>For me, the real question is what exactly is GPT-4 going to be able to do.

Yep, this is the burning question. Since it will have the most SOTA scaling methods/tuning, if it's a much larger scale model than GPT3, we will may be able to extrapolate a lot better on where we're headed with subsequent models in the future. We currently don't really have any baseline to compare outside of GPT2 to 3 which isn't really that useful to compare anymore.