From Lesswrongwiki
Revision as of 22:02, 29 September 2012 by Costanza R (talk | contribs)
Jump to: navigation, search

A problem is Friendly AI-complete if solving it is equivalent to creating Friendly AI. Friendliness theory is one proposal among many for ushering in safe Artificial General Intelligence technology. The Singularity Institute argues that any safe superintelligence architecture is FAI-complete. For example,

In "Dreams of Friendliness" Eliezer Yudkowsky argues that if you have an Oracle AI, then you can ask it, "What should I do?" If it can answer this question correctly, then it is FAI-complete.

Similarly, if you have a tool AI, it must make extremely complex decisions about how many resources it can use, how to display answers in human understandable yet accurate form, et cetera. The many ways in which it could choose catastrophically require it to be FAI-complete. Note that this does not imply that an agent-like, fully free FAI is easier to create than any of the other proposals.

Goertzel proposed a "Nanny AI"(Should humanity build a global AI nanny to delay the singularity until it’s better understood?) with moderate superhuman intelligence, able to forestall Singularity eternally, or to delay it. However, it has been noticed by Luke Muehlhauser and Anna Salamon (Intelligence Explosion: Evidence and Import) that a Nanny AI is FAI-complete. In fact, building it would require to solve the problems required to build Friendly Artificial Intelligence.

Blog posts


See also