Pablo | v1.6.0Jul 12th 2022 | (+9) | ||
Pablo | v1.5.0Mar 16th 2022 | (+128) | ||
Leo | v1.4.0Jan 14th 2022 | (+130/-149) | ||
Pablo | v1.3.0May 17th 2021 | (+244/-37) | ||
MichaelA | v1.2.0Mar 11th 2021 | (+8/-3) Changed "can do" to "wants to do"; I'm guessing the first sentence had been copied and edited from capability control methods page | ||
Pablo | v1.1.0Jan 21st 2021 | (+20/-9) | ||
Pablo | v1.0.0Jan 21st 2021 | (+393) |
Bostrom, Nick (2014) Superintelligence: Paths, Dangers, Strategies, Oxford: Oxford University Press, pp. 138-143.
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).augmentation.[1] Motivation selection methods may be contrasted with capability control methods, which attempt instead to restrict what the AI can do.
Bostrom, Nick (2014) Superintelligence: Paths, Dangers, Strategies, Oxford: Oxford University Press.
Bostrom, Nick (2014) Superintelligence: Paths, Dangers, Strategies, Oxford: Oxford University Press, pp. 138-143.
A Motivationmotivation selection methodsmethod areis method that attempts to prevent undesirable outcomes from artificial intelligence that involveby influencing what the AI wants to do. TheseMotivation 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.
Bostrom, Nick (2014) Superintelligence: Paths, Dangers, Strategies, Oxford: Oxford University Press.
AI alignment | capability control method | indirect normativity
Motivation selection methods are attempts to prevent undesirable outcomes from artificial intelligence that involve influencing what the AI canwants to do. These 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.
Motivation selection methods are methodsattempts to prevent undesirable outcomes from artificial intelligence bythat involve influencing what the AI can do. These 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.
Motivation selection methods are methods to prevent undesirable outcomes from artificial intelligence by influencing what the AI can do. These 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.
A motivation selection method is method that attempts to prevent undesirable outcomes from advanced artificial intelligence by influencing what the AI wants to do. Motivation selection methods encompass direct specification, domesticity, indirect normativity, and augmentation.[1] Motivation selection methods may be contrasted with capability control methods, which attempt instead to restrict what the AI can do.