Expert and Non-Expert Opinion about Technological Unemployment

TL;DR

This study compares expert and non-expert opinions on the risk of automation-induced unemployment, revealing experts are more cautious and that technological progress may be slower than public fears suggest.

Contribution

It provides a comparative analysis of expert and non-expert predictions on AI and Robotics-driven unemployment risks and timelines.

Findings

Experts predict slower automation timelines than non-experts.

Public fears may overestimate the speed of AI progress.

Technological barriers could delay widespread unemployment.

Abstract

There is significant concern that technological advances, especially in Robotics and Artificial Intelligence (AI), could lead to high levels of unemployment in the coming decades. Studies have estimated that around half of all current jobs are at risk of automation. To look into this issue in more depth, we surveyed experts in Robotics and AI about the risk, and compared their views with those of non-experts. Whilst the experts predicted a significant number of occupations were at risk of automation in the next two decades, they were more cautious than people outside the field in predicting occupations at risk. Their predictions were consistent with their estimates for when computers might be expected to reach human level performance across a wide range of skills. These estimates were typically decades later than those of the non-experts. Technological barriers may therefore provide society with more time to prepare for an automated future than the public fear. In addition, public expectations may need to be dampened about the speed of progress to be expected in Robotics and AI.