Requisite Variety in Ethical Utility Functions for AI Value Alignment

06/30/2019
by   Nadisha-Marie Aliman, et al.
0

Being a complex subject of major importance in AI Safety research, value alignment has been studied from various perspectives in the last years. However, no final consensus on the design of ethical utility functions facilitating AI value alignment has been achieved yet. Given the urgency to identify systematic solutions, we postulate that it might be useful to start with the simple fact that for the utility function of an AI not to violate human ethical intuitions, it trivially has to be a model of these intuitions and reflect their variety - whereby the most accurate models pertaining to human entities being biological organisms equipped with a brain constructing concepts like moral judgements, are scientific models. Thus, in order to better assess the variety of human morality, we perform a transdisciplinary analysis applying a security mindset to the issue and summarizing variety-relevant background knowledge from neuroscience and psychology. We complement this information by linking it to augmented utilitarianism as a suitable ethical framework. Based on that, we propose first practical guidelines for the design of approximate ethical goal functions that might better capture the variety of human moral judgements. Finally, we conclude and address future possible challenges.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/02/2019

Augmented Utilitarianism for AGI Safety

In the light of ongoing progresses of research on artificial intelligent...
research
07/11/2019

Grounding Value Alignment with Ethical Principles

An important step in the development of value alignment (VA) systems in ...
research
05/04/2023

A computational framework of human values for ethical AI

In the diverse array of work investigating the nature of human values fr...
research
10/25/2018

Mimetic vs Anchored Value Alignment in Artificial Intelligence

"Value alignment" (VA) is considered as one of the top priorities in AI ...
research
12/08/2017

AI Safety and Reproducibility: Establishing Robust Foundations for the Neuroscience of Human Values

We propose the creation of a systematic effort to identify and replicate...
research
01/30/2023

Exploring AI Ethics of ChatGPT: A Diagnostic Analysis

Recent breakthroughs in natural language processing (NLP) have permitted...
research
12/31/2018

Impossibility and Uncertainty Theorems in AI Value Alignment (or why your AGI should not have a utility function)

Utility functions or their equivalents (value functions, objective funct...

Please sign up or login with your details

Forgot password? Click here to reset