A motivation selection method is method that attempts to prevent undesirable outcomes from artificial intelligence by influencing what the AI wants to do. Motivation selection methods encompass direct specification, domesticity, indirect normativity, and augmentation (Bostrom 2014: 138-143). Motivation selection methods may be contrasted with capability control methods, which attempt instead to restrict what the AI can do.

Bibliography

Bostrom, Nick (2014) Superintelligence: Paths, Dangers, Strategies, Oxford: Oxford University Press.

AI alignment | capability control method | indirect normativity

Posts tagged Motivation selection method
Most Relevant