Skip to main content
Home/Risks/Uuk2025/Deceptive alignment

Deceptive alignment

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.

"AI models and systems that appear aligned with human goals during development may behave unpredictably or dangerously once deployed"(p. 12)

Other risks from Uuk2025 (60)