"Starting now"? How's about 5 to 10 years ago. This is being released free now, which indicates to me this is now disposable tech and the authors have much, much better in their labs.

Usually it's the other way around with ML researchers - what they show is better than what they have in the lab :)

Probably not; the GAN technique wasn't even published until 2014, and this is based on other work that's been done even more recently. The field moves fast and is more open than you might expect (because it's still so academic).

Not sure it works this way except in extremely specific areas of research (and I'm not even sure about that).

Publicly available research is usually the cutting edge in most areas of knowledge.