Its agent is a lot worse than Cursor's in my experience so far. Even tab edits feel worse.
My understanding is that these are not custom models but a combination of prompting and steering. That makes Cursor's performance relative to others pretty surprising to me. Are they just making more requests? I wonder what the secret sauce is.
Yeah exactly. In all years of my experience I have seen different implementation of this which is hard to maintain. I hope this can help developers to keep their focus on the actual problems that they are solving.
Thanks. Please share your experience if you ended up using it. I will be more than happy to address any issues you might face or any concerns and suggestions you have.