Skip to main content
Home/Risks/Steimers & Schneider (2022)/Degree of Automation and Control

Degree of Automation and Control

Sources of Risk of AI Systems

Steimers & Schneider (2022)

Category
Risk Domain

AI systems acting in conflict with human goals or values, especially the goals of designers or users, or ethical standards. These misaligned behaviors may be introduced by humans during design and development, such as through reward hacking and goal misgeneralisation, or may result from AI using dangerous capabilities such as manipulation, deception, situational awareness to seek power, self-proliferate, or achieve other goals.

"The degree of automation and control describes the extent to which an AI system functions independently of human supervision and control."(p. 12)

Other risks from Steimers & Schneider (2022) (7)