Next Article in Journal
Two Experimental Devices for Record and Playback of Tactile Data
Next Article in Special Issue
Provably Safe Artificial General Intelligence via Interactive Proofs
Previous Article in Journal
Naturalizing Logic: How Knowledge of Mechanisms Enhances Inductive Inference
Previous Article in Special Issue
AI Ethics and Value Alignment for Nonhuman Animals

Understanding and Avoiding AI Failures: A Practical Guide

Speed School of Engineering, University of Louisville, Louisville, KY 40292, USA
Author to whom correspondence should be addressed.
Academic Editor: Marcin J. Schroeder
Philosophies 2021, 6(3), 53;
Received: 7 May 2021 / Revised: 9 June 2021 / Accepted: 9 June 2021 / Published: 28 June 2021
(This article belongs to the Special Issue The Perils of Artificial Intelligence)
As AI technologies increase in capability and ubiquity, AI accidents are becoming more common. Based on normal accident theory, high reliability theory, and open systems theory, we create a framework for understanding the risks associated with AI applications. This framework is designed to direct attention to pertinent system properties without requiring unwieldy amounts of accuracy. In addition, we also use AI safety principles to quantify the unique risks of increased intelligence and human-like qualities in AI. Together, these two fields give a more complete picture of the risks of contemporary AI. By focusing on system properties near accidents instead of seeking a root cause of accidents, we identify where attention should be paid to safety for current generation AI systems. View Full-Text
Keywords: AI safety; normal accident theory; risk analysis AI safety; normal accident theory; risk analysis
Show Figures

Figure 1

MDPI and ACS Style

Williams, R.; Yampolskiy, R. Understanding and Avoiding AI Failures: A Practical Guide. Philosophies 2021, 6, 53.

AMA Style

Williams R, Yampolskiy R. Understanding and Avoiding AI Failures: A Practical Guide. Philosophies. 2021; 6(3):53.

Chicago/Turabian Style

Williams, Robert, and Roman Yampolskiy. 2021. "Understanding and Avoiding AI Failures: A Practical Guide" Philosophies 6, no. 3: 53.

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

Back to TopTop