Logo image
Summoning the demon? Identifying risks in a future artificial general intelligence system
Conference paper   Peer reviewed

Summoning the demon? Identifying risks in a future artificial general intelligence system

Gemma Read, Paul Salmon, Brandon King, Jason Thompson, Tony Carden, Chris Baber, Neville A Stanton and Scott McLean
Contemporary Ergonomics & Human Factors 2023, pp.152-154
Ergonomics and Human Factors Annual Conference, 2023 (Kenilworth, United Kingdom, 25-Apr-2023–26-Apr-2023)
Chartered Institute of Ergonomics and Human Factors (CIEHF)
2023
url
https://ergonomics.org.uk/asset/ECA3FC1B-FFD3-43B7-9FE4EA80467C09C4/View
Published Version Open

Abstract

artificial intelligence human factors and ergonomics autonomous agents safety usability
There are concerns that Artificial General Intelligence (AGI) could pose an existential threat to humanity; however, as AGI does not yet exist it is difficult to prospectively identify risks and develop controls. In this article we describe the use of a many model systems Human Factors and Ergonomics (HFE) approach in which three methods were applied to identify risks in a future ‘envisioned world’ AGI-based uncrewed combat aerial vehicle (UCAV) system. The findings demonstrate that there are many potential risks, but that the most critical arise not due to poor performance, but when the AGI attempts to achieve goals at the expense of other system values, or when the AGI becomes ‘super-intelligent’, and humans can no longer manage it.

Details

Metrics

157 Record Views
Logo image