• Earn real money by being active: Hello Guest, earn real money by simply being active on the forum — post quality content, get reactions, and help the community. Once you reach the minimum credit amount, you’ll be able to withdraw your balance directly. Learn how it works.

Courses Superintelligence: Paths, Dangers, Strategies

dEEpEst

☣☣ In The Depths ☣☣
Staff member
Administrator
Super Moderator
Hacker
Specter
Crawler
Shadow
Joined
Mar 29, 2018
Messages
13,860
Solutions
4
Reputation
27
Reaction score
45,546
Points
1,813
Credits
55,340
‎7 Years of Service‎
 
56%

Superintelligence.jpg

Superintelligence: Paths, Dangers, Strategies

Synopsis​

It is unknown whether human-level
This link is hidden for visitors. Please Log in or register now.
will arrive in a matter of years, later this century, or not until future centuries. Regardless of the initial timescale, once human-level machine intelligence is developed, a "superintelligent" system that "greatly exceeds the cognitive performance of humans in virtually all domains of interest" would most likely follow surprisingly quickly. Such a superintelligence would be very difficult to control.

While the ultimate goals of superintelligences could vary greatly, a functional superintelligence will spontaneously generate, as natural subgoals, "
This link is hidden for visitors. Please Log in or register now.
" such as self-preservation and goal-content integrity, cognitive enhancement, and resource acquisition. For example, an agent whose sole final goal is to solve the
This link is hidden for visitors. Please Log in or register now.
(a famous unsolved mathematical
This link is hidden for visitors. Please Log in or register now.
) could create and act upon a subgoal of transforming the entire Earth into some form of
This link is hidden for visitors. Please Log in or register now.
(hypothetical material optimized for computation) to assist in the calculation. The superintelligence would proactively resist any outside attempts to turn the superintelligence off or otherwise prevent its subgoal completion. In order to prevent such an
This link is hidden for visitors. Please Log in or register now.
, it is necessary to successfully solve the "
This link is hidden for visitors. Please Log in or register now.
" for the first superintelligence. The solution might involve instilling the superintelligence with goals that are compatible with human survival and well-being. Solving the control problem is surprisingly difficult because most goals, when translated into machine-implementable code, lead to unforeseen and undesirable consequences.

More info
This link is hidden for visitors. Please Log in or register now.
Download


 
Back
Top