Similar experience, I try so hard to make AI useful, and there are some decent spots here and there. Overall though I see the fundamental problem being that people need information. Language isn't strictly information, and the LLMs are very good at language, but they aren't great at information. I think anything more than the novelty of "talking" to the AI is very over hyped.

There is some usefulness to be had for sure, but I don't know if the usefulness is there with the non-subsidized models.

Perhaps we could help if you shared some real examples of what walls you’re hitting. But it sounds like you’ve already made up your mind.

Do you mean that you have successfully managed to get the same experience in cursor but in neovim? I have been looking for something like that to move back to my neovim setup instead of using cursor. Any hints would be greatly appreciated!

It's worth actually trying Cursor, because it is a valuable step change over previous products and you might find it's better in some ways than your custom setup. The processes they use for creating the context seems to be really good. And their autocomplete is far better than Copilot's in ways that could provide inspiration.

That said, you're right that it's not as overwhelmingly revolutionary as the internet would lead you to believe. It's a step change over Copilot.

The entire wrapped package of tested prompts, context management etc. is a whole step change from what you can build yourself.

There is a reason Cursor is the fastest startup to $100M in revenue, ever.