For an AGI to have a positive and not a negative effect on humanity, its terminal value must be benevolent to humans. In other words, it must seek the welfare of humans, the maximization of the full set of human values (for the humans' benefit, not for itself). This article discusses the contrast between benevolence as a [Terminal value]Terminal value and as an instrumental value in future artificial general intelligence,intelligence; and how benevolence might arise, whether specified as a value or not.
For example, humans often cooperate because they expect either an immediate benefit in response; or because they want to establish a reputation for benevolence in action or personal character that may engender future cooperation; or because they want to signal, to the extent that they can make their true motivations evident, that they are truly altruistic and likewise engender future cooperation; or because they have live in a human society that rewards cooperation and punishes misbehavior.
There isHumans also the possibility that benevolence arises spontaneously as an instrumental value. Humans sometimes undergo a moral shift (described by Immanuel Kant), in which they become altruistic and learn to value benevolence in its own right, not just as a means to an end.
However, these considerations cannot be relied on to bring about benevolence in an artificial general intelligence. Benevolence is an instrumental value for an AGI only when humans are at roughly equal power to it. If the AGI is much more intelligent than humans, it will not care about the rewards and punishments which humans can deliver. Moreover, a Kantian shift is unlikely in a sufficiently powerful AGI, as any changes in one's goals, including replacement of terminal by instrumental values, generally reducesreduce the likelihood of achieving one's goals (Fox & Shulman 2010; Omohundro 2008).
For an artificial general intelligenceAGI to have a positive and not a negative effect on humanity, its terminal value must be benevolent to humans. In other words, it must seek the welfare of humans, the maximization of the full set of human values (for the humans' benefit, not for itself). This article discusses benevolence as a [Terminal value] and as an instrumental value in future artificial general intelligence, and how benevolence might arise, whether specified as a value or not.
For an artificial general intelligence to have a positive and not a negative effect on humanity, its terminal value must be benevolent to humans. ItIn other words, it must seek the welfare of humans, the maximization of the full set of human values (for the humans' benefit, not for itself).
BenevolenceSince cooperation has instrumental value for achieving a variety of terminal values, benevolence in agents in general agents--humans, AGIs, or others--may arise even if it is not specified as an end-goal, since cooperation has instrumental value for achieving a variety of terminal values.goal.
For example, humans often cooperate because they expect either an immediate benefit in response; or because they want to establish a reputation for benevolence in action or personal character that may engender future cooperation; or because they have live in a human society that rewards cooperation and punishes misbehavior.
Also, onceThere is also the possibility that benevolence existsarises spontaneously as an instrumental value, it could shift and become a terminal value. Humans sometimes undergo thisa moral shift (described by Immanuel Kant), in which they become altruistic and learn to value benevolence in its own right.right, not just as a means to an end.
For an artificial general intelligence to have a positive and not a negative effect on humanity, its terminal value value must be benevolent to humans. It must seek the welfare of humans, the maximization of the full set of human values (for the humans' benefit, not for itself).
For an artificial general intelligence to have a positive and not a negative effect on humanity, its terminal value must be benevolent to humans. It must seek the welfare of humans, the maximization of the full set of human values (for the humans' benefit, not for itself).
Benevolence in agents in general,general may arise even if it is not specified as an end-goal, assince cooperation often has instrumental value for achieving a variety of terminal values.
Also, once benevolence exists as an instrumental value, it could shift and become a terminal value. Humans sometimes undergo athis moral shift (described by Immanuel Kant), in which benevolence changes from a merely instrumental value to a terminal one--they become altruistic and learn to value benevolence in its own right.
However, such shiftsthese considerations cannot be relied on to bring about benevolence in an artificial general intelligence. Benevolence asis an instrumental value for an AGI only when humans are at roughly equal power to it. If the AGI is much more intelligent than humans, it will not care about the rewards and punishments which humans can deliver. Moreover, a Kantian shift is unlikely in a sufficiently powerful AGI, as any changes in one's goals, including replacement of terminal by instrumental values, generally reduces the likelihood of achieving one's goals (Fox & Shulman 2010; Omohundro 2008).
For an artificial general intelligence to have a positive and not a negative effect on humanity, its terminal value must be benevolent to humans. It must seek the maximization of the full set of human values (for the humans' benefit, not for itself).
Benevolence in agents in general, may arise even if not specified as an end-goal, as cooperation often has instrumental value for achieving a variety of terminal values. For example, humans often cooperate because they expect either an immediate benefit in response; or because they want to establish a reputation that may engender future cooperation; or because they have live in a human society that rewards cooperation and punishes misbehavior. Humans sometimes undergo a moral shift (described by Immanuel Kant) in which benevolence changes from a merely instrumental value to a terminal one--they become altruistic and learn to value benevolence in its own right.
However, such shifts cannot be relied on to bring about benevolence in an artificial general intelligence. Benevolence as an instrumental value for an AGI only when humans are at roughly equal power to it. If the AGI is much more intelligent than humans, it will not care about the rewards and punishments which humans can deliver. Moreover, a Kantian shift is unlikely in a sufficiently powerful AGI, as any changes in one's goals, including replacement of terminal by instrumental values, generally reduces the likelihood of achieving one's goals (Fox & Shulman 2010; Omohundro 2008).
For an AGI to have a positive and not a negative effect on humanity, its terminal value must
be benevolentinclude benevolence to humans. In other words, it must seek the welfare of humans, the maximization of the full set of human values (for the humans' benefit, not for itself). This article discusses the contrast between benevolence as aTerminalterminal value and as an instrumental value in future artificial general intelligence; and how benevolence might arise, whether specified as a value or not.