The models might benefit you, but they do not benefit the Host websites that were scraped to feed you a result.
It's narrow take I think, let us say someone read my comment or blog, among others, and used that shape their understanding, and then by doing that, they offered better consultation, then should that person pay back every author, book and blog they read?
I don't understand what's the argument here, and also the same methods is used to give us open source models..
Enough with the IP maximalism, it's perfectly fine to extract non-copyrightable ideas from copyrighted works.