial general intelligences (AGIs), we envision artificial agents that have at least this high, and possibly considerably higher, levels of autonomy and rationality. We use the method of bounds to argue that AGIs meeting these criteria are subject to Gewirth's dialectical argument to the necessity of morality, compelling them to behave in a moral fashion, provided Gewirth's argument can be formally shown to be conclusive. The main practical obstacles to bounding AGIs by means of ethical rationalism are also discussed. © 2014 © 2014 Taylor & Francis.

Item Type: ISI Article
Additional Information: N1 Article in Press
Uncontrolled Keywords: principle of generic consistency, formal verification, ethical rationalism
Subjects: Q Science > QA Mathematics and Computer Science > QA75 Electronic computers. Computer science / számítástechnika, számítógéptudomány
Depositing User: EPrints Admin
Date Deposited: 26 Aug 2014 14:07
Last Modified: 26 Aug 2014 14:47
URI: https://eprints.sztaki.hu/id/eprint/7922

Update Item Update Item