WOW I think it’s just amazing!
“So in theory we could hand it off to human philosophers or some other human-based procedure, thus dealing with “complexity of value” without much risk.”
*That could simply be handled by producing more complexity than entropy in replication pdf
“Then we could launch a powerful AI aimed at rebuilding reality to match it (more concretely, making the world’s conscious experiences match a specific coarse-grained VR utopia, without any extra hidden suffering). That’s still a very hard task, because it requires solving decision theory and the problem of consciousness, but it seems more manageable than solving friendliness completely.”
*In a coarse-grained virtual reality where everything is built from polygons and textures consciousness could be quantized trough Stone’s representation theorem or Heyting algebra as symbols that represent themselves by way of symmetry.
“The resulting world would be suboptimal in many ways, e.g. it wouldn’t have much room for science or self-modification.”
*It will have room for science as the predictor of thermodynamic cost. Really the trick by which coarse-grained VR utopia might just work is because of a process called “refrigeration by randomizing a bit” and “adiabatic demagnetization”.
In a nutshell,
We can measure and predict the thermodynamic costs as a result of producing more complexity (a series of undeveloped modules that may or may not lead to functional specialization).
If the “coarseness” of the VR is obtained by randomizing a bit and using that bit as a refrigeration, well then we can blow the second law of thermodynamics.
Effectiveness of functional specialization in decreasing thermodynamic cost would be the golden rule that will avoid decision making or consciousness.
WOW I think it’s just amazing! “So in theory we could hand it off to human philosophers or some other human-based procedure, thus dealing with “complexity of value” without much risk.” *That could simply be handled by producing more complexity than entropy in replication pdf
“Then we could launch a powerful AI aimed at rebuilding reality to match it (more concretely, making the world’s conscious experiences match a specific coarse-grained VR utopia, without any extra hidden suffering). That’s still a very hard task, because it requires solving decision theory and the problem of consciousness, but it seems more manageable than solving friendliness completely.” *In a coarse-grained virtual reality where everything is built from polygons and textures consciousness could be quantized trough Stone’s representation theorem or Heyting algebra as symbols that represent themselves by way of symmetry.
“The resulting world would be suboptimal in many ways, e.g. it wouldn’t have much room for science or self-modification.” *It will have room for science as the predictor of thermodynamic cost. Really the trick by which coarse-grained VR utopia might just work is because of a process called “refrigeration by randomizing a bit” and “adiabatic demagnetization”.
In a nutshell,
We can measure and predict the thermodynamic costs as a result of producing more complexity (a series of undeveloped modules that may or may not lead to functional specialization).
If the “coarseness” of the VR is obtained by randomizing a bit and using that bit as a refrigeration, well then we can blow the second law of thermodynamics.
Effectiveness of functional specialization in decreasing thermodynamic cost would be the golden rule that will avoid decision making or consciousness.