Skip to main content
BackUnintended consequences
Home/Risks/Hogenhout (2021)/Unintended consequences

Unintended consequences

A framework for ethical Ai at the United Nations

Hogenhout (2021)

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.

"Sometimes an AI finds ways to achieve its given goals in ways that are completely different from what its creators had in mind."(p. 9)

Other risks from Hogenhout (2021) (12)