I still use Cursor and am still very happy with it.

I've found the grok-4.5+ variants to be quite suitable for powerhouse work, and I have a legacy plan with a Third Party model allowance, so I can throw the occasional harder planning tasks at e.g. Fable when needed.

I like that I can run any model from the major labs (or anything on Bedrock), instead of being fully tethered to a single vendor. I'll occasionally run the same task through several models/vendors to understand what's most cost effective to achieve a given outcome (and also to keep my grok calls -- which are very cheap through Cursor -- honest and within the limits of what it can do well).

I run most tasks through Cloud agents, with exceptions for Mac-native stuff (iOS builds, app store I/O etc).