Develop AI systems to efficiently learn new skills and solve open-ended problems, rather than depend exclusively on AI systems trained with extensive datasets
Reasoning doesn't guarantee an optimal solution (e.g. fewest transformations to output), but it should still generate a solution none the less.
As I think a little about some of the transformations we'd make on the holographically encoded input, I know that the set of operations I come up with will not be exhaustive.
The good thing is it still may be sufficient. Because you can chain operations to make larger operations, if we choose a good set of operations, we may be able to make all other operations using compositions of them.
Discover other posts like this one