Part of the cleverness of GANs was to have found a way to train a neural network that generates data without explicitly modeling the probability density.
In a stats textbook, when you know that your training data comes from a normal distribution, you can maximize the MLE wrt the parameters, and then use that for sampling. That's basic theory.
In practice, it was very hard to learn a good pdf for experimental data when you had a training set of images. GANs provided a way to bypass this.
Of course, people could have said "hey let's generate samples without maximizing a loglikelihood first", but they didn't know how to do it properly, how to train the network in any other way besides minimizing cross-entropy (which is equivalent to maximizing loglikelihood).
Then GANs actually provided a new loss function that could be trained. Total paradigm shift!
I also found that the best system is having the first layer of folder organization be "which period of my time is this from?".
Conceptually, it's easier to think of "music from high school" than about the specific mix of subgenres from my playlist back then. Same for documents that I saved. Those ICQ logs from high school are there. They don't belong in the same folder as the stuff I wrote yesterday, even though they could be of a similar nature.
You could even write an article asking why that original article was even written, and it might make for more interesting content.