PhilSci Archive

The Linguistic Blind Spot of Value-Aligned Agency, Natural and Artificial

LaCroix, Travis (2022) The Linguistic Blind Spot of Value-Aligned Agency, Natural and Artificial. [Preprint]

[img]
Preview
Text
LaCroix-Linguistic-Blind-Spot-Pre-Print-02-07-22.pdf

Download (4MB) | Preview

Abstract

The value-alignment problem for artificial intelligence (AI) asks how we can ensure that the 'values'—i.e., objective functions—of artificial systems are aligned with the values of humanity. In this paper, I argue that linguistic communication is a necessary condition for robust value alignment. I discuss the consequences that the truth of this claim would have for research programmes that attempt to ensure value alignment for AI systems—or, more loftily, designing robustly beneficial or ethical artificial agents.


Export/Citation: EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL
Social Networking:
Share |

Item Type: Preprint
Creators:
CreatorsEmailORCID
LaCroix, Travistlacroix@dal.ca0000-0002-1724-3434
Keywords: Artificial Intelligence; AI; Value-Alignment Problems; Principal-Agent Problems; Machine Learning; Objective Functions; Normative Theory; Language; Linguistic Communication; Communication Systems; Information Transfer; Coordination; Values; Preferences; Objectives
Subjects: Specific Sciences > Artificial Intelligence > AI and Ethics
Specific Sciences > Biology > Evolutionary Theory
Specific Sciences > Artificial Intelligence
Specific Sciences > Cultural Evolution
General Issues > Decision Theory
Specific Sciences > Economics
General Issues > Ethical Issues
General Issues > Game Theory
Specific Sciences > Artificial Intelligence > Machine Learning
General Issues > Technology
Depositing User: Dr. Travis LaCroix
Date Deposited: 05 Jul 2022 04:06
Last Modified: 05 Jul 2022 04:06
Item ID: 20835
Subjects: Specific Sciences > Artificial Intelligence > AI and Ethics
Specific Sciences > Biology > Evolutionary Theory
Specific Sciences > Artificial Intelligence
Specific Sciences > Cultural Evolution
General Issues > Decision Theory
Specific Sciences > Economics
General Issues > Ethical Issues
General Issues > Game Theory
Specific Sciences > Artificial Intelligence > Machine Learning
General Issues > Technology
Date: 2 July 2022
URI: https://philsci-archive.pitt.edu/id/eprint/20835

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item