Skip to main content

Control

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.

"The risk of AI models and systems acting against human interests due to misalignment, loss of control, or rogue AI scenarios."(p. 10)

Other risks from Uuk2025 (60)