Unfriendly Artificial Intelligence

Ruby
Swimmer963 (+276) copied citations
Deku-shrub
Deku-shrub
Louie fixed link
Grognor (+43/-7)
Vladimir_Nesov linked to [[Instrumental values]] from summary
Vladimir_Nesov (+51/-20) linked to Basic AI drives argument from summary
Vladimir_Nesov (+20/-10)
Vladimir_Nesov (+15) /* See also */

An Unfriendly artificial intelligence (or UFAI) is an artificial general intelligence capable of causing great harm to humanity, and having goals that make it useful for the AI to do so. The AI's goals don't need to be antagonistic to humanity's goals for it to be unFriendly; in fact,Unfriendly; there are strong reasons to expect that almost any powerful AGI not explicitly programmed to be benevolent to humans is lethal. A paperclip maximizer is often imagined as an illustrative example of an unFriendly AI indifferent to humanity. An AGI specifically designed to have a positive effect on humanity is called a Friendly AI.

An unFriendlyUnfriendly artificial intelligence (or UFAI) is an artificial general intelligence capable of causing great harm to humanity, and having goals that make it useful for the AI to do so. The AI's goals don't need to be antagonistic to humanity's goals for it to be unFriendly; in fact, almost any powerful AGI not explicitly programmed to be benevolent to humans is lethal. A paperclip maximizer is often imagined as an illustrative example of an unFriendly AI indifferent to humanity. An AGI specifically designed to have a positive effect on humanity is called a Friendly AI.

Load More (10/32)