The claim that somehow LLMs as they stand are somehow the answer is disturbing. ChatGPTs ability to be authoritatively wrong is a serious problem…
Just to see what it would do, I gave it a basic word problem the other day (two people drive towards each other) and it had the steps right, but buried in it was a simple logic error (it claimed that the two parties traveling at different speeds would travel the same distance in a unit of time).
That it was good enough to seem trustworthy, made it worse…
Absolutely! I spent 20+ happy years in academia. I loved research, I loved working with grad students. Were it not for the funding changes and the retirement of my faculty, I hope I would still be there now.
If you are interested in approaches to combining programming language and database semantic. There is a bunch of work in this area from the 80s… Look up “Persistent Programming” and “Database Programming Languages” (DBPL).
In 1909 E.M. Forster published “The Machine Stops” a dystopian vision of a world where nobody ever leaves their individual rooms, and instead interacts solely through “the machine.” 1909!
Neuromancer, The Matrix, the list goes on… Plenty of prior art, and somebody still thinks this is a good idea!?