Sorry, one other thing, as an actual AI researcher:
These generative models, whether NLP or vision, are cool but are really examples from a very narrow field. Most ML researchers and practitioners are working in completely different areas and would not obviously benefit from the new generative models (which are themselves prodictized extensions of existing tech trained on more data) so nothing's going to change day-to-day. If you were working on some alternative general purpose generative model, maybe you got scooped. Otherwise it's business as usual.
The "revolution" is happening for tech savvy non-ML people, "tech-bros" colloquially.
These generative models, whether NLP or vision, are cool but are really examples from a very narrow field. Most ML researchers and practitioners are working in completely different areas and would not obviously benefit from the new generative models (which are themselves prodictized extensions of existing tech trained on more data) so nothing's going to change day-to-day. If you were working on some alternative general purpose generative model, maybe you got scooped. Otherwise it's business as usual.
The "revolution" is happening for tech savvy non-ML people, "tech-bros" colloquially.