[HN Gopher] Composer: Building a fast frontier model with RL
       ___________________________________________________________________
        
       Composer: Building a fast frontier model with RL
        
       Author : leerob
       Score  : 157 points
       Date   : 2025-10-29 16:04 UTC (6 hours ago)
        
 (HTM) web link (cursor.com)
 (TXT) w3m dump (cursor.com)
        
       | ibash wrote:
       | Very cool, congrats!
        
       | romanovcode wrote:
       | Where is the comparison with Sonnet 4.5? That would be the only
       | thing that matters, really.
        
         | matheist wrote:
         | > _" Best Frontier" includes GPT-5 and Sonnet 4.5, which both
         | outperform Composer._
        
           | yodon wrote:
           | >> "Best Frontier" includes GPT-5 and Sonnet 4.5, which both
           | outperform Composer.
           | 
           | Looking at the graph, it would appear there's an implicit
           | "today" in that statement, as they do appear poised to equal
           | or surpass Sonnet 4.5 on that same benchmark in the near
           | future.
        
           | timcobb wrote:
           | Does anyone code with GPT-5? I've never had it work in
           | Cursor. I mean, like, at all.
        
             | srush wrote:
             | A lot of people use it! It scores very well on our
             | benchmarks, significantly better than Composer-1.
        
       | alyxya wrote:
       | I wonder if this custom model is trained on cursor users. There's
       | a lot of potential on how much better a custom model could be the
       | closer it is integrated with the product. Having the model learn
       | to adapt to different user preferences would make it stand out
       | compared to memoryless frontier models.
        
         | Sammi wrote:
         | The fact that you are wondering this is bad. You definitely
         | should know this. _ALL_ the online ai providers are training on
         | your data. They have more expensive enterprise plans if want to
         | opt out.
        
           | alyxya wrote:
           | I've generally seen providers allow you to opt in or out.
           | What may vary is what the default is and what they may offer
           | in exchange for using your data (perhaps they could offer
           | higher rate limits).
        
       | nu11ptr wrote:
       | 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.
        
         | Sammi wrote:
         | 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 jumping in with useless
         | suggestions. They have a snooze function for this though.
        
           | WanderPanda wrote:
           | Damn TIL, I always used > Cursor: disable completions and
           | forgot to turn it on again I need to try snooze then!
        
       | stared wrote:
       | 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).
        
         | srush wrote:
         | 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.
        
       | solarkraft wrote:
       | 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 messing up the project, from way
       | too large changes I didn't ask for all the way to constant syntax
       | and request errors.
       | 
       | It's the only coding agent I've used that feels serious about
       | being a product rather than a prototype. Their effort in
       | improving their stack is totally paying off.
        
         | pqdbr wrote:
         | 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_ fast, but right at the second new agent I
         | started I got this:
         | 
         | > Connection failed. If the problem persists, please check your
         | internet connection or VPN
        
           | davidgomes wrote:
           | A lot of progress is being made here on the Cursor side I
           | encourage you to try it again.
           | 
           | (Cursor dev)
        
           | cleak wrote:
           | 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.
        
             | jonasnelle wrote:
             | They've improved performance dramatically in the last few
             | weeks, might have fixed your issues.
        
               | hobs wrote:
               | Its clear they've been shipping a lot of windows updates.
        
           | chasebank wrote:
           | I use cursor daily, my business partner uses CC. Without a
           | doubt, CC is certainly better, I'm just not willing to let go
           | of the flow I spent the last year fine tuning. I'll probably
           | make the leap after we finish the latest release.
        
           | infecto wrote:
           | 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.
        
         | ramon156 wrote:
         | You tried Claude and still prefer cursor?
        
           | solarkraft wrote:
           | 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.
        
             | infecto wrote:
             | Auto is pretty amazing and I think most folks that have
             | issues or complain about cost are simply not using Auto.
        
               | enraged_camel wrote:
               | 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.
        
               | infecto wrote:
               | 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.
        
               | lubujackson wrote:
               | Auto had a big improvement a few weeks ago (around when
               | pricing changed)
        
               | infecto wrote:
               | 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.
        
           | infecto wrote:
           | Absolutely. I actually don't understand the preference folks
           | have for Claude code. I don't find it that powerful. That
           | said, I think some of it comes down to preference and work
           | context.
        
         | psygn89 wrote:
         | 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.
        
         | rtfeldman wrote:
         | > I've tried all the popular alternatives (Copilot, Claude
         | Code, Codex, Gemini CLI, Cline)
         | 
         | Can't help but notice you haven't tried Zed!
        
         | infecto wrote:
         | I too have tried them all and have settled with Cursor being
         | the best. That said I see the current space split between folks
         | like me who know generally what I want built and appreciate a
         | tool that helps me get to goal quicker and on the otherwise of
         | the spectrum, folks who want the tool to orchestrate most of
         | the engineering. I have no opinion on which is better but for
         | me I sit on the first camp. In that camp Cursor is by far the
         | best tool.
        
       | jasonjmcghee wrote:
       | 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?
        
         | srush wrote:
         | Agree that Sonnet 4.5 is an excellent model. Would be curious
         | to hear your experience using Composer though, it's quite good.
        
           | jasonjmcghee wrote:
           | 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!
        
             | srush wrote:
             | 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.
        
         | swyx wrote:
         | > 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
        
           | vidarh wrote:
           | Yes? Because why should we settle for less now that it is
           | available?
        
             | swyx wrote:
             | 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
        
               | vidarh wrote:
               | It's not good enough for a lot of us, though, clearly.
        
           | jasonjmcghee wrote:
           | 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)
        
         | solarkraft wrote:
         | 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.
        
         | alyxya wrote:
         | 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.
        
           | jasonjmcghee wrote:
           | I'm very solidly in the second group - but I review all the
           | code. If it writes faster than I can read, that's fast
           | enough.
        
         | timcobb wrote:
         | Same... I've found that using a non-Claude model just ends up
         | being more expensive and not worth it. "Auto" tokens are hardly
         | free, and I've had plenty of experiences putting "Auto" to work
         | on a "simple" seeming task to have it consume like 1 USD of
         | tokens quite quickly while producing nothing of value, when I'd
         | replay with Claude 4.5 Sonnet non-thinking and it would provide
         | a solid solution for 0.5 USD.
        
         | NaomiLehman wrote:
         | gpt-5-high is as low as i can go :]
        
       | jonasnelle wrote:
       | 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.
        
         | srush wrote:
         | We also are big Tab users here at Cursor. In the blog we talk
         | about the motivation for this project came from thinking about
         | a Tab-like agent.
        
         | dagss wrote:
         | 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
        
           | RosalieCodes wrote:
           | You can change the key bind, I personally set it to ctrl+tab
        
         | vidarh wrote:
         | 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.
        
           | lubujackson wrote:
           | This is just a completely different use of LLMs and has
           | little to do with working at a real business with a live site
           | and users. Cursor is great when you want to gain
           | understanding of an issue quickly, or resolve something clear
           | and specific quickly.
           | 
           | I'm not against YOLO vibe coding, but being against tab
           | completion is just insane to me. At the end of the day, LLMs
           | help you achieve goals quicker. You still need to know what
           | goal you want to achieve, and tab completion basically let's
           | me complete a focused goal nearly as soon as I determine what
           | my goal is.
        
             | vidarh wrote:
             | Some of these projects are at a "real business with a live
             | site and users". Two of the current ones are.
             | 
             | And it's not remotely "YOLO vibe coding". All the code gets
             | reviewed, and tested thoroughly, and they are worked to
             | specs, and gated by test suites.
             | 
             | What I don't do is babysit the LLM until it's code passes
             | both the test suite _and_ automated review stages, because
             | it 's a waste of time.
             | 
             | Others of these projects are research tasks. While I wrote
             | this comment, Claude unilaterally fixed a number of bugs in
             | a compiler.
        
           | camdenreslink wrote:
           | 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.
        
             | vidarh wrote:
             | A compiler (hobby project). A web application server
             | (tooling for my consultancy). An agentic framework to part-
             | automate end-to-end development of a large web app
             | (customer project). An analytics platform to analyze
             | infrastructure maturity (customer project).
             | 
             | Usually I'll have several Claude Code sessions running in
             | parallel on different projects, and when one of them stops
             | I will review the code for that project and start it again
             | - either moving forwards or re-doing things that have
             | issues.
        
         | enraged_camel wrote:
         | Tab model is fantastic but I wish it was somehow aware of the
         | conversation happening in the currently active AI chat session.
        
       | kilroy123 wrote:
       | What I can't stand about cursor is the constantly changing and
       | confusing billing and usage.
       | 
       | I think competition in the space is a good thing, but I'm very
       | skeptical their model will outperform Claude.
        
       | srush wrote:
       | 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.
        
         | alyxya wrote:
         | Is the new model trained from scratch? What training data went
         | into it?
        
         | dfltr wrote:
         | Is it true that Cheetah is Grok Code Fast 2? Does this mean
         | that the new Cursor model is also based on Grok?
        
           | srush wrote:
           | 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.
        
             | dfltr wrote:
             | Awesome, thanks for the clarification. So are the rumors
             | around Cheetah being based on a Grok model just straight up
             | untrue? I want to try Composer but have a pretty strict no
             | X/Grok policy.
        
               | srush wrote:
               | Straight up untrue.
        
             | carlosbaraza wrote:
             | 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).
        
               | srush wrote:
               | Let us know how you like it.
        
         | WanderPanda wrote:
         | 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
        
           | srush wrote:
           | We did a lot of internal testing and thought this model was
           | already quite useful for release.
        
             | WanderPanda wrote:
             | 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
        
               | srush wrote:
               | Thanks! I do like the labs blog posts as well though,
               | OpenAI and Anthropic have some classics.
        
         | pdeva1 wrote:
         | is Composer a fine tune of an existing open source base model?
        
           | srush wrote:
           | 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.
        
             | comex wrote:
             | So, yes, but you won't say what the base model is? :)
        
         | chaidhat wrote:
         | 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
        
           | srush wrote:
           | The blog talks about the training process. Specifically we
           | trained with RL post-training on coding examples.
        
             | chis wrote:
             | Makes sense, but what model was used for the base? Is it
             | some open-source model, and you're not at liberty to
             | disclose?
        
             | chaidhat wrote:
             | that's cool thanks!
        
         | MysticFear wrote:
         | There is a youtube livestreamer building with it now, if you
         | are looking for direct feedback:
         | https://www.youtube.com/watch?v=1bDPMVq69ac
        
           | srush wrote:
           | neat!
        
         | carlosbaraza wrote:
         | How do you work with multiple agents?
        
           | srush wrote:
           | We train with a single agent. is that the question?
        
         | az226 wrote:
         | How many times have you needed to reset the optimizer during
         | the RL training cycles?
        
         | juanma0216 wrote:
         | I prefer the approach of focusing on faster models despite
         | their lower intelligence because I want my IDE to fly when I
         | can see the code. I find this useful when I need to manually
         | debug something that any model is able to do, so I know it's
         | going to fail but at least it will fail fast. On the other
         | hand, if I need more intelligence I have my other CLI that
         | doesn't allow me to see the code but gets the planning and
         | difficult code done.
        
           | srush wrote:
           | Our view is that there is a now a minimal amount of
           | intelligence that is necessary to be productive, and that if
           | you can pair that with speed that is awesome.
        
         | smg wrote:
         | Can you please tell us more about how you used Ray for setting
         | up the RL infrastructure?
        
           | srush wrote:
           | Oh good question. Actually speaking at the Ray Summit next
           | week in SF so we will talk more about it. We used Ray
           | throughout the pipeline for running evals, for the RL
           | controller, for data collation, and for visualizations. One
           | tool we found helpful was Ray Data which let us easily scale
           | over data and run logs.
        
             | nvartolomei wrote:
             | Please share more about Ray Data use case.
        
               | srush wrote:
               | We use Ray data for our map-style processing jobs. For
               | example one tool have runs over all the rollouts from the
               | RL system and collects qualitative statistics to
               | understand which type of agent trajectories are being
               | reward, and what types of searches and terminal commands
               | are being made.
        
         | embedding-shape wrote:
         | Do you have any graphs handy that kind of replicates the one
         | used first in the blog post but a bit less ambiguous, maybe
         | without model grouping? I feel like it would have been a bit
         | more fair to include proper names, and individualize them
         | rather than group everything together by _something_ , and then
         | present your own model on its own.
        
         | coder543 wrote:
         | Impressive systems write-up. A question: if Composer is an RL
         | finetune on an open model, why keep weights closed? The edge
         | from a slightly better checkpoint erodes quickly in this
         | market, it's not a durable advantage. Composer protects
         | Cursor's margins from being squeezed by the big AI labs, but
         | that is true whether the weights are open or closed, and I
         | think Cursor would have more lasting benefit by generating
         | developer goodwill than from a narrow, short-lived advantage.
         | But, that's just my opinion. I personally find it hard to get
         | excited about yet-another proprietary model. GPT-5 and Sonnet
         | 4.5 are around when I need one of those, but I think the future
         | is open.
        
       | swyx wrote:
       | 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
        
         | swyx wrote:
         | 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
        
           | srush wrote:
           | We like the name Composer and were sad to see it go. Excited
           | to bring it back. (Agree Cheetah is a cool name too.)
        
       | OsrsNeedsf2P wrote:
       | One thing no competitor is serious on is average response
       | completion time. Cursor lapped everyone there
        
         | srush wrote:
         | 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)
        
       | 80hd wrote:
       | Insane velocity from the Cursor team. I wonder how they move so
       | fast?
        
         | srush wrote:
         | We don't wear shoes [1].
         | 
         | [1] https://www.businessinsider.com/no-shoes-policy-in-office-
         | cu...
        
           | timcobb wrote:
           | I would have thought it's because you use Cursor...
        
       | numbers wrote:
       | 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.
        
         | srush wrote:
         | We will do our best. Luckily I don't think there are major
         | telecom companies called Composer-2.
        
       | carlosbaraza wrote:
       | 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?
        
         | asdev wrote:
         | 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.
        
           | carlosbaraza wrote:
           | 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.
        
             | asdev wrote:
             | I built an open source project to make the whole workflow
             | easier: https://github.com/built-by-as/FleetCode
        
       | asdev wrote:
       | is Cursor Bench open? Would like to see an open benchmark for
       | agentic coding
        
         | srush wrote:
         | 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.
        
           | gabriel666smith wrote:
           | 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.
        
             | srush wrote:
             | Roughly, we had Cursor software engineers record real
             | questions they were asking models, and then had them record
             | the PR that they made that contained the result. We then
             | cleaned these up. That is the benchmark.
        
               | ukblewis wrote:
               | Which programming languages/tools/libraries did the teams
               | questions/code involve?
        
       | carlosbaraza wrote:
       | Cursor 2.0 keeps crashing on me while having an agent running and
       | opening the IDE part of the application. I might have to
       | rollback.
        
         | amilich wrote:
         | Hey - really sorry to hear this - could you email me
         | andrew@cursor.com? Here are 3 suggestions to try- 1. Reset your
         | settings.json - if shared with vscode, sometimes settings can
         | cause perf regressions 2. Could you try cmd-shift-p -> "capture
         | and send debugging data"? Will send us some profiling data to
         | debug 3. Clear your user data (will delete chats) as a last
         | resort - cmd-shift-p, "reveal user data," close the app, then
         | delete this folder and restart the app
        
       | neuronexmachina wrote:
       | For anyone else who was wondering, it looks like the within-
       | Cursor model pricing for Cursor Composer is identical to
       | gemini-2.5-pro, gpt-5, and gpt-5-codex:
       | https://cursor.com/docs/models#model-pricing
       | 
       | ($1.25 input, $1.25 cache write, $0.13 cache read, and $10 output
       | per million tokens)
        
         | lubujackson wrote:
         | I'm curious if their near-term expectation is that this is be
         | better than these models or is this a model they tend to use in
         | Auto mode, or if the focus is really if you want speed...? I
         | guess my question is why would I actively chose this over Auto?
        
       | cwyers wrote:
       | The lack of transparency here is wild. They aggregate the scores
       | of the models they test against, which obscures the performance.
       | They only release results on their own internal benchmark that
       | they won't release. They talk about RL training but they don't
       | discuss anything else about how the model was trained, including
       | if they did their own pre-training or fine-tuned an existing
       | model. I'm skeptical of basically everything claimed here until
       | either they share more details or someone is able to
       | interpedently benchmark this.
        
       | timcobb wrote:
       | I wish it was easy to find out how much it costs relative to
       | Claude :)
        
         | skeptrune wrote:
         | Facts. They really need to make pricing more clear across the
         | entire product.
        
         | sebdufbeau wrote:
         | As a stealth model, it was priced as $1.25M in / $10M out
         | 
         | Right now, it seems free when you are a Cursor Pro user, but
         | I'd love more clarity on how much it will cost (I can't believe
         | it'll be unlimited usage for subscribers)
        
       | Jayakumark wrote:
       | This looks like a model RLed on top of Qwen3-Coder or GLM 4.6 as
       | per their graph and foot note.
        
       | netcraft wrote:
       | 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.
        
         | Jcampuzano2 wrote:
         | Building off of VSCode was probably Cursors silver bullet and
         | the best decision they could have ever made.
         | 
         | It made migrating for everyone using VSCode (probably the
         | single most popular editor) or another vscode forked editor
         | (but at the time it was basically all VSCode) as simple as
         | install and import settings.
         | 
         | I do not think Cursor would have done nearly as well as it has
         | if it didn't. So even though it can be subpar in some areas due
         | to VSCodes baggage, its probably staying that way for a while.
        
           | netcraft wrote:
           | I dont disagree with anything you said. If I was in their
           | shoes, I would have done exactly the same thing.
           | 
           | Maybe my complaint is that I wish vscode had more features
           | like intellij, or that intellij was the open source baseline
           | a lot of other things could be built on.
           | 
           | Intellij is not without its cruft and problems, dont get me
           | wrong. But its git integration, search, navigation, database
           | tools - I could go on - all of these features are just so
           | much nicer than what vscode offers.
        
         | pbowyer wrote:
         | Intellij's tab-complete is coming along; it's hit and miss if
         | it will work but for similar edits I'm finding it picks up the
         | pattern quickly and I can tab - tab - tab to make them happen.
         | 
         | Still not up to Cursor standards though :)
        
       | simonw wrote:
       | Here's the Composer 1 pelican riding a bicycle:
       | https://static.simonwillison.net/static/2025/cursor-1-pelica...
        
         | jeffnv wrote:
         | honestly better than I expected
        
       ___________________________________________________________________
       (page generated 2025-10-29 23:01 UTC)