This is pretty much the conclusion I've come to as well. It's not good at being an autocomplete for entire chunks of your codebase. You lose the mental model of what is doing what, and exactly where. I prefer to use it as a personalized, faster-iterating StackOverflow. I'll ask it to give me a rundown of a concept I'm not familiar with, or for a general direction to point me in if I'm uncertain of what a good solution would be. Then I'll make the decision, and implement it myself. That workflow has worked out much better for me so far.
I use it the same way but cursor is constantly insisting on making code changes. Is there a trick to get it to introspect on the codebase without wanting to modify it?
I say something like "without making any code changes right now, investigate blah blah blah" and if I want more than just info "and propose a direction that I can look at", or sometimes give it a file to write a proposal into.
In Zed you can toggle between read-only and write modes at any point when using the agent. You can also create custom modes that allow the use of specific tools, editing only specific files, etc. Does cursor have a similar feature?
I don't have this experience. The mental mode might not be quite as strong, but if you always review the code given carefully, you will have a good pretty idea what is where and how things interact.
It seems to be analogous to just reading a concept, versus reading a concept and taking notes on it to solidify it further. Writing the code myself helps it all solidify in my brain.
