A capability control method is a method that attempt to prevent undesirable outcomes from artificial intelligence by restricting what the AI can do. Capability control methods encompass AI boxing, incentive methods (including anthropic capture), stunting, and tripwires (Bostrom 2014: 129-138). Capability control methods may be contrasted with motivation selection methods, which attempt instead to restrict what the AI wants to do.


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

AI alignment | AI boxing | anthropic capture | motivation selection method

Posts tagged Capability control method
Most Relevant