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

31–40 of 169 posts

Re: Composer: Building a fast frontier model with RL

#31

Post by vidarh »

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.

Re: Composer: Building a fast frontier model with RL

#32

Post by vidarh »

swyx wrote: post #23
jasonjmcghee wrote: post #11

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

Yes? Because why should we settle for less now that it is available?

Re: Composer: Building a fast frontier model with RL

#33

Post by psygn89 »

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…

Yep, it just works seamlessly. Sure, it hangs sometimes, but their UI allows you to retry or undo changes to an earlier point in the conversation easily. The autocompletion is nice as well and pretty satisfying to tab through the small and menial things when refactoring.

Re: Composer: Building a fast frontier model with RL

#34

Post by srush »

stared wrote: post #8

While I am excited to see a new model, I am skeptical when there is so much vagueness - charts with "frontier models" without actually spelling out which ones, charts with no numbers (time axis, or in one chart - entirely).

There is a footnote that should help with the models. Training is a harder thing to report on, but roughly our finding here is that RL scales.

Re: Composer: Building a fast frontier model with RL

#35

Post by enraged_camel »

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.

Tab model is fantastic but I wish it was somehow aware of the conversation happening in the currently active AI chat session.

Re: Composer: Building a fast frontier model with RL

#36

Post by rtfeldman »

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’ve tried all the popular alternatives (Copilot, Claude Code, Codex, Gemini CLI, Cline)

Can't help but notice you haven't tried Zed!

Re: Composer: Building a fast frontier model with RL

#37

Post by solarkraft »

ramon156 wrote: post #27
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…

You tried Claude and still prefer cursor?

Absolutely. CC can be tuned to not do too much crap on its own, but even with the new extension its IDE integration and multi thread management are still significantly worse, as is its status reporting, which I find to be very important.

Also, somehow magically, I’ve found Cursor’s Auto mode to be significantly faster than the specific models I’ve tried, Claude being among them.

Re: Composer: Building a fast frontier model with RL

#38

Post by swyx »

swyx wrote: post #17

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

Re: Composer: Building a fast frontier model with RL

#39

Post by solarkraft »

jasonjmcghee wrote: post #11

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?

The reason I pulled out the comparison is to highlight how serious they are about all the important parts that make or break the AI coding experience - speed being very important to me. I’d rather catch my model doing the wrong thing quickly than having a higher chance of one-shotting it at the cost of having to do a lot of specification upfront.
Post reply on HN