see also https://cursor.com/changelog/2-0 and https://cursor.com/blog/2-0 other links across the web: https://x.com/amanrsanger/status/1983581288755032320?s=46 https://x.com/cursor_ai/status/1983567619946147967?s=46
my very small nit is... why is the model called Composer?? of all things?? when there was already a Cursor Composer from 2024. Cursor Cheetah wouldve been amazing. reusing the Composer name feels like the reverse OpenAI Codex move haha
We like the name Composer and were sad to see it go. Excited to bring it back. (Agree Cheetah is a cool name too.)
Maybe I'm an outlier but Sonnet 4.5 quality is about as low as I'm willing to go. It's generation speed is not the problem or the time sink. It's wrestling with it to get the right output. --- And just to clarify as maybe I misunderstood again but people are comparing cursor to Claude Code and codex etc here- isn't this whole article all cursor just using different models?
Agree that Sonnet 4.5 is an excellent model. Would be curious to hear your experience using Composer though, it's quite good.
I'll try it out! I haven't yet - just generally conveying my opinion that I personally weigh "better model" much more important than speed, assuming some "fast enough"
Also, didn't realize you worked at Cursor - I'm a fan of your work - they're lucky to have you!
Maybe I'm an outlier but Sonnet 4.5 quality is about as low as I'm willing to go. It's generation speed is not the problem or the time sink. It's wrestling with it to get the right output. --- And just to clarify as maybe I misunderstood again but people are comparing cursor to Claude Code and codex etc here- isn't this whole article all cursor just using different models?
> Sonnet 4.5 quality is about as low as I'm willing to go. literally a 30 day old model and you've moved the "low" goalpost all the way there haha. funny how humans work
Yup - just like sibling comment said - my "low bar" is going to be whatever the best model is that isn't unreasonably costly/expensive.
Speed of model just isn't the bottleneck for me.
Before it I used Opus 4.1, and before that Opus 4.0 and before that Sonnet 4.0 - which each have been getting slightly better. It's not like Sonnet 4.5 is some crazy step function improvement (but the speed over Opus is definitely nice)
> Sonnet 4.5 quality is about as low as I'm willing to go. literally a 30 day old model and you've moved the "low" goalpost all the way there haha. funny how humans work
Yes? Because why should we settle for less now that it is available?
because engineering is the art of "good enough" and composer is clearly "good enough but a lot faster" which makes up for intelligence gaps in interesting ways
Hi everyone, I am an ML researcher at Cursor, and worked on this project. Would love to hear any feedback you may have on the model, and can answer question about the blog post.
Is it true that Cheetah is Grok Code Fast 2? Does this mean that the new Cursor model is also based on Grok?
Hi everyone, I am an ML researcher at Cursor, and worked on this project. Would love to hear any feedback you may have on the model, and can answer question about the blog post.
Why did you stop training shy of the frontier models? From the log plot it seems like you would only need ~50% more compute to reach frontier capability
Maybe I'm an outlier but Sonnet 4.5 quality is about as low as I'm willing to go. It's generation speed is not the problem or the time sink. It's wrestling with it to get the right output. --- And just to clarify as maybe I misunderstood again but people are comparing cursor to Claude Code and codex etc here- isn't this whole article all cursor just using different models?
There’s two different kinds of users, on one side people are more hands off and want the model to autonomously handle longer tasks on its own with minimal guidance, and on the other side is users who want to interactively collaborate with the model to produce desired results. Speed matters much more for the second case, where you know what you want and just want the model to implement whatever you had in mind as quick as possible. Intelligence/ability matters more for the first case when you don’t have full understanding of all the code. I think it’s context dependent for me where more serious work tends to be more interactive. The intelligence of a model doesn’t make up for issues due to lack of context to me.
Hi everyone, I am an ML researcher at Cursor, and worked on this project. Would love to hear any feedback you may have on the model, and can answer question about the blog post.
Is it true that Cheetah is Grok Code Fast 2? Does this mean that the new Cursor model is also based on Grok?
Cheetah was an earlier (and dumber) version of this model that we used to test production speed. They are both developed in-house. If you liked Cheetah, give this model a try.
I love Cursor. I've tried Copilot/Claude/etc. but keep coming back to Cursor. I just want to work, and Cursor tab complete is dang accurate, esp. for refactoring tasks.
I tried going back to VS Code + Copilot a month ago. I only lasted 4 days because it was to bad. It was super slow and gave poor suggestions, but mostly it just flat out did not suggest anything. Cursor feels snappy in comparison and the suggestions are more often than not useful. The most annoying thing about Cursor tab complete, is that it is so fast that when I am doing something unusual then it will keep on jumpi…
Damn TIL, I always used > Cursor: disable completions and forgot to turn it on again
I need to try snooze then!
Hi everyone, I am an ML researcher at Cursor, and worked on this project. Would love to hear any feedback you may have on the model, and can answer question about the blog post.
Why did you stop training shy of the frontier models? From the log plot it seems like you would only need ~50% more compute to reach frontier capability
We did a lot of internal testing and thought this model was already quite useful for release.