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

101–110 of 169 posts

Re: Composer: Building a fast frontier model with RL

#101

Post by gabriel666smith »

srush wrote: post #76
asdev wrote: post #60

is Cursor Bench open? Would like to see an open benchmark for agentic coding

Unfortunately not, as we used our own internal code for the benchmark. We would also like to see more benchmarks that reflect the day-to-day agentic coding use.

Is there any information at all available, anywhere, on what Cursor Bench is testing and how?

It's the most prominent part of the release post - but it's really hard to understand what exactly it's saying.

Re: Composer: Building a fast frontier model with RL

#102

Post by timcobb »

matheist wrote: post #4
romanovcode wrote: post #3

Where is the comparison with Sonnet 4.5? That would be the only thing that matters, really.

> "Best Frontier" includes GPT-5 and Sonnet 4.5, which both outperform Composer.

Does anyone code with GPT-5? I've never had it work in Cursor. I mean, like, at all.

Re: Composer: Building a fast frontier model with RL

#105

Post by camdenreslink »

vidarh wrote: post #31
jonasnelle wrote: post #12

Cursor 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.

I feel like that's like having a lead in producing better buggy whips. I run Claude Code in the background near constantly for a variety of projects, with --dangerously-skip-permissions, and review progress periodically. Tabbing is only relevant when it's totally failing to make progress and I have to manually intervene, and that to me is a failure scenario that is happening less and less often.

What are you building with this workflow? Is it an application live in production with users? It is such a foreign way of working to me.

Re: Composer: Building a fast frontier model with RL

#106

Post by smg »

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.

Can you please tell us more about how you used Ray for setting up the RL infrastructure?

Re: Composer: Building a fast frontier model with RL

#107

Post by netcraft »

I love cursor, the tab completion and agent mode. But I really dislike vscode after using intellij for so many years. I really wish the underlying editor was better, or I could get cursor features in intellij instead. The editing of the files is mostly fine, but its everything else around it that a full IDE provides thats just so much better. Right now its intellij + claude code for me, and its fine, but I wish I could get the AI power of cursor in a better package.

Re: Composer: Building a fast frontier model with RL

#108

Post by infecto »

enraged_camel wrote: post #87
infecto wrote: post #68

Earlier quoted context omitted.

Auto is pretty amazing and I think most folks that have issues or complain about cost are simply not using Auto.

Auto is only good for trivial stuff at this point. It is quite subpar at everything else. Th is is probably because it almost always defaults to Claude Sonnet 3.5 (which you can tell if you ask the agent to identify itself and tell you its version), and that is pretty outdated.

Again it goes back to what your workflow is. I don’t think trivial is the right word. I use auto to write fairly advanced code but I do it in bite size chunks or relatively bite size. So thinking function level or a couple of interdependent functions ruins being written.

I would agree it is not as good on doing lengthy work where it’s taking design all the way through implementing a feature in a single shot but trivial is not a good description.

I also don’t think you’re right. 3.5 was recently deprecated and even before then, Cursor has been hitting rate limits with Anthropic. Auto is as much a token cost optimization as it is a rate limit optimization.

Re: Composer: Building a fast frontier model with RL

#110

Post by infecto »

lubujackson wrote: post #88
infecto wrote: post #68

Earlier quoted context omitted.

Auto is pretty amazing and I think most folks that have issues or complain about cost are simply not using Auto.

Auto had a big improvement a few weeks ago (around when pricing changed)

If a few weeks is months I would agree I think the change to Auto was 2-3+ months ago when they moved to charging named models and higher limits on Auto.
Post reply on HN