If you start from terabytes of some of the highest quality orchestral recordings available, you have to work quite hard to make the output sound terrible.
It's a very nice demo piece, and vastly better than most of the NN efforts around.
But it still has the usual problem that it's sort-of-random orchestral wallpaper. Even if you create a workable grammar - by NN accident or design - you still have to solve the problem of intention and agency to generate music that isn't just mimicry or wallpaper.
I've heard some very, very good classical pastiche writing now - piano, chorales, orchestra - so it's essentially a solved problem technically.
Not so much artistically though.