I want to say something because it concerns an executive decision Cursor made recently with its new model.
Cursor 1.5 was an epiphany! It showed perfect understanding, it worked thoroughly through any task at hand, and delivered what it was asked to deliver. It examined extensively codebase and showed concern and will to provide grounded answers and solutions.
Cursor 2 is just an average approximation. I understand that it is cheaper, and that strategically an expensive model is not a good choice for a vendor model, but… It is not like 1.5, and definitely not better.
Cursor 2 is spending a ridiculously large amount of tokens in thinking garbage (thankfully we can only see a few things from this). It also has a lot of attitude - yes in some cases it is for safety, which is not always bad, but for matters of architecture it gets on the way and I have to change model just to proceed with implementation of my directions.
I do a ton of iteration rather then really big plans and tasks. When i first started using composer 2 it felt like it had not been as good. I’ve started using it for more and more and even planning. Its really hard to say its much better then composer 1.5 but its still quite good.
I’ve had claude models give broken changes more lately.
I use convex + nextjs a lot so i think this may be highly dependent on how good your existing DX is.
The team is actively collecting feedback on Composer 2 in the official thread: Share your experience with Composer 2!. If you have specific examples where Composer 2 performs worse than 1.5 like prompt types or the kind of pushback it gives, it’d be really helpful to share them there. The more specific the examples, the easier it is for the team to prioritize improvements.
About the “attitude” on architecture decisions, for now the workaround is what you’re already doing, switch to another model for those tasks. In agent mode you can choose Claude or GPT for requests that need strict instruction following.
Composer 1.5 was replaced by Composer 2 Fast, so going back isn’t possible. But your feedback is being tracked, and the team knows some users felt 1.5 worked better for them.
I completely agree. I have given a long try and still trying to use Composer 2 but its just not it, I do not care about the bench scores and random bars, students cheat all the time, numbers on a chart means nothing I say all that because my own experience is ruined compared to the 1.5. From the way it explains and converses with you to clarity of actions and understanding the 1.5 was by far way superior model than the 2.0. That being said, I am not using the model only as an agentic grunt, but as a partner in thinking about ideas and understanding the implementation details and pros and cons. I returned back to composer 1.5 (you can do that form the add models and add it to the list again) but Cursor is spamming you with a pop-up that 1.5 being retired all the time, which if it happens and I cannot actually use it, I will be really sad. Also another thing to add: The Composer 2.0 is literally a rude AI that will fight with you and tell you to not talk to him in a specific way and try to give you a lesson in how to talk to him or not.
Hey @Supsy, thanks for the feedback. The team knows that some users preferred 1.5, and we’re actively collecting this kind of feedback.
About Composer 1.5 via Add Models, it’s being phased out and will be fully replaced by Composer 2, so the pop-up is expected. Unfortunately, 1.5 won’t be a long-term option.
If you have specific examples where Composer 2 is worse, like task types, error patterns, or pushback on architectural decisions, it’d be really helpful to share them in the official thread: Share your experience with Composer 2!. Concrete cases help the team prioritize improvements.
For tasks that need strict instruction following, you can switch to Claude or GPT in agent mode for now.