Yeah many rough edges indeed. The generated SQL is the plain output from GPT-3; I have not done anything to customize the model or validate syntax outside it, so the roughness is expected. No idea if folks will find value in this despite that, hence the demo.
Definitely passes the 'is it interesting' test. Certainly passes the 'should dig deeper' gate. Well done. I like to think I have a solid sql understanding but it's also nice to be able to ask questions in a natural language.
I'm still amazed that I can type a natural language phrase into google and often get sensible results.