Hello, I’ve been enjoying Cursor alot, it really transformed my workflow and speed, even though i’ve been doing this for over 10 years!
I do have a suggestion though, since now Cursor has so many options to choose from (And I hope you guys add Qwen 2.5 Max too, the way it suggests answers is far more clean than anything else I tested except for DS-R1, o3 mini so lazy),
there are just alot of models to choose and it can get confusing to know which one to use depending on the tasks.
For example, I love the way DeepSeek R1 gives good explanations to concepts, Claude gives better completion at speed and quick refactors, and I give o3 more difficult logic patterns.
It would be nice if there was a small explanation as to which model is likely to give good answers to certain topics or requests, so users have to guess less which model is the best fit or which is more likely to give them what they want.
I envision it as a small tooltip popup when you hover over the models selecting them, with a more advanced implementation being a flag to enable context-switching to a different model based on interpretation of the request.
Until we actually have AGI, this is the best solution to maximize the output of each model and maybe also share some of the load.