I work on compilers. A friend of mine works on webapps. I've seen Cursor give him lots of useful code, but it's never been particularly useful on any of the code of mine that I've tried it on.
It seems very logical to me that there'd be orders of magnitude more training data for some domains than others, and that existing models' skill is not evenly distributed cross-domain.
It seems very logical to me that there'd be orders of magnitude more training data for some domains than others, and that existing models' skill is not evenly distributed cross-domain.