Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Composer: Building a fast frontier model with RL

cursor.com

Post reply on HN
Print view View original

71–80 of 169 posts

Re: Composer: Building a fast frontier model with RL

#71

Post by infecto »

pqdbr wrote: post #15
solarkraft wrote: post #10

People on here love to be contrarian about Cursor, but I’ve tried all the popular alternatives (Copilot, Claude Code, Codex, Gemini CLI, Cline) and found Cursor’s overall experience to just be unmatched. A big part of that is its speed, another its reliability. It’s the only coding agent I’m actually really motivated to use out of the box because it really does make me feel more productive while the others keep messi…

I dropped cursor for the precise reason you mention: reliability. Countless times my requests in the AI chat just hang there for 30+ seconds more until I can retry them. When I decided to give Claude Code a try (I thought I didn't need it because I used Claude in Cursor) I couldn't believe how faster it was, and literally 100% reliable. EDIT: given today's release, decided to give it a go. The Composer1 model _is_ fa…

Sounds like you have a network problem. Did you try checking the network diagnostic in settings? They default to http2 which can throw a wrench in some corporate networks.

I would be willing to bet money your issue is on your side. I am a daily user since the beginning and cannot recall when I have had issues like you describe unless it was related to my corp network.

Re: Composer: Building a fast frontier model with RL

#72

Post by chis »

srush wrote: post #64
chaidhat wrote: post #55

Earlier quoted context omitted.

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

The blog talks about the training process. Specifically we trained with RL post-training on coding examples.

Makes sense, but what model was used for the base? Is it some open-source model, and you're not at liberty to disclose?

Re: Composer: Building a fast frontier model with RL

#73

Post by carlosbaraza »

srush wrote: post #48
dfltr wrote: post #45

Earlier quoted context omitted.

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.

This is nice. I liked Cheetah for grunt work that I want to get out quickly and is not too hard. The speed is really awesome. A model that would run at even higher speeds like the OSS models at groq/cerebras would really be workflow changing, because the slowness of SOTA models really breaks the flow. I find myself taking a ton of breaks and getting distracted while I wait for a model to complete a task (e.g. just now).

Re: Composer: Building a fast frontier model with RL

#74

Post by MysticFear »

srush wrote: post #16

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.

There is a youtube livestreamer building with it now, if you are looking for direct feedback: https://www.youtube.com/watch?v=1bDPMVq69ac

Re: Composer: Building a fast frontier model with RL

#77

Post by srush »

numbers wrote: post #53

Please 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.

We will do our best. Luckily I don't think there are major telecom companies called Composer-2.

Re: Composer: Building a fast frontier model with RL

#78

Post by srush »

jasonjmcghee wrote: post #42
srush wrote: post #22

Earlier quoted context omitted.

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!

Thanks! Yeah, been working here for 9 months now. Fascinated byt agentic coding both as a researcher and user.

Totally agree that "smart model" is the table stakes for usefulness these days.

Re: Composer: Building a fast frontier model with RL

#79

Post by carlosbaraza »

asdev wrote: post #66
carlosbaraza wrote: post #58

Could 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?

you can use git worktrees and just have multiple Claude Code terminal instances working on each worktree. That way they don't clash, just delete the worktree when the task is done.

I have never leveraged git worktrees... That is such a crazy useful tool that I am almost ashamed of not having researched it before. Git is such a beautiful piece of software.

Re: Composer: Building a fast frontier model with RL

#80

Post by srush »

OsrsNeedsf2P wrote: post #20

One thing no competitor is serious on is average response completion time. Cursor lapped everyone there

There are lots of good models we like here. But we agree that getting the right point on the smart+fast graph can make agentic coding feel really good.

(Cursor researcher)

Post reply on HN