MIT AI Risk Repository · Risk Category · 06.08.00

Unintended consequences

Description

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

From A framework for ethical Ai at the United Nations (Hogenhout2021), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Causal entity
AI
Timing
Other

Subdomain definition: 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.

Real-world incidents in this subdomain

Browse all incidents in this subdomain

How other frameworks describe this risk

Other entries from Hogenhout2021