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 Composer a fine tune of an existing open source base model?
Composer: Building a fast frontier model with RL
51–60 of 169 posts
Re: Composer: Building a fast frontier model with RL
#52Earlier quoted context omitted.
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.
Makes sense! I like that you guys are more open about it. The other labs just drop stuff from the ivory tower. I think your style matches better with engineers who are used to datasheets etc. and usually don't like poking a black box
Re: Composer: Building a fast frontier model with RL
#53Please keep the naming of your models sane, I'd like to know that composer 1 is the first model and composer 2 is second but composer 1o is not yet another 1 variant that's actually newer and better than 2, that's just dumb. Not that you're doing that, some other companies do that.
Re: Composer: Building a fast frontier model with RL
#54Earlier quoted context omitted.
This is the exact reason I left Cursor for Claude Code. Night and day difference in reliability. The Windows experience might be especially bad, but it would get constantly hung or otherwise fail when trying to run commands. I also had to babysit Cursor and tell it to continue for mid sized tasks.
They've improved performance dramatically in the last few weeks, might have fixed your issues.
Its clear they've been shipping a lot of windows updates.
Re: Composer: Building a fast frontier model with RL
#55Hi 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.
Which model did you distill it from? Great work! PS getting a few scenarios where it doesn't follow rules as well as sonnet 4.5
Re: Composer: Building a fast frontier model with RL
#56Hi 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 Composer a fine tune of an existing open source base model?
Our primary focus is on RL post-training. We think that is the best way to get the model to be a strong interactive agent.
Re: Composer: Building a fast frontier model with RL
#57Cursor has the best Tab model, and I feel like their lead there has kept growing - they're doing some really cool things there. https://cursor.com/blog/tab-rl I wonder how much the methods/systems/data transfer, if they can pull off the same with their agentic coding model that would be exciting.
It's great. BUT: Wish they had selected another shortcut like shift+tab. Every time I write code myself I find myself racing the AI to get an indentation in before the AI is done... gets annoying
You can change the key bind, I personally set it to ctrl+tab
Re: Composer: Building a fast frontier model with RL
#58Could anyone explain how to use multiple agents and subagents in Cursor, Claude Code, or others? It is already challenging to me taming one model doing work, let alone synchronizing multiple parallel workers.
Do you have to split the plan in parallelizable tasks that could be worked in parallel in one codebase without breaking and confusing the other agents?
Re: Composer: Building a fast frontier model with RL
#59Earlier quoted context omitted.
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
It's not good enough for a lot of us, though, clearly.
Re: Composer: Building a fast frontier model with RL
#60is Cursor Bench open? Would like to see an open benchmark for agentic coding