Corrigibility is defined in Arbital as: [the agent] doesn’t interfere with what we would intuitively see as attempts to ‘correct’ the agent, or ‘correct’ our mistakes in building it
Corrigibility is defined in Arbital as:
[the agent] doesn’t interfere with what we would intuitively see as attempts to ‘correct’ the agent, or ‘correct’ our mistakes in building it
Corrigibility is defined by me as “the objective function of the AI can be changed”.
Corrigibility is defined by me as “the objective function of the AI can be changed”.