Difference between revisions of "Nonperson predicate"

From Lesswrongwiki
Jump to: navigation, search
m
Line 1: Line 1:
A '''Nonperson Predicate''' is a theorized test used to distinguish between a person and anything that isn't a person. The need for such a test arises from the possibility that when an [[Artificial General Intelligence]] predicts a person's actions, it may develop a model of them so complete that the model itself qualifies as a person. As the AGI investigates possibilities, all the negative situations the model experiences would generate a large amount of negative [[utility]]. Simulating a sufficiently complex model of a person is a [[computational hazard]]. Such a situation may be avoidable by limiting the complexity of any model of a person that an AGI creates, as discussed in Computational Hazards.  
+
A '''Nonperson Predicate''' is a theorized test used to distinguish between a person and anything that isn't a person.
  
Any practical implementation would likely consist of a large number of nonperson predicates of increasing complexity. For most nonpersons, an predicate will quickly return that it is not a person and conclude the test. Although any number of the predicates may be used before the test claims that something is not a person, it is crucial that any predicate in the test never claims that a person isn't. If unavoidable, it is preferable that the AGI considers nonpersons persons than considering a person a nonperson.  
+
The need for such a test arises from the possibility that when an [[Artificial General Intelligence]] predicts a person's actions, it may develop a model of them so complete that the model itself qualifies as a person. As the AGI investigates possibilities, these simulated people might be subjected to a large number of unpleasant situations. With a Nonperson predicate, either the AGI's designers or the AGI itself could ensure that no actual people are created.
 +
 
 +
Any practical implementation would likely consist of a large number of nonperson predicates of increasing complexity. For most nonpersons, a predicate will quickly return that it is not a person and conclude the test. Although any number of the predicates may be used before the test claims that something is not a person, it is crucial that any predicate in the test never claims that a person isn't a person. If false classifications are unavoidable, it is preferable that the AGI errs on the side of considering nonpersons persons.
  
 
== See Also ==
 
== See Also ==
 +
* [[Computational hazard]]
 
* [[Philosophical zombie]]
 
* [[Philosophical zombie]]
  

Revision as of 21:17, 22 October 2012

A Nonperson Predicate is a theorized test used to distinguish between a person and anything that isn't a person.

The need for such a test arises from the possibility that when an Artificial General Intelligence predicts a person's actions, it may develop a model of them so complete that the model itself qualifies as a person. As the AGI investigates possibilities, these simulated people might be subjected to a large number of unpleasant situations. With a Nonperson predicate, either the AGI's designers or the AGI itself could ensure that no actual people are created.

Any practical implementation would likely consist of a large number of nonperson predicates of increasing complexity. For most nonpersons, a predicate will quickly return that it is not a person and conclude the test. Although any number of the predicates may be used before the test claims that something is not a person, it is crucial that any predicate in the test never claims that a person isn't a person. If false classifications are unavoidable, it is preferable that the AGI errs on the side of considering nonpersons persons.

See Also

Blog Posts