Difference between revisions of "AI takeoff"

From Lesswrongwiki
Jump to: navigation, search
(Soft takeoff)
Line 3: Line 3:
 
==Soft takeoff==
 
==Soft takeoff==
  
A '''soft takeoff''' refers to an SAI that would self-improve over a period of months, years or decades. This could be due to either the learning algorithm being too demanding for the hardware or because the AI relies on experiencing feedback from the real-world that would have to be played out in real time. By maintaining control of the AGI’s ascent it should be easier for a [[Friendly AI]] to emerge.
+
A '''soft takeoff''' refers to an SAI that would self-improve over a period of years or decades. This could be due to either the learning algorithm being too demanding for the hardware or because the AI relies on experiencing feedback from the real-world that would have to be played out in real time. By maintaining control of the AGI’s ascent it should be easier for a [[Friendly AI]] to emerge.
  
Vernor Vinge, Hans Moravec and Ray Kurzweil have all expressed the view that soft takeoff is preferable to a hard takeoff as it would be both safer and easier to engineer.
+
Vernor Vinge, Hans Moravec and Ray Kurzweil have all expressed the view that soft takeoff is preferable to a hard takeoff as it would be both safer and easier to engineer.
  
 
==Hard takeoff==
 
==Hard takeoff==

Revision as of 07:56, 3 September 2012

AI takeoff refers to a point in the future where Artificial General Intelligence recursively self-improves. This will lead to an increase in intelligence, and will likely lead to an increase in computing power and other resources. The speed at which a AGI may expand is usually split into “soft” and “hard” takeoff scenarios.

Soft takeoff

A soft takeoff refers to an SAI that would self-improve over a period of years or decades. This could be due to either the learning algorithm being too demanding for the hardware or because the AI relies on experiencing feedback from the real-world that would have to be played out in real time. By maintaining control of the AGI’s ascent it should be easier for a Friendly AI to emerge.

Vernor Vinge, Hans Moravec and Ray Kurzweil have all expressed the view that soft takeoff is preferable to a hard takeoff as it would be both safer and easier to engineer.

Hard takeoff

A hard takeoff refers to AGI expansion in a matter of minutes, hours or days. This scenario is widely considered much more precarious, as this involves an AGI rapidly ascending in power without human control. This may result in unexpected or undesired behavior (i.e. Unfriendly AI). A hard takeoff can either be defined as a system with vastly greater intelligence or one that has acquired extensive computing resources (e.g. control of the Internet).

The feasibility of “hard takeoff” has been addressed by Hugo de Garis, Eliezer Yudkowsky, Ben Goertzel, Nick Bostrom and Michael Anissimov. However, it is widely agreed that a hard takeoff is something to be avoided due to the risks.

Blog posts

External links

See Also