{"slug": "composer", "name": "Composer", "category": "ai", "category_name": "AI models and assistants", "description": "Cursor's in-house agentic coding model, fine-tuned from Kimi K2.5, available inside the Cursor editor.", "recommenders": 31, "commenters": 46, "warners": 8, "score": 22.453, "rising": -2.18, "first": "2025-11-18", "latest": "2026-09-26", "why": "Liked as a cheap, fast workhorse for small, well-scoped coding tasks, often implementing plans drafted by larger models.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 31, "neutral": 6, "compare": 1, "warn": 8}, "spark": [2, 0, 0, 0, 0, 2, 2, 11, 8, 2, 4, 0], "listed": true, "loved": ["Low cost", "Speed"], "caveat": "Complex tasks", "short_quote": "I find it really hard to justify the other models for the performance/cost I'm getting with Composer 2.5.", "icon": false, "domain": "cursor.com", "github_repo": null, "official_url": "https://cursor.com", "pricing": "freemium", "aliases": ["Composer 2.5", "Composer", "Composer 2", "Cursor Composer"], "verdict": [{"text": "Liked as a cheap, fast workhorse for small, well-scoped coding tasks", "cites": [{"id": 794776992, "item_id": 49673562, "url": "https://news.ycombinator.com/item?id=49673562", "by": "time0ut", "date": "2026-09-12", "stance": "recommend", "quote": "It is just a cheap, fast, surgical workhorse.", "excerpt": "If I had to pick just one, these days it\u2019s Composer. It is just a cheap, fast, surgical workhorse. My workflow uses other models as well for various phases: Opus for planning, Sonnet for review, etc. I prefer Cursor at this point just because of Composer. Claude Code is passable but the lack of a good, fast, cheap workhorse sucks. Sonnet and Haiku aren\u2019t it. I also do like Codex and Sol, Terra, and Luna. They are dec", "context": "", "use_case": "implementation", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 780117184, "item_id": 48757324, "url": "https://news.ycombinator.com/item?id=48757324", "by": "danfritz", "date": "2026-07-01", "stance": "recommend", "quote": "It's my daily driver, it's fast affordable and with a bit of guidance gets the job done.", "excerpt": "It's my daily driver, it's fast affordable and with a bit of guidance gets the job done. I only reach for Claud when i need to plan something big or want to have a sparring partner to fire of some ideas. I think what a lot of people don't realize is that you don't need a fronteer model for 80% of coding tasks. Composer 2.5 is often more than good enough, less token hungry and way faster", "context": "", "use_case": "daily coding", "switched_from": "", "story": "CursorBench 3.1"}, {"id": 775428416, "item_id": 48464276, "url": "https://news.ycombinator.com/item?id=48464276", "by": "vorticalbox", "date": "2026-06-09", "stance": "recommend", "quote": "for almost all the tasks i have given it, it has handled it perfectly well and is a lot cheaper.", "excerpt": "for the last few weeks I have been using composer 2.5 (cursors fine tune of kimi 2.5) and honestly i don't see it worth the price to use 5.5, opus or sonnet any more. for almost all the tasks i have given it, it has handled it perfectly well and is a lot cheaper. if I get a harder challenge for it i'll jump up a model for planning until that its been solid.", "context": "", "use_case": "coding tasks", "switched_from": "", "story": "Claude Fable 5"}, {"id": 797680064, "item_id": 49855004, "url": "https://news.ycombinator.com/item?id=49855004", "by": "the_other", "date": "2026-09-26", "stance": "recommend", "quote": "I do the bulk of my work with Composer 2.5. It\u2019s quite good for \u201cgoing forward\u201d on smallish tasks", "excerpt": "The last couple of weeks, I\u2019ve got rigorous about making the agent refactor old code. We\u2019ve removed, moved, consolidated, reordered loads of cruft. It has made the code much tidier and reduced the chance that the next feature will build on top of cruft. E.G. over time we\u2019d gained two client-side caches of related server state. This started out as two different parts of the same model, because we couldn\u2019t get all the ", "context": "employer provides limited LLM budget", "use_case": "daily coding tasks", "switched_from": "", "story": "Plan mode is dead"}, {"id": 776868512, "item_id": 48554282, "url": "https://news.ycombinator.com/item?id=48554282", "by": "senordevnyc", "date": "2026-06-16", "stance": "recommend", "quote": "I agree, Composer 2.5 is really good.", "excerpt": "I agree, Composer 2.5 is really good. I use it for all kinds of small tasks, and really for any kind of first pass at debugging, answering questions about the codebase, pulling data for reports, etc. It\u2019s fast, pretty accurate, and basically free.", "context": "", "use_case": "small tasks, debugging, codebase questions", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}]}, {"text": ", often implementing plans drafted by larger models.", "cites": [{"id": 796707840, "item_id": 49794240, "url": "https://news.ycombinator.com/item?id=49794240", "by": "the_sleaze_", "date": "2026-09-21", "stance": "recommend", "quote": "Composer 2.5 - which remains incredible and honestly nothing else compares for me", "excerpt": "I didn't find 4.6 any better than Composer 2.5 - which remains incredible and honestly nothing else compares for me. Make a galaxy model search the space, create a document, argue and defend decisions, then hand it to 2.5 to implement. 4.6 was a slower less enjoyable version of that. 4.7 is better at \"I want the button to cancel the jobs, dont make any mistakes\" but honestly that's not what I use it's class for.", "context": "", "use_case": "implementing plans from documents", "switched_from": "", "story": "Grok 4.7"}, {"id": 791794673, "item_id": 49487167, "url": "https://news.ycombinator.com/item?id=49487167", "by": "rippeltippel", "date": "2026-08-29", "stance": "recommend", "quote": "their free tier of Composer is good enough", "excerpt": "I may be a rare Cursor user around here, but I am saddened by this news. The thing that keeps me using it is precisely the ability to switch between models: I usually do brainstorm/planning with Sol or Terra, then let Composer (free) deal with the implementation. For certain tasks I use Claude, which tends to be more expensive but sometimes saves me time. Using both OpenAI and Anthropic models, Cursor is cheaper than", "context": "", "use_case": "implementation", "switched_from": "", "story": "Our decision on Cursor following its acquisition by SpaceX"}, {"id": 794776992, "item_id": 49673562, "url": "https://news.ycombinator.com/item?id=49673562", "by": "time0ut", "date": "2026-09-12", "stance": "recommend", "quote": "It is just a cheap, fast, surgical workhorse.", "excerpt": "If I had to pick just one, these days it\u2019s Composer. It is just a cheap, fast, surgical workhorse. My workflow uses other models as well for various phases: Opus for planning, Sonnet for review, etc. I prefer Cursor at this point just because of Composer. Claude Code is passable but the lack of a good, fast, cheap workhorse sucks. Sonnet and Haiku aren\u2019t it. I also do like Codex and Sol, Terra, and Luna. They are dec", "context": "", "use_case": "implementation", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 776508706, "item_id": 48531794, "url": "https://news.ycombinator.com/item?id=48531794", "by": "Implicated", "date": "2026-06-14", "stance": "recommend", "quote": "I use this as my 'fast' research & report", "excerpt": "I'm chime in here as another Pi user, starting with OMP and then just ditching it for vanilla Pi + MCP/LSP from OMP as well as pi-cursor-sdk to get access to Composer 2.5 through Pi. I use this as my 'fast' research & report (through my project/codebase) or boilerplate/tightly-specced implementation agent that's available to my planning/orchestrator (GPT 5.5 if complex backend work, Fable/Opus if wanting the extended", "context": "", "use_case": "fast research and boilerplate", "switched_from": "", "story": "Kimi K2.7-Code: open-source coding model with better token efficiency"}]}, {"text": " The most common complaint is shallow or error-prone output on complex tasks", "cites": [{"id": 780313664, "item_id": 48769604, "url": "https://news.ycombinator.com/item?id=48769604", "by": "Losenok", "date": "2026-07-02", "stance": "warn", "quote": "it is very fast, especially compared to anthropic models, but the result it produces, especially with more difficult tasks is very shallow.", "excerpt": "Very skeptical about the composer accuracy. I have been using it for 6 months now and it is very fast, especially compared to anthropic models, but the result it produces, especially with more difficult tasks is very shallow. It feels like it just finds the cheapest way to deliver the task.", "context": "using it 6 months", "use_case": "AI coding", "switched_from": "", "story": "CursorBench 3.1"}, {"id": 780997952, "item_id": 48812372, "url": "https://news.ycombinator.com/item?id=48812372", "by": "richkuo", "date": "2026-07-06", "stance": "recommend", "quote": "Incredibly token efficient, fast, and gets the same quality as if you worked the whole thing with Fable/Opus/GPT.", "excerpt": "Composer 2.5 is really effective at some tasks, but doesn't do as well on higher complexity tasks from my own experience. With that being said, Cursor Bench is nonetheless a fantastic gauge of LLM quality and performance. The most interesting outcome of Cursor Bench is Fable 5 to GPT 5.5, its almost a perfect continuous line. As of the report, Fable to GPT might be the new standard of agentic programming/building I d", "context": "open source maintainer", "use_case": "building code after planning", "switched_from": "", "story": "CursorBench 3.1"}, {"id": 761952658, "item_id": 47622041, "url": "https://news.ycombinator.com/item?id=47622041", "by": "athoscouto", "date": "2026-04-02", "stance": "recommend", "quote": "Now Composer 2 has taken over as my default model.", "excerpt": "Cursor has been my main AI tool for over a year now. I've been trying to use Claude Code seriously for over a month, but every time I do it, I get the impression that it would take me less work to do with Cursor. I'm on the enterprise plan, so it can get pricey. This is why I used to stick mostly to auto mode. Now Composer 2 has taken over as my default model. It is not as intelligent as OpenAI's or Anthropic's flags", "context": "", "use_case": "default coding model in Cursor", "switched_from": "", "story": "Cursor 3"}, {"id": 781370464, "item_id": 48835654, "url": "https://news.ycombinator.com/item?id=48835654", "by": "bhouston", "date": "2026-07-08", "stance": "warn", "quote": "Every time I use Composer 2.5 I have to spend a bunch of time cleaning up its mistakes.", "excerpt": "Every time I use Composer 2.5 I have to spend a bunch of time cleaning up its mistakes. It is unusable compared to GPT 5.4 or 5.5. My time is more valuable that I will use a model that doesn\u2019t f** up my code base.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Grok 4.5"}, {"id": 780265537, "item_id": 48766596, "url": "https://news.ycombinator.com/item?id=48766596", "by": "subhobroto", "date": "2026-07-02", "stance": "warn", "quote": "Composer hands me a quickly put together college project that was started the night before it was due.", "excerpt": "I'm not disputing what you're saying. The slowness of Opus in particular is pretty accurate but you should have been getting little popups in Cursor saying Opus is under load and to try switching to other models? I mentioned my frustration with Composer in another thread and why I rely on Opus, but Opus, atleast via Cursor is practically unusable for me M-F 9-5 EST. As a result, I have modified my working schedule ou", "context": "", "use_case": "AI coding via Cursor", "switched_from": "", "story": "CursorBench 3.1"}]}, {"text": ", so many users still switch to Opus or GPT for hard problems.", "cites": [{"id": 779824403, "item_id": 48739025, "url": "https://news.ycombinator.com/item?id=48739025", "by": "ifwinterco", "date": "2026-06-30", "stance": "recommend", "quote": "I use Composer (since we use Cursor) or GPT 5.3-codex as my workhorse models", "excerpt": "I prefer GPT 5.5 to Opus but both are absurdly expensive token hogs, I can't afford to use either as my main model at $work with the monthly spend cap we have. I use Composer (since we use Cursor) or GPT 5.3-codex as my workhorse models and only break out the big guns when I have a genuinely difficult problem to solve. IMO somewhat weirdly 5.3-codex might be the best overall coding model OpenAI have ever released. It", "context": "works under a monthly spend cap at work", "use_case": "main coding workhorse model", "switched_from": "", "story": "Claude Sonnet 5"}, {"id": 780117184, "item_id": 48757324, "url": "https://news.ycombinator.com/item?id=48757324", "by": "danfritz", "date": "2026-07-01", "stance": "recommend", "quote": "It's my daily driver, it's fast affordable and with a bit of guidance gets the job done.", "excerpt": "It's my daily driver, it's fast affordable and with a bit of guidance gets the job done. I only reach for Claud when i need to plan something big or want to have a sparring partner to fire of some ideas. I think what a lot of people don't realize is that you don't need a fronteer model for 80% of coding tasks. Composer 2.5 is often more than good enough, less token hungry and way faster", "context": "", "use_case": "daily coding", "switched_from": "", "story": "CursorBench 3.1"}, {"id": 775428416, "item_id": 48464276, "url": "https://news.ycombinator.com/item?id=48464276", "by": "vorticalbox", "date": "2026-06-09", "stance": "recommend", "quote": "for almost all the tasks i have given it, it has handled it perfectly well and is a lot cheaper.", "excerpt": "for the last few weeks I have been using composer 2.5 (cursors fine tune of kimi 2.5) and honestly i don't see it worth the price to use 5.5, opus or sonnet any more. for almost all the tasks i have given it, it has handled it perfectly well and is a lot cheaper. if I get a harder challenge for it i'll jump up a model for planning until that its been solid.", "context": "", "use_case": "coding tasks", "switched_from": "", "story": "Claude Fable 5"}, {"id": 780265537, "item_id": 48766596, "url": "https://news.ycombinator.com/item?id=48766596", "by": "subhobroto", "date": "2026-07-02", "stance": "warn", "quote": "Composer hands me a quickly put together college project that was started the night before it was due.", "excerpt": "I'm not disputing what you're saying. The slowness of Opus in particular is pretty accurate but you should have been getting little popups in Cursor saying Opus is under load and to try switching to other models? I mentioned my frustration with Composer in another thread and why I rely on Opus, but Opus, atleast via Cursor is practically unusable for me M-F 9-5 EST. As a result, I have modified my working schedule ou", "context": "", "use_case": "AI coding via Cursor", "switched_from": "", "story": "CursorBench 3.1"}]}], "praise": [{"label": "Low cost", "summary": "Commenters say it is much cheaper than frontier models, with generous usage limits, and still does the job.", "quotes": [{"id": 780262112, "item_id": 48766382, "url": "https://news.ycombinator.com/item?id=48766382", "by": "soyin", "date": "2026-07-02", "stance": "recommend", "quote": "I find it really hard to justify the other models for the performance/cost I'm getting with Composer 2.5.", "excerpt": "I'm also using it as my daily driver. I've been trying Opus 4.8 this week to see if I was missing something but haven't noticed a meaningful difference. I'm working on a fairly routine full stack web app that isn't doing anything incredible. Once I had the patterns I wanted in place, it's been very capable of following those with new work. I also don't ever give it long running tasks, it's always focused and small ch", "context": "working on a fairly routine full stack web app", "use_case": "full stack web app coding", "switched_from": "", "story": "CursorBench 3.1"}, {"id": 777034048, "item_id": 48564628, "url": "https://news.ycombinator.com/item?id=48564628", "by": "ghshephard", "date": "2026-06-16", "stance": "recommend", "quote": "that I use a lot of the time when I have fairly straightforward tasks", "excerpt": "You nailed it - in fact, most of Anthropic's early revenue came from Cursor - much of claude code programming components is essentially a feature copy of Cursor, so it makes sense they are similar. Cursor does have it's own model - it's a heavily reworked version of KimiK2, called \"composer\" - that I use a lot of the time when I have fairly straightforward tasks that don't require a lot of exploration or independent ", "context": "", "use_case": "straightforward coding tasks", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}, {"id": 791780433, "item_id": 49486277, "url": "https://news.ycombinator.com/item?id=49486277", "by": "charrondev", "date": "2026-08-29", "stance": "recommend", "quote": "price very competitively for their quality and have very generous usage limits", "excerpt": "I used cursor extensively both at work and for personal use. Its harness is pretty darn good but I basically never used OpenAI models in it. The first party cursor models (initially composer and now grok-cursor) and price very competitively for their quality and have very generous usage limits included in the base plans, and then per token pricing afterwards. Occasionally I\u2019ve used some of the Anthropic models in it ", "context": "", "use_case": "coding model", "switched_from": "", "story": "Our decision on Cursor following its acquisition by SpaceX"}]}, {"label": "Speed", "summary": "Commenters repeatedly describe it as very fast, including in comparison with Anthropic models.", "quotes": [{"id": 794776992, "item_id": 49673562, "url": "https://news.ycombinator.com/item?id=49673562", "by": "time0ut", "date": "2026-09-12", "stance": "recommend", "quote": "It is just a cheap, fast, surgical workhorse.", "excerpt": "If I had to pick just one, these days it\u2019s Composer. It is just a cheap, fast, surgical workhorse. My workflow uses other models as well for various phases: Opus for planning, Sonnet for review, etc. I prefer Cursor at this point just because of Composer. Claude Code is passable but the lack of a good, fast, cheap workhorse sucks. Sonnet and Haiku aren\u2019t it. I also do like Codex and Sol, Terra, and Luna. They are dec", "context": "", "use_case": "implementation", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 777084561, "item_id": 48567785, "url": "https://news.ycombinator.com/item?id=48567785", "by": "jemmyw", "date": "2026-06-17", "stance": "recommend", "quote": "Composer is actually really good, and fast.", "excerpt": "I didn't like cursor when it first came about but now I use it for my personal projects. The plan is good value for accessing different sota models occasionally for planning. Composer is actually really good, and fast. I'm not sure if it's because my personal projects are small enough I know them inside out and my work project is huge, but I prefer terminal code agents for day work over ide integration.", "context": "", "use_case": "", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}, {"id": 776893616, "item_id": 48555851, "url": "https://news.ycombinator.com/item?id=48555851", "by": "infecto", "date": "2026-06-16", "stance": "recommend", "quote": "I use it quite a bit and it works well and is extremely fast for the tasks it was built for", "excerpt": "Hmmm. Not in my experience. I don\u2019t think it can be compared to Haiku, maybe sonnet levels? It\u2019s obviously not Opus and never was intended for that use case. I use it quite a bit and it works well and is extremely fast for the tasks it was built for", "context": "", "use_case": "fast coding tasks", "switched_from": "", "story": "SpaceX Is Buying Cursor"}]}, {"label": "Daily driver", "summary": "Several users have made it their default model for everyday coding work.", "quotes": [{"id": 780117184, "item_id": 48757324, "url": "https://news.ycombinator.com/item?id=48757324", "by": "danfritz", "date": "2026-07-01", "stance": "recommend", "quote": "It's my daily driver, it's fast affordable and with a bit of guidance gets the job done.", "excerpt": "It's my daily driver, it's fast affordable and with a bit of guidance gets the job done. I only reach for Claud when i need to plan something big or want to have a sparring partner to fire of some ideas. I think what a lot of people don't realize is that you don't need a fronteer model for 80% of coding tasks. Composer 2.5 is often more than good enough, less token hungry and way faster", "context": "", "use_case": "daily coding", "switched_from": "", "story": "CursorBench 3.1"}, {"id": 776868065, "item_id": 48554254, "url": "https://news.ycombinator.com/item?id=48554254", "by": "senordevnyc", "date": "2026-06-16", "stance": "recommend", "quote": "Composer 2.5 is really solid", "excerpt": "Yes, it\u2019s my daily driver for building the saas I run full-time. I\u2019m not happy about this news. I like the ability to switch between any models, Composer 2.5 is really solid, I like having my agents coworking in the IDE with me, the plan mode is great, Cloud Agents are great, especially with slack, linear, web, etc integrations. I routinely tag an error report in slack and Cursor fires up a Composer 2.5 cloud agent t", "context": "runs a SaaS full-time", "use_case": "cloud agent issue triage", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}, {"id": 761952658, "item_id": 47622041, "url": "https://news.ycombinator.com/item?id=47622041", "by": "athoscouto", "date": "2026-04-02", "stance": "recommend", "quote": "Now Composer 2 has taken over as my default model.", "excerpt": "Cursor has been my main AI tool for over a year now. I've been trying to use Claude Code seriously for over a month, but every time I do it, I get the impression that it would take me less work to do with Cursor. I'm on the enterprise plan, so it can get pricey. This is why I used to stick mostly to auto mode. Now Composer 2 has taken over as my default model. It is not as intelligent as OpenAI's or Anthropic's flags", "context": "", "use_case": "default coding model in Cursor", "switched_from": "", "story": "Cursor 3"}]}, {"label": "Small tasks", "summary": "Seen as reliable for small, straightforward, focused changes.", "quotes": [{"id": 797680064, "item_id": 49855004, "url": "https://news.ycombinator.com/item?id=49855004", "by": "the_other", "date": "2026-09-26", "stance": "recommend", "quote": "I do the bulk of my work with Composer 2.5. It\u2019s quite good for \u201cgoing forward\u201d on smallish tasks", "excerpt": "The last couple of weeks, I\u2019ve got rigorous about making the agent refactor old code. We\u2019ve removed, moved, consolidated, reordered loads of cruft. It has made the code much tidier and reduced the chance that the next feature will build on top of cruft. E.G. over time we\u2019d gained two client-side caches of related server state. This started out as two different parts of the same model, because we couldn\u2019t get all the ", "context": "employer provides limited LLM budget", "use_case": "daily coding tasks", "switched_from": "", "story": "Plan mode is dead"}, {"id": 777034048, "item_id": 48564628, "url": "https://news.ycombinator.com/item?id=48564628", "by": "ghshephard", "date": "2026-06-16", "stance": "recommend", "quote": "that I use a lot of the time when I have fairly straightforward tasks", "excerpt": "You nailed it - in fact, most of Anthropic's early revenue came from Cursor - much of claude code programming components is essentially a feature copy of Cursor, so it makes sense they are similar. Cursor does have it's own model - it's a heavily reworked version of KimiK2, called \"composer\" - that I use a lot of the time when I have fairly straightforward tasks that don't require a lot of exploration or independent ", "context": "", "use_case": "straightforward coding tasks", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}, {"id": 735505584, "item_id": 45969099, "url": "https://news.ycombinator.com/item?id=45969099", "by": "chis", "date": "2025-11-18", "stance": "recommend", "quote": "impressively fast and able but not tuned to be that agentic, so it's better for one-shot code changes than long-running tasks.  Fantastic UI.", "excerpt": "Has anyone switched to Gemini CLI? It's so important but also exhausting keeping up with which model is the leading edge. Especially since every model has different idiosyncrasies you have to learn to work with it effectively. Currently my ranking is * Cursor composer: impressively fast and able but not tuned to be that agentic, so it's better for one-shot code changes than long-running tasks. Fantastic UI. * Claude ", "context": "", "use_case": "one-shot code changes", "switched_from": "", "story": "5 Things to Try with Gemini 3 Pro in Gemini CLI"}]}, {"label": "Plan execution", "summary": "Commenters pair it with stronger models that plan, then let it implement.", "quotes": [{"id": 796707840, "item_id": 49794240, "url": "https://news.ycombinator.com/item?id=49794240", "by": "the_sleaze_", "date": "2026-09-21", "stance": "recommend", "quote": "Composer 2.5 - which remains incredible and honestly nothing else compares for me", "excerpt": "I didn't find 4.6 any better than Composer 2.5 - which remains incredible and honestly nothing else compares for me. Make a galaxy model search the space, create a document, argue and defend decisions, then hand it to 2.5 to implement. 4.6 was a slower less enjoyable version of that. 4.7 is better at \"I want the button to cancel the jobs, dont make any mistakes\" but honestly that's not what I use it's class for.", "context": "", "use_case": "implementing plans from documents", "switched_from": "", "story": "Grok 4.7"}, {"id": 791794673, "item_id": 49487167, "url": "https://news.ycombinator.com/item?id=49487167", "by": "rippeltippel", "date": "2026-08-29", "stance": "recommend", "quote": "their free tier of Composer is good enough", "excerpt": "I may be a rare Cursor user around here, but I am saddened by this news. The thing that keeps me using it is precisely the ability to switch between models: I usually do brainstorm/planning with Sol or Terra, then let Composer (free) deal with the implementation. For certain tasks I use Claude, which tends to be more expensive but sometimes saves me time. Using both OpenAI and Anthropic models, Cursor is cheaper than", "context": "", "use_case": "implementation", "switched_from": "", "story": "Our decision on Cursor following its acquisition by SpaceX"}, {"id": 774466421, "item_id": 48404151, "url": "https://news.ycombinator.com/item?id=48404151", "by": "phsource", "date": "2026-06-04", "stance": "recommend", "quote": "Kimi K2.5, Composer 2.5, GPT-5.4 mini, etc. for faster implementation", "excerpt": "Personally, with our company on Cursor, I can see why model makers are not the best people to go all the way down the stack. Using the right model for the situation will continue to be important, and model makers, by design, do not want to give you the choice to run different models. Right now, we use: - Kimi K2.5 for easy fixes, asking about the code, various agentic commands (e.g., summarizing Loom videos for Slack", "context": "", "use_case": "faster implementation", "switched_from": "", "story": "Show HN: Boxes.dev: ditch localhost; run Claude Code and Codex in the cloud"}]}, {"label": "Codebase Q&A", "summary": "Commenters say it is fast and useful for code search, explanations and research about a codebase.", "quotes": [{"id": 776963841, "item_id": 48560240, "url": "https://news.ycombinator.com/item?id=48560240", "by": "darklinear", "date": "2026-06-16", "stance": "recommend", "quote": "Composer 2.5 is really fast in their harness at code search/explanation/Q&A tasks", "excerpt": "It's still my primary at work (data engineering/platform engineering), running a mix of GPT-5.5 and Composer 2.5. We also have Claude Code subscriptions. I find myself preferring Cursor for most tasks. 70% of the time I use AI agents on a pretty tight leash. I often reject edits and ask it to change things. The IDE integration is really efficient for this workflow compared to Claude (yes, I've tried the Claude extens", "context": "data engineering/platform engineering", "use_case": "code search and debugging", "switched_from": "", "story": "SpaceX Is Buying Cursor"}, {"id": 776868512, "item_id": 48554282, "url": "https://news.ycombinator.com/item?id=48554282", "by": "senordevnyc", "date": "2026-06-16", "stance": "recommend", "quote": "I agree, Composer 2.5 is really good.", "excerpt": "I agree, Composer 2.5 is really good. I use it for all kinds of small tasks, and really for any kind of first pass at debugging, answering questions about the codebase, pulling data for reports, etc. It\u2019s fast, pretty accurate, and basically free.", "context": "", "use_case": "small tasks, debugging, codebase questions", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}, {"id": 776508706, "item_id": 48531794, "url": "https://news.ycombinator.com/item?id=48531794", "by": "Implicated", "date": "2026-06-14", "stance": "recommend", "quote": "I use this as my 'fast' research & report", "excerpt": "I'm chime in here as another Pi user, starting with OMP and then just ditching it for vanilla Pi + MCP/LSP from OMP as well as pi-cursor-sdk to get access to Composer 2.5 through Pi. I use this as my 'fast' research & report (through my project/codebase) or boilerplate/tightly-specced implementation agent that's available to my planning/orchestrator (GPT 5.5 if complex backend work, Fable/Opus if wanting the extended", "context": "", "use_case": "fast research and boilerplate", "switched_from": "", "story": "Kimi K2.7-Code: open-source coding model with better token efficiency"}]}], "caveats": [{"label": "Complex tasks", "summary": "Users report shallow results or getting stuck on harder, more complex work.", "quotes": [{"id": 780313664, "item_id": 48769604, "url": "https://news.ycombinator.com/item?id=48769604", "by": "Losenok", "date": "2026-07-02", "stance": "warn", "quote": "it is very fast, especially compared to anthropic models, but the result it produces, especially with more difficult tasks is very shallow.", "excerpt": "Very skeptical about the composer accuracy. I have been using it for 6 months now and it is very fast, especially compared to anthropic models, but the result it produces, especially with more difficult tasks is very shallow. It feels like it just finds the cheapest way to deliver the task.", "context": "using it 6 months", "use_case": "AI coding", "switched_from": "", "story": "CursorBench 3.1"}, {"id": 780997952, "item_id": 48812372, "url": "https://news.ycombinator.com/item?id=48812372", "by": "richkuo", "date": "2026-07-06", "stance": "recommend", "quote": "Incredibly token efficient, fast, and gets the same quality as if you worked the whole thing with Fable/Opus/GPT.", "excerpt": "Composer 2.5 is really effective at some tasks, but doesn't do as well on higher complexity tasks from my own experience. With that being said, Cursor Bench is nonetheless a fantastic gauge of LLM quality and performance. The most interesting outcome of Cursor Bench is Fable 5 to GPT 5.5, its almost a perfect continuous line. As of the report, Fable to GPT might be the new standard of agentic programming/building I d", "context": "open source maintainer", "use_case": "building code after planning", "switched_from": "", "story": "CursorBench 3.1"}, {"id": 761952658, "item_id": 47622041, "url": "https://news.ycombinator.com/item?id=47622041", "by": "athoscouto", "date": "2026-04-02", "stance": "recommend", "quote": "Now Composer 2 has taken over as my default model.", "excerpt": "Cursor has been my main AI tool for over a year now. I've been trying to use Claude Code seriously for over a month, but every time I do it, I get the impression that it would take me less work to do with Cursor. I'm on the enterprise plan, so it can get pricey. This is why I used to stick mostly to auto mode. Now Composer 2 has taken over as my default model. It is not as intelligent as OpenAI's or Anthropic's flags", "context": "", "use_case": "default coding model in Cursor", "switched_from": "", "story": "Cursor 3"}]}, {"label": "Code mistakes", "summary": "Some users find its output error-prone and well below GPT or Opus quality.", "quotes": [{"id": 781370464, "item_id": 48835654, "url": "https://news.ycombinator.com/item?id=48835654", "by": "bhouston", "date": "2026-07-08", "stance": "warn", "quote": "Every time I use Composer 2.5 I have to spend a bunch of time cleaning up its mistakes.", "excerpt": "Every time I use Composer 2.5 I have to spend a bunch of time cleaning up its mistakes. It is unusable compared to GPT 5.4 or 5.5. My time is more valuable that I will use a model that doesn\u2019t f** up my code base.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Grok 4.5"}, {"id": 780265537, "item_id": 48766596, "url": "https://news.ycombinator.com/item?id=48766596", "by": "subhobroto", "date": "2026-07-02", "stance": "warn", "quote": "Composer hands me a quickly put together college project that was started the night before it was due.", "excerpt": "I'm not disputing what you're saying. The slowness of Opus in particular is pretty accurate but you should have been getting little popups in Cursor saying Opus is under load and to try switching to other models? I mentioned my frustration with Composer in another thread and why I rely on Opus, but Opus, atleast via Cursor is practically unusable for me M-F 9-5 EST. As a result, I have modified my working schedule ou", "context": "", "use_case": "AI coding via Cursor", "switched_from": "", "story": "CursorBench 3.1"}, {"id": 770927762, "item_id": 48182985, "url": "https://news.ycombinator.com/item?id=48182985", "by": "svclaws", "date": "2026-05-18", "stance": "warn", "quote": "in my day-to-day usage it fell short across the board", "excerpt": "Their previous Composer was already marketed as a cheap model capable of competing with SOTA on most tasks. The evals they shared back then backed this up but in my day-to-day usage it fell short across the board. Canceled my cursor subscription and switched to Claude Code a few weeks ago. It has its own shortcomings but in terms of model capability and UX quality Cursor will have a hard time competing in the long te", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Cursor Introduces Composer 2.5"}]}, {"label": "Needs guidance", "summary": "It reportedly needs a good plan or hand-holding to produce good results.", "quotes": [{"id": 776378800, "item_id": 48523675, "url": "https://news.ycombinator.com/item?id=48523675", "by": "AgentMasterRace", "date": "2026-06-13", "stance": "recommend", "quote": "Composer is really good, but just like any Chinese model it needs a good plan. It's cheap and fast", "excerpt": "Composer is really good, but just like any Chinese model it needs a good plan. It's cheap and fast, in 1 month of pro I used the equivalent of 500$ in API credit for it.", "context": "", "use_case": "coding", "switched_from": "", "story": "Kimi K2.7-Code: open-source coding model with better token efficiency"}, {"id": 777288482, "item_id": 48580530, "url": "https://news.ycombinator.com/item?id=48580530", "by": "tomerbd", "date": "2026-06-17", "stance": "neutral", "quote": "composer 2.5 - mediocre with hand holding and super fast", "excerpt": "I code daily with AI - real programming tasks, real work I use below 3: codex 5.5 medium - best results less hand holding glm 5.2 max - mediocre with hand holding and super slow composer 2.5 - mediocre with hand holding and super fast I use all, since i run mulitple coding in parallel. disclosure - I use rexide which we created for all these agents to run in parallel with good visibility and feedback.", "context": "codes daily with AI", "use_case": "AI coding", "switched_from": "", "story": "GLM-5.2 is the new leading open weights model on Artificial Analysis"}, {"id": 780269488, "item_id": 48766843, "url": "https://news.ycombinator.com/item?id=48766843", "by": "subhobroto", "date": "2026-07-02", "stance": "warn", "quote": "my distaste for Composer and my preference for Opus", "excerpt": "> it tends to leave big, dangerous holes hiding inside implementations unless babied it's fascinating that I used these same exact words to express my distaste for Composer and my preference for Opus. I suspect, the domains and problems we are trying to solve need to be shared. I wrote about it here: https://news.ycombinator.com/item?id=48766275 Would love to reach out to discuss more, if you're ok with it, or absolu", "context": "", "use_case": "AI coding", "switched_from": "", "story": "CursorBench 3.1"}]}, {"label": "Benchmark doubts", "summary": "Some commenters distrust the benchmark claims used to market it as frontier-level.", "quotes": [{"id": 771150369, "item_id": 48196898, "url": "https://news.ycombinator.com/item?id=48196898", "by": "wunderlotus", "date": "2026-05-19", "stance": "warn", "quote": "I've experienced Composer 2's performance and it leaves much to be desired as a daily driver for a knowledge worker.", "excerpt": "I love Cursor as a tool, but I'm skeptical bc: 1/ CursorBench is so opaque [1] that it makes it hard to trust. Not to mention the v3.1 eval is a newer iteration and there's no insight into the tasks or if the model was just tuned to max it out. Composer 2 previously scored between 60-65% on the previous benchmark eval [2] but scores between 50-55% on CB v3.1[3]. 2/ I've experienced Composer 2's performance and it lea", "context": "knowledge worker", "use_case": "daily driver coding model", "switched_from": "", "story": "Cursor Introduces Composer 2.5"}, {"id": 759759232, "item_id": 47484952, "url": "https://news.ycombinator.com/item?id=47484952", "by": "amanhij", "date": "2026-03-22", "stance": "warn", "quote": "the release of Composer was so odd", "excerpt": "I made a post previously saying that the release of Composer was so odd. It takes lots of dedication and compute power to achieve frontier level, and they suddenly have a benchmark score saying composer is frontier. I love all the innovation that is happening I just hate when actual good product gets shadowed by marketing mongers.", "context": "", "use_case": "coding model", "switched_from": "", "story": "Cursor admits its new coding model was built on top of Moonshot AI's Kimi"}, {"id": 770927762, "item_id": 48182985, "url": "https://news.ycombinator.com/item?id=48182985", "by": "svclaws", "date": "2026-05-18", "stance": "warn", "quote": "in my day-to-day usage it fell short across the board", "excerpt": "Their previous Composer was already marketed as a cheap model capable of competing with SOTA on most tasks. The evals they shared back then backed this up but in my day-to-day usage it fell short across the board. Canceled my cursor subscription and switched to Claude Code a few weeks ago. It has its own shortcomings but in terms of model capability and UX quality Cursor will have a hard time competing in the long te", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Cursor Introduces Composer 2.5"}]}], "who": [{"by": "the_other", "context": "employer provides limited LLM budget", "url": "https://news.ycombinator.com/item?id=49855004", "date": "2026-09-26"}, {"by": "richkuo", "context": "open source maintainer", "url": "https://news.ycombinator.com/item?id=48812372", "date": "2026-07-06"}, {"by": "soyin", "context": "working on a fairly routine full stack web app", "url": "https://news.ycombinator.com/item?id=48766382", "date": "2026-07-02"}, {"by": "ifwinterco", "context": "works under a monthly spend cap at work", "url": "https://news.ycombinator.com/item?id=48739025", "date": "2026-06-30"}, {"by": "tomerbd", "context": "codes daily with AI", "url": "https://news.ycombinator.com/item?id=48580530", "date": "2026-06-17"}, {"by": "darklinear", "context": "data engineering/platform engineering", "url": "https://news.ycombinator.com/item?id=48560240", "date": "2026-06-16"}, {"by": "senordevnyc", "context": "runs a SaaS full-time", "url": "https://news.ycombinator.com/item?id=48554254", "date": "2026-06-16"}, {"by": "wahnfrieden", "context": "solo indie developer", "url": "https://news.ycombinator.com/item?id=46075688", "date": "2025-11-27"}], "tags": ["for Cursor users", "for budget-capped teams", "for small coding tasks", "for codebase Q&A", "for solo devs"], "use_cases": ["ai coding", "coding", "coding model", "implementation", "daily coding tasks", "implementing plans from documents"], "compared": [{"slug": "cursor", "name": "Cursor", "co": 22, "switched_from": 0, "switched_to": 0}, {"slug": "claude-code", "name": "Claude Code", "co": 14, "switched_from": 0, "switched_to": 0}, {"slug": "claude-opus", "name": "Claude Opus", "co": 13, "switched_from": 0, "switched_to": 0}, {"slug": "codex", "name": "Codex", "co": 10, "switched_from": 0, "switched_to": 0}, {"slug": "grok", "name": "Grok", "co": 10, "switched_from": 0, "switched_to": 0}, {"slug": "gpt-5", "name": "GPT-5", "co": 10, "switched_from": 0, "switched_to": 0}, {"slug": "claude-sonnet", "name": "Claude Sonnet", "co": 8, "switched_from": 0, "switched_to": 0}, {"slug": "claude", "name": "Claude", "co": 7, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=48756840", "title": "CursorBench 3.1", "mentions": 7}, {"url": "https://news.ycombinator.com/item?id=48553224", "title": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B", "mentions": 5}, {"url": "https://news.ycombinator.com/item?id=48182516", "title": "Cursor Introduces Composer 2.5", "mentions": 4}, {"url": "https://news.ycombinator.com/item?id=49486172", "title": "Our decision on Cursor following its acquisition by SpaceX", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=48835111", "title": "Grok 4.5", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=48554215", "title": "SpaceX Is Buying Cursor", "mentions": 2}], "sentiment_by_month": {"2025-11": {"recommend": 2}, "2025-12": {}, "2026-01": {}, "2026-02": {}, "2026-03": {"warn": 1}, "2026-04": {"recommend": 2, "warn": 1}, "2026-05": {"warn": 2, "recommend": 2, "compare": 1}, "2026-06": {"recommend": 11, "neutral": 3, "warn": 1}, "2026-07": {"recommend": 8, "warn": 3, "neutral": 1}, "2026-08": {"neutral": 2, "recommend": 2}, "2026-09": {"recommend": 4}, "2026-10": {}}, "quotes": [{"id": 797680064, "item_id": 49855004, "url": "https://news.ycombinator.com/item?id=49855004", "by": "the_other", "date": "2026-09-26", "stance": "recommend", "quote": "I do the bulk of my work with Composer 2.5. It\u2019s quite good for \u201cgoing forward\u201d on smallish tasks", "excerpt": "The last couple of weeks, I\u2019ve got rigorous about making the agent refactor old code. We\u2019ve removed, moved, consolidated, reordered loads of cruft. It has made the code much tidier and reduced the chance that the next feature will build on top of cruft. E.G. over time we\u2019d gained two client-side caches of related server state. This started out as two different parts of the same model, because we couldn\u2019t get all the ", "context": "employer provides limited LLM budget", "use_case": "daily coding tasks", "switched_from": "", "story": "Plan mode is dead"}, {"id": 796707840, "item_id": 49794240, "url": "https://news.ycombinator.com/item?id=49794240", "by": "the_sleaze_", "date": "2026-09-21", "stance": "recommend", "quote": "Composer 2.5 - which remains incredible and honestly nothing else compares for me", "excerpt": "I didn't find 4.6 any better than Composer 2.5 - which remains incredible and honestly nothing else compares for me. Make a galaxy model search the space, create a document, argue and defend decisions, then hand it to 2.5 to implement. 4.6 was a slower less enjoyable version of that. 4.7 is better at \"I want the button to cancel the jobs, dont make any mistakes\" but honestly that's not what I use it's class for.", "context": "", "use_case": "implementing plans from documents", "switched_from": "", "story": "Grok 4.7"}, {"id": 794776992, "item_id": 49673562, "url": "https://news.ycombinator.com/item?id=49673562", "by": "time0ut", "date": "2026-09-12", "stance": "recommend", "quote": "It is just a cheap, fast, surgical workhorse.", "excerpt": "If I had to pick just one, these days it\u2019s Composer. It is just a cheap, fast, surgical workhorse. My workflow uses other models as well for various phases: Opus for planning, Sonnet for review, etc. I prefer Cursor at this point just because of Composer. Claude Code is passable but the lack of a good, fast, cheap workhorse sucks. Sonnet and Haiku aren\u2019t it. I also do like Codex and Sol, Terra, and Luna. They are dec", "context": "", "use_case": "implementation", "switched_from": "", "story": "Ask HN: What default model do you use and why?"}, {"id": 792880017, "item_id": 49555001, "url": "https://news.ycombinator.com/item?id=49555001", "by": "lacoolj", "date": "2026-09-03", "stance": "recommend", "quote": "can be handled with Auto mode or Composer 2.5 (or Grok 4.6 High)", "excerpt": "Jesus what are you doing that requires Sol usage so often? Terra not enough? I know Luna isn't reliable, so that's fair. Genuinely curious though, because I use Cursor daily and almost everything I do, highly complex or high volume, can be handled with Auto mode or Composer 2.5 (or Grok 4.6 High). So I have to assume you're doing something far more complex than what I am", "context": "", "use_case": "coding", "switched_from": "", "story": "OpenAI begins rolling out GPT-6 Astra"}, {"id": 791913572, "item_id": 49494598, "url": "https://news.ycombinator.com/item?id=49494598", "by": "thefourthchime", "date": "2026-08-30", "stance": "neutral", "quote": "auto picks between Opus 5, GPT 5.6, Grok 4.6, and Composer 2.5", "excerpt": "It's a little confusing because Grok and Cursor kinda live in different worlds. Grok has SuperGrok and SuperGrok Heavy ($300 a month!) The best bet is Cursor Ultra ($200), which is the equivalent a month plan that you get from OpenAI and Anthropic. I get a LOT more capacity out of it because I almost always use the \"Auto\" mode, which auto picks between Opus 5, GPT 5.6, Grok 4.6, and Composer 2.5. I like Auto mode so ", "context": "", "use_case": "coding via Cursor Auto", "switched_from": "", "story": "Our decision on Cursor following its acquisition by SpaceX"}, {"id": 791794673, "item_id": 49487167, "url": "https://news.ycombinator.com/item?id=49487167", "by": "rippeltippel", "date": "2026-08-29", "stance": "recommend", "quote": "their free tier of Composer is good enough", "excerpt": "I may be a rare Cursor user around here, but I am saddened by this news. The thing that keeps me using it is precisely the ability to switch between models: I usually do brainstorm/planning with Sol or Terra, then let Composer (free) deal with the implementation. For certain tasks I use Claude, which tends to be more expensive but sometimes saves me time. Using both OpenAI and Anthropic models, Cursor is cheaper than", "context": "", "use_case": "implementation", "switched_from": "", "story": "Our decision on Cursor following its acquisition by SpaceX"}, {"id": 791780433, "item_id": 49486277, "url": "https://news.ycombinator.com/item?id=49486277", "by": "charrondev", "date": "2026-08-29", "stance": "recommend", "quote": "price very competitively for their quality and have very generous usage limits", "excerpt": "I used cursor extensively both at work and for personal use. Its harness is pretty darn good but I basically never used OpenAI models in it. The first party cursor models (initially composer and now grok-cursor) and price very competitively for their quality and have very generous usage limits included in the base plans, and then per token pricing afterwards. Occasionally I\u2019ve used some of the Anthropic models in it ", "context": "", "use_case": "coding model", "switched_from": "", "story": "Our decision on Cursor following its acquisition by SpaceX"}, {"id": 790115637, "item_id": 49382227, "url": "https://news.ycombinator.com/item?id=49382227", "by": "nikolay", "date": "2026-08-20", "stance": "neutral", "quote": "Why would I need Composer unless I'm a poor hobbyist?", "excerpt": "I use Claude with the Codex plugin as a critic (sometimes I switch and manually review with Claude). With the Superpowers skill (which I am trying to get rid of), it designs expensive models and implementations, uses cheaper ones for other, less important stuff, including Haiku, sometimes upgrading if it hits a roadblock, and then, finally, reviews with expensive ones. Why would I need Composer unless I'm a poor hobb", "context": "", "use_case": "", "switched_from": "", "story": "Git at Any Scale"}, {"id": 783919617, "item_id": 48994976, "url": "https://news.ycombinator.com/item?id=48994976", "by": "gokuljs", "date": "2026-07-21", "stance": "recommend", "quote": "I use Cursor and am happy with Composer :)", "excerpt": "I use Cursor and am happy with Composer :)", "context": "", "use_case": "AI coding model", "switched_from": "", "story": "Ask HN: Claude Code or Codex?"}, {"id": 781973144, "item_id": 48873321, "url": "https://news.ycombinator.com/item?id=48873321", "by": "gabriel-uribe", "date": "2026-07-11", "stance": "recommend", "quote": "Like GLM, (now with 4.5) Grok, Composer.", "excerpt": "Fwiw, don't buy into all the hype that you're falling behind. Yes, AI does cool things now, but I would say the impact is still unproven past indie hackers or early-stage startups. And a lot of the esoteric setups people have created with things like OpenClaw have become outdated as quickly as they were conceived. The popular thing is now to setup loops (eg I setup hourly integrations for Claude/Codex to 1) scrape my", "context": "", "use_case": "reviewing model output", "switched_from": "", "story": "AI 2040: Plan A"}, {"id": 781862192, "item_id": 48866387, "url": "https://news.ycombinator.com/item?id=48866387", "by": "arendtio", "date": "2026-07-10", "stance": "recommend", "quote": "Composer 2.5 was a lot better than I had expected", "excerpt": "I also like to take a look at https://cursor.com/cursorbench While in the past months Composer 2.5 was a lot better than I had expected a year ago, and the GPT 5.6 family does a good job in terms of cost for performance, I wonder why nobody is talking about Grok 4.5 high? Those numbers look very convincing to me.", "context": "", "use_case": "coding", "switched_from": "", "story": "GPT-5.6"}, {"id": 781503056, "item_id": 48843941, "url": "https://news.ycombinator.com/item?id=48843941", "by": "espadrine", "date": "2026-07-09", "stance": "neutral", "quote": "Composer 2.5 finetuned Kimi K2.5", "excerpt": "Composer 2.5 finetuned Kimi K2.5[0]. In the blog post, it is unclear whether Grok 4.5 is also a finetune on top of Kimi; they do imply it is also a finetune. > Training included trillions of tokens of Cursor data\u2026 We used reinforcement learning on difficult problems If xAI pivoted from a frontier base model company, to a finetuning company, it does mark a stark change to their relevance in the industry. [0]: https://", "context": "", "use_case": "", "switched_from": "", "story": "Grok 4.5"}, {"id": 781370464, "item_id": 48835654, "url": "https://news.ycombinator.com/item?id=48835654", "by": "bhouston", "date": "2026-07-08", "stance": "warn", "quote": "Every time I use Composer 2.5 I have to spend a bunch of time cleaning up its mistakes.", "excerpt": "Every time I use Composer 2.5 I have to spend a bunch of time cleaning up its mistakes. It is unusable compared to GPT 5.4 or 5.5. My time is more valuable that I will use a model that doesn\u2019t f** up my code base.", "context": "", "use_case": "AI coding", "switched_from": "", "story": "Grok 4.5"}, {"id": 781307378, "item_id": 48831711, "url": "https://news.ycombinator.com/item?id=48831711", "by": "jarodrh", "date": "2026-07-08", "stance": "neutral", "quote": "other models (GPT*, GEMINI*, Cursor - Composer 2.5 etc) as more like workhorse models", "excerpt": "Hmm, I honestly think a harness should be more about workflow, control, ease of use, memory optimization...other things I can't think of right now, the model/subscription being the least of them. Most of my experience has come from using Claude Code so I can only speak from that, but I will at some point pick up 'Pi' when I'm feeling adventurous. I feel completely free to use any number of subscriptions alongside Cla", "context": "", "use_case": "workhorse model for cost", "switched_from": "", "story": "Ask HN: What is your AI harness that lets you switch LLM models easily?"}, {"id": 780997952, "item_id": 48812372, "url": "https://news.ycombinator.com/item?id=48812372", "by": "richkuo", "date": "2026-07-06", "stance": "recommend", "quote": "Incredibly token efficient, fast, and gets the same quality as if you worked the whole thing with Fable/Opus/GPT.", "excerpt": "Composer 2.5 is really effective at some tasks, but doesn't do as well on higher complexity tasks from my own experience. With that being said, Cursor Bench is nonetheless a fantastic gauge of LLM quality and performance. The most interesting outcome of Cursor Bench is Fable 5 to GPT 5.5, its almost a perfect continuous line. As of the report, Fable to GPT might be the new standard of agentic programming/building I d", "context": "open source maintainer", "use_case": "building code after planning", "switched_from": "", "story": "CursorBench 3.1"}, {"id": 780430739, "item_id": 48776921, "url": "https://news.ycombinator.com/item?id=48776921", "by": "jarodrh", "date": "2026-07-03", "stance": "recommend", "quote": "Composer 2.5 (brilliant and fast)", "excerpt": "Orchestration works very well for me, but not in the way most people seem to be pushing for, with middlemen scoring and routing every request. I'm not sure I agree with that direction. For coding agents the routing problem is mostly solved at the config level, the harness already lets you pin models per role (done via subagents), and that covers most of what a per-request router promises. Three things have happened t", "context": "", "use_case": "agent pool coding", "switched_from": "", "story": "Ask HN: Is anyone experimenting with different ways of using LLMs for coding?"}, {"id": 780313664, "item_id": 48769604, "url": "https://news.ycombinator.com/item?id=48769604", "by": "Losenok", "date": "2026-07-02", "stance": "warn", "quote": "it is very fast, especially compared to anthropic models, but the result it produces, especially with more difficult tasks is very shallow.", "excerpt": "Very skeptical about the composer accuracy. I have been using it for 6 months now and it is very fast, especially compared to anthropic models, but the result it produces, especially with more difficult tasks is very shallow. It feels like it just finds the cheapest way to deliver the task.", "context": "using it 6 months", "use_case": "AI coding", "switched_from": "", "story": "CursorBench 3.1"}, {"id": 780269488, "item_id": 48766843, "url": "https://news.ycombinator.com/item?id=48766843", "by": "subhobroto", "date": "2026-07-02", "stance": "warn", "quote": "my distaste for Composer and my preference for Opus", "excerpt": "> it tends to leave big, dangerous holes hiding inside implementations unless babied it's fascinating that I used these same exact words to express my distaste for Composer and my preference for Opus. I suspect, the domains and problems we are trying to solve need to be shared. I wrote about it here: https://news.ycombinator.com/item?id=48766275 Would love to reach out to discuss more, if you're ok with it, or absolu", "context": "", "use_case": "AI coding", "switched_from": "", "story": "CursorBench 3.1"}, {"id": 780265537, "item_id": 48766596, "url": "https://news.ycombinator.com/item?id=48766596", "by": "subhobroto", "date": "2026-07-02", "stance": "warn", "quote": "Composer hands me a quickly put together college project that was started the night before it was due.", "excerpt": "I'm not disputing what you're saying. The slowness of Opus in particular is pretty accurate but you should have been getting little popups in Cursor saying Opus is under load and to try switching to other models? I mentioned my frustration with Composer in another thread and why I rely on Opus, but Opus, atleast via Cursor is practically unusable for me M-F 9-5 EST. As a result, I have modified my working schedule ou", "context": "", "use_case": "AI coding via Cursor", "switched_from": "", "story": "CursorBench 3.1"}, {"id": 780262112, "item_id": 48766382, "url": "https://news.ycombinator.com/item?id=48766382", "by": "soyin", "date": "2026-07-02", "stance": "recommend", "quote": "I find it really hard to justify the other models for the performance/cost I'm getting with Composer 2.5.", "excerpt": "I'm also using it as my daily driver. I've been trying Opus 4.8 this week to see if I was missing something but haven't noticed a meaningful difference. I'm working on a fairly routine full stack web app that isn't doing anything incredible. Once I had the patterns I wanted in place, it's been very capable of following those with new work. I also don't ever give it long running tasks, it's always focused and small ch", "context": "working on a fairly routine full stack web app", "use_case": "full stack web app coding", "switched_from": "", "story": "CursorBench 3.1"}, {"id": 780142192, "item_id": 48758887, "url": "https://news.ycombinator.com/item?id=48758887", "by": "maxdo", "date": "2026-07-02", "stance": "recommend", "quote": "I use for everything like trigger and monitor a 10 steps release process using composer , a very capable model", "excerpt": "The opposite , I use for everything like trigger and monitor a 10 steps release process using composer , a very capable model", "context": "", "use_case": "release process automation", "switched_from": "", "story": "CursorBench 3.1"}, {"id": 780117184, "item_id": 48757324, "url": "https://news.ycombinator.com/item?id=48757324", "by": "danfritz", "date": "2026-07-01", "stance": "recommend", "quote": "It's my daily driver, it's fast affordable and with a bit of guidance gets the job done.", "excerpt": "It's my daily driver, it's fast affordable and with a bit of guidance gets the job done. I only reach for Claud when i need to plan something big or want to have a sparring partner to fire of some ideas. I think what a lot of people don't realize is that you don't need a fronteer model for 80% of coding tasks. Composer 2.5 is often more than good enough, less token hungry and way faster", "context": "", "use_case": "daily coding", "switched_from": "", "story": "CursorBench 3.1"}, {"id": 779824403, "item_id": 48739025, "url": "https://news.ycombinator.com/item?id=48739025", "by": "ifwinterco", "date": "2026-06-30", "stance": "recommend", "quote": "I use Composer (since we use Cursor) or GPT 5.3-codex as my workhorse models", "excerpt": "I prefer GPT 5.5 to Opus but both are absurdly expensive token hogs, I can't afford to use either as my main model at $work with the monthly spend cap we have. I use Composer (since we use Cursor) or GPT 5.3-codex as my workhorse models and only break out the big guns when I have a genuinely difficult problem to solve. IMO somewhat weirdly 5.3-codex might be the best overall coding model OpenAI have ever released. It", "context": "works under a monthly spend cap at work", "use_case": "main coding workhorse model", "switched_from": "", "story": "Claude Sonnet 5"}, {"id": 777288482, "item_id": 48580530, "url": "https://news.ycombinator.com/item?id=48580530", "by": "tomerbd", "date": "2026-06-17", "stance": "neutral", "quote": "composer 2.5 - mediocre with hand holding and super fast", "excerpt": "I code daily with AI - real programming tasks, real work I use below 3: codex 5.5 medium - best results less hand holding glm 5.2 max - mediocre with hand holding and super slow composer 2.5 - mediocre with hand holding and super fast I use all, since i run mulitple coding in parallel. disclosure - I use rexide which we created for all these agents to run in parallel with good visibility and feedback.", "context": "codes daily with AI", "use_case": "AI coding", "switched_from": "", "story": "GLM-5.2 is the new leading open weights model on Artificial Analysis"}, {"id": 777084561, "item_id": 48567785, "url": "https://news.ycombinator.com/item?id=48567785", "by": "jemmyw", "date": "2026-06-17", "stance": "recommend", "quote": "Composer is actually really good, and fast.", "excerpt": "I didn't like cursor when it first came about but now I use it for my personal projects. The plan is good value for accessing different sota models occasionally for planning. Composer is actually really good, and fast. I'm not sure if it's because my personal projects are small enough I know them inside out and my work project is huge, but I prefer terminal code agents for day work over ide integration.", "context": "", "use_case": "", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}, {"id": 777034048, "item_id": 48564628, "url": "https://news.ycombinator.com/item?id=48564628", "by": "ghshephard", "date": "2026-06-16", "stance": "recommend", "quote": "that I use a lot of the time when I have fairly straightforward tasks", "excerpt": "You nailed it - in fact, most of Anthropic's early revenue came from Cursor - much of claude code programming components is essentially a feature copy of Cursor, so it makes sense they are similar. Cursor does have it's own model - it's a heavily reworked version of KimiK2, called \"composer\" - that I use a lot of the time when I have fairly straightforward tasks that don't require a lot of exploration or independent ", "context": "", "use_case": "straightforward coding tasks", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}, {"id": 776963841, "item_id": 48560240, "url": "https://news.ycombinator.com/item?id=48560240", "by": "darklinear", "date": "2026-06-16", "stance": "recommend", "quote": "Composer 2.5 is really fast in their harness at code search/explanation/Q&A tasks", "excerpt": "It's still my primary at work (data engineering/platform engineering), running a mix of GPT-5.5 and Composer 2.5. We also have Claude Code subscriptions. I find myself preferring Cursor for most tasks. 70% of the time I use AI agents on a pretty tight leash. I often reject edits and ask it to change things. The IDE integration is really efficient for this workflow compared to Claude (yes, I've tried the Claude extens", "context": "data engineering/platform engineering", "use_case": "code search and debugging", "switched_from": "", "story": "SpaceX Is Buying Cursor"}, {"id": 776949553, "item_id": 48559347, "url": "https://news.ycombinator.com/item?id=48559347", "by": "TrisMcC", "date": "2026-06-16", "stance": "neutral", "quote": "mostly using Composer 2.5, but I freely change the model when the need arises", "excerpt": "I use cursor (through a work subscription), only the cli (https://cursor.com/cli), and mostly using Composer 2.5, but I freely change the model when the need arises. Most comments here seem to think there is no command line client? I have never used the editor. For my personal projects, I use a heavily modified pi. I also have access to a claude code account through work (bedrock), but I don't use it much. It always ", "context": "", "use_case": "coding model", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}, {"id": 776893616, "item_id": 48555851, "url": "https://news.ycombinator.com/item?id=48555851", "by": "infecto", "date": "2026-06-16", "stance": "recommend", "quote": "I use it quite a bit and it works well and is extremely fast for the tasks it was built for", "excerpt": "Hmmm. Not in my experience. I don\u2019t think it can be compared to Haiku, maybe sonnet levels? It\u2019s obviously not Opus and never was intended for that use case. I use it quite a bit and it works well and is extremely fast for the tasks it was built for", "context": "", "use_case": "fast coding tasks", "switched_from": "", "story": "SpaceX Is Buying Cursor"}, {"id": 776868512, "item_id": 48554282, "url": "https://news.ycombinator.com/item?id=48554282", "by": "senordevnyc", "date": "2026-06-16", "stance": "recommend", "quote": "I agree, Composer 2.5 is really good.", "excerpt": "I agree, Composer 2.5 is really good. I use it for all kinds of small tasks, and really for any kind of first pass at debugging, answering questions about the codebase, pulling data for reports, etc. It\u2019s fast, pretty accurate, and basically free.", "context": "", "use_case": "small tasks, debugging, codebase questions", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}, {"id": 776868065, "item_id": 48554254, "url": "https://news.ycombinator.com/item?id=48554254", "by": "senordevnyc", "date": "2026-06-16", "stance": "recommend", "quote": "Composer 2.5 is really solid", "excerpt": "Yes, it\u2019s my daily driver for building the saas I run full-time. I\u2019m not happy about this news. I like the ability to switch between any models, Composer 2.5 is really solid, I like having my agents coworking in the IDE with me, the plan mode is great, Cloud Agents are great, especially with slack, linear, web, etc integrations. I routinely tag an error report in slack and Cursor fires up a Composer 2.5 cloud agent t", "context": "runs a SaaS full-time", "use_case": "cloud agent issue triage", "switched_from": "", "story": "SpaceX to buy Cursor AI coding agent operator Anysphere for $60B"}, {"id": 776508706, "item_id": 48531794, "url": "https://news.ycombinator.com/item?id=48531794", "by": "Implicated", "date": "2026-06-14", "stance": "recommend", "quote": "I use this as my 'fast' research & report", "excerpt": "I'm chime in here as another Pi user, starting with OMP and then just ditching it for vanilla Pi + MCP/LSP from OMP as well as pi-cursor-sdk to get access to Composer 2.5 through Pi. I use this as my 'fast' research & report (through my project/codebase) or boilerplate/tightly-specced implementation agent that's available to my planning/orchestrator (GPT 5.5 if complex backend work, Fable/Opus if wanting the extended", "context": "", "use_case": "fast research and boilerplate", "switched_from": "", "story": "Kimi K2.7-Code: open-source coding model with better token efficiency"}, {"id": 776378800, "item_id": 48523675, "url": "https://news.ycombinator.com/item?id=48523675", "by": "AgentMasterRace", "date": "2026-06-13", "stance": "recommend", "quote": "Composer is really good, but just like any Chinese model it needs a good plan. It's cheap and fast", "excerpt": "Composer is really good, but just like any Chinese model it needs a good plan. It's cheap and fast, in 1 month of pro I used the equivalent of 500$ in API credit for it.", "context": "", "use_case": "coding", "switched_from": "", "story": "Kimi K2.7-Code: open-source coding model with better token efficiency"}, {"id": 775644771, "item_id": 48477798, "url": "https://news.ycombinator.com/item?id=48477798", "by": "cookiengineer", "date": "2026-06-10", "stance": "warn", "quote": "they will happily execute the malware payloads on install", "excerpt": "> \"cd folder\" does nothing. That's like recommending to use the xterm on Windows. Statistically, nobody uses their computer that way anymore. The world has moved on since the 1990s. I was only not affected because I use a heavily customized VIM, but even there can I not control how package managers like npm, pip or composer or go are behaving, because they will happily execute the malware payloads on install. And tim", "context": "", "use_case": "package management", "switched_from": "", "story": "Microsoft's open source tools were hacked to steal passwords of AI developers"}, {"id": 775435808, "item_id": 48464738, "url": "https://news.ycombinator.com/item?id=48464738", "by": "qingcharles", "date": "2026-06-09", "stance": "neutral", "quote": "I use Composer 2.5 because it comes free with Grok", "excerpt": "I use Composer 2.5 because it comes free with Grok, and it's obviously better than using Grok, but it is far worse than GPT5.5 in my daily usage :(", "context": "", "use_case": "coding", "switched_from": "", "story": "Claude Fable 5"}, {"id": 775428416, "item_id": 48464276, "url": "https://news.ycombinator.com/item?id=48464276", "by": "vorticalbox", "date": "2026-06-09", "stance": "recommend", "quote": "for almost all the tasks i have given it, it has handled it perfectly well and is a lot cheaper.", "excerpt": "for the last few weeks I have been using composer 2.5 (cursors fine tune of kimi 2.5) and honestly i don't see it worth the price to use 5.5, opus or sonnet any more. for almost all the tasks i have given it, it has handled it perfectly well and is a lot cheaper. if I get a harder challenge for it i'll jump up a model for planning until that its been solid.", "context": "", "use_case": "coding tasks", "switched_from": "", "story": "Claude Fable 5"}, {"id": 774647396, "item_id": 48415462, "url": "https://news.ycombinator.com/item?id=48415462", "by": "AndreVitorio", "date": "2026-06-05", "stance": "recommend", "quote": "Cursor for manual or small changes w/ Composer 2.5.", "excerpt": "If you are teaching newbies, just get them into the Claude Code or Codex desktop apps. For devs: Claude, Codex and Cursor. All on the $20 subscription. Then use Conductor for worktrees w/ Claude/Codex for mid-size tasks and code review. Cursor for manual or small changes w/ Composer 2.5.", "context": "", "use_case": "small changes", "switched_from": "", "story": "Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)"}, {"id": 774466421, "item_id": 48404151, "url": "https://news.ycombinator.com/item?id=48404151", "by": "phsource", "date": "2026-06-04", "stance": "recommend", "quote": "Kimi K2.5, Composer 2.5, GPT-5.4 mini, etc. for faster implementation", "excerpt": "Personally, with our company on Cursor, I can see why model makers are not the best people to go all the way down the stack. Using the right model for the situation will continue to be important, and model makers, by design, do not want to give you the choice to run different models. Right now, we use: - Kimi K2.5 for easy fixes, asking about the code, various agentic commands (e.g., summarizing Loom videos for Slack", "context": "", "use_case": "faster implementation", "switched_from": "", "story": "Show HN: Boxes.dev: ditch localhost; run Claude Code and Codex in the cloud"}, {"id": 772816625, "item_id": 48301039, "url": "https://news.ycombinator.com/item?id=48301039", "by": "captn3m0", "date": "2026-05-27", "stance": "recommend", "quote": "I love the work Packagist/Composer is doing in the space.", "excerpt": "I arrived at a similar model for NPM using hooks in pnpm: https://github.com/captn3m0/npm-sec-feed. I love the work Packagist/Composer is doing in the space. I\u2019m now a firm believer that every package manager needs to support hooks globally. Composer also supports conflicts which results in this amazing approach of having a meta-package conflict with insecure packages: https://github.com/Roave/SecurityAdvisories. Can", "context": "", "use_case": "PHP package security", "switched_from": "", "story": "An Update on Composer and Packagist Supply Chain Security"}, {"id": 771152801, "item_id": 48197050, "url": "https://news.ycombinator.com/item?id=48197050", "by": "chemex", "date": "2026-05-19", "stance": "compare", "quote": "Two things I'd watch on Composer 2.5 specifically", "excerpt": "I've been using Claude Code as my daily driver on a React Native + iOS codebase for the last few months. The thing that surprised me wasn't quality differences on individual edits \u2014 those are pretty close once you control for harness wiring \u2014 but how differently I'd ended up structuring my workflow around each style of tool. Tab completion + chat-in-sidebar feels like an extension of my editing. An agentic harness fe", "context": "", "use_case": "", "switched_from": "", "story": "Cursor Introduces Composer 2.5"}, {"id": 761952658, "item_id": 47622041, "url": "https://news.ycombinator.com/item?id=47622041", "by": "athoscouto", "date": "2026-04-02", "stance": "recommend", "quote": "Now Composer 2 has taken over as my default model.", "excerpt": "Cursor has been my main AI tool for over a year now. I've been trying to use Claude Code seriously for over a month, but every time I do it, I get the impression that it would take me less work to do with Cursor. I'm on the enterprise plan, so it can get pricey. This is why I used to stick mostly to auto mode. Now Composer 2 has taken over as my default model. It is not as intelligent as OpenAI's or Anthropic's flags", "context": "", "use_case": "default coding model in Cursor", "switched_from": "", "story": "Cursor 3"}]}