Update README.md

README.md

@@ -25,9 +25,15 @@ skipping huge amounts of early pretraining using organized spectral attuned SVD
 There will be multiple capable patchworks, multiple capable potentials, and multiple capable substructure options
 each with their own benefits, own negatives, and own convergence speeds.
 
-The goal here, is to synthetic shape expand the structural invariance of systems like this, to introduce
+The current goal here, is to synthetic shape expand the structural invariance of systems like this, to introduce
 prefabricated utility-driven patchworks using SVD as a catalyst.
 
+The ultimate goal is to allow the system to learn independently and usefully from standard encoding techniques, as the SVD
+provides enough information. The information is just highly difficult to extract and use usefully without a specific
+architectural behavior involved.
+
+I'm working out every element.
+
 
 # geolip-svd-transformer API