Totally makes sense. Data is so messy in real life and constantly changing like you mentioned in that post. AI will have a tough time with it. I've also noticed that unlike other problems like SQL there isn't a huge knowledge base around dara modeling out there. So I wonder if it struggles even more because of that as well
Probably! It's a hard thing to learn outside of actually doing the work. Theoretical is one thing but real data problems are hard to measure and define.
Totally makes sense. Data is so messy in real life and constantly changing like you mentioned in that post. AI will have a tough time with it. I've also noticed that unlike other problems like SQL there isn't a huge knowledge base around dara modeling out there. So I wonder if it struggles even more because of that as well
Probably! It's a hard thing to learn outside of actually doing the work. Theoretical is one thing but real data problems are hard to measure and define.
Everything NLP is a superpower right now while the industry is mesmerized by mediocrity.
Love this. Have you come across an example where AI said something incorrect wrt data modeling?
Thanks Moiz! I wouldn’t say “incorrect” because I’ve given it a lot of context on what data models should look like, especially with grain.
It’s more so important things that it forgets to include unless I specifically specify.
I imagine if I haven’t given it all the details that I do, that it would spit out something wrong.
I have a use case in a previous article where I talk about using Cursor for data modeling and that goes into all its weaknesses.