Skip to main content
BackLoss of control of autonomous systems and unforeseen behaviour due to lack of transparency and self-programming/ reprogramming
Home/Risks/Wirtz, Weyerer & Kehl (2022)/Loss of control of autonomous systems and unforeseen behaviour due to lack of transparency and self-programming/ reprogramming

Loss of control of autonomous systems and unforeseen behaviour due to lack of transparency and self-programming/ reprogramming

Governance of artificial intelligence: A risk and guideline-based integrative framework

Wirtz, Weyerer & Kehl (2022)

Sub-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.

Other risks from Wirtz, Weyerer & Kehl (2022) (37)