RSS

Mo­ti­va­tion se­lec­tion method

TagLast edit: 17 May 2021 13:14 UTC by Pablo

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.

Related entries

AI alignment | capability control method | indirect normativity

No entries.
No comments.