[jonathannorris]

Yeah, hard disagree on that one, based on recent surveys, 80-90% of developers globally use IDEs over CLIs for their day-to-day work.

I was pretty worried about Cursor's business until they launched their Composer 1 model, which is fine-tuned to work amazingly well in their IDE. It's significantly faster than using any other model, and it's clearly fine-tuned for the type of work people use Cursor for. They are also clearly charging a premium for it and making a healthy margin on it, but for how fast + good it's totally worth it.

Composer 1 + now eventually creating an AI native version of GitHub with Graphite, that's a serious business, with a much clearer picture to me how Cursor gets to serious profitability vs the AI labs.

[bangaladore]

As the other commenter stated, I don't use CLIs for development. I use VSCode.

I'm very pro IDE. I've built up an entire collection of VSCode extensions and workflows for programming, building, customizing build & debugging embedded systems within VSCode. But I still prefer CLI based AI (when talking about an agent to the IDE version).

> Composer 1

My bet is their model doesn't realistically compare to any of the frontier models. And even if it did, it would become outdated very quickly.

It seems somewhat clear (at least to me) that economics of scale heavily favor AI model development. Spend billions making massive models that are unusable due to cost and speed and distill their knowledge + fine tune them for stuff like tools. Generalists are better than specialists. You make one big model and produce 5 models that are SOTA in 5 different domains. Cursor can't do that realistically.

[santoriv]

> My bet is their model doesn't realistically compare to any of the frontier models.

I've been using composer-1 in Cursor for a few weeks and also switching back and forth between it, Gemini Flash 3, Claude Opus 4.5, Claude Sonnet 4.5 and GPT 5.2.

And you're right it's not comparable. It's about the same quality of code output of the aforementioned models but about 4x as fast. Which enables a qualitatively different workflow for me where instead of me spending a bunch of time waiting on the model, the model is waiting on me to catch up with its outputs. After using composer-1, it feels painful to switch back to other models.

I work in a larg(ish) enterprise codebase. I spend a lot of time asking it questions about the codebase and then making small incremental changes. So it works very well for my particular workflow.

Other people use CLI and remote agents and that sort of thing and that's not really my workflow so other models might work better for other people.

[neutronicus]

Does it have some huge context window? Or is it really good at grep?

The Copilot version of this is just fucking terrible at suggesting anything remotely useful about our codebase.

I've had reasonable success just sticking single giant functions into context and asking Sonnet 4.5 targeted questions (is anything in this function modifying X, does this function appear to be doing Y) as a shortcut for reading through the whole thing or scattershot text search.

When I try to give it a whole file I actually hit single-query token limits.

But that's very "opt-in" on my part, and different from how I understand Cursor to work.

[santoriv]

It is really good at grep and will make multiple grep calls in parallel.

And when I open it in the parent directory of a bunch of repos in our codebase, it can very quickly trace data flow through a bunch of different services. It will tell me all the files the data goes through.

It's context window is "only" 200k tokens. When it gets near 200k, it compresses the conversation and starts a new conversation..... which mostly works but sometimes it has a bit of amnesia if you have a really long running conversation on something.

[Yoric]

> It is really good at grep and will make multiple grep calls in parallel.

How does that work? Multiple agents grepping simultaneously?

[dimava]

When other models would grep, then read results, then use search, then read results, then read 100 lines from a file, then read results, Composer 1 is trained to grep AND search AND read in one round trip It may read 15 files, and then make small edits in all 15 files at once

[simondotau]

Presumably if it knows it needs to perform multiple searches in order to gather information (e.g. searching for redundant implementations of an algorithm, plus calls to the codebase's canonical implementation) it should be able to run those searches in parallel grep calls.

[void-star]

Probably something closer to ripgrep, if not actually ripgrep.

[spruce_tips]

composer 1 has been my most used model the past few months. but i only use it to execute plans that i write with the help of larger, more intelligent models like opus 4.5. composer 1 is great at following plan instructions so after some careful time providing the right context and building a plan, it basically never messes up the implementation. sometimes requires a few small tweaks around the edges but overall a fantastic workflow that's so delightfully fast

[nusl]

OP isn't saying to do all of your work in the terminal; they're saying they prefer CLI-based LLM interfaces. You can have your IDE running alongside it just fine, and the CLIs can often present the changes as diffs in the IDEs too.

[CharlieDigital]

This is how some folks on my team work. Ran into this when I saved a file manually and the editor ran formatting on it. Turns out that the dev that wrote it only codes via CLI though reviews the files in an IDE so he never manually saved it and ran the formatter.

[atomicUpdate]

I expect the formatter/linter to be run as part of presubmit and/or committing the code so it doesn't matter how it's edited and saved by the developer. It's strange to hear of a specific IDE being mandated to work around that, and making quick edits with tools like vi unsupported.

[CharlieDigital]

This was with Rider which had its own rules for which we hadn't set up an override in .editorconfig.

[whalesalad]

Part of a healthy codebase is ensuring that anyone can hack on it, regardless of their editor setup. Relying on something in .vscode and just assuming people are using that editor is what leads to this kind of situation.

Bake that into the workflow some other way.

[satvikpendem]

Or just enforce that the team all uses the same tools, and you save quite a lot in productivity between making things work on different tools, more so than whatever productivity gains individual devs on the team get from using their own preferred tools. Many teams I know issue everyone MacBooks and enforce VSCode usage, for example, and that has saved so much time compared to other teams I've seen where devs can choose between macOS or Windows for example.

[wredcoll]

Saves so much time??? Really? You set up a dev env once, how much time is it even possible to save?

[satvikpendem]

No, it's saving time because some things might work on one OS but not another, and then dealing with updates to each OS that might break something, or we need a new piece of software but it doesn't work on Windows for local development, et cetera, et cetera, et cetera. There are so many ways it goes wrong, I speak from personal experience.

[tyre]

allow me to introduce you to the lord and savior, https://pre-commit.com/

[adamcharnock]

Agreed. Also Lefthook: https://github.com/evilmartians/lefthook

[robertfw]

and if your pre-commit runs fast (thank you, ruff), you can set this up as a post-edit hook in claude code

[jswny]

I would not recommend this. A hook that modifies files causes Claude to have to re-read the file before modifying it again, which can build up your context window fast

[the_mitsuhiko]

> Yeah, hard disagree on that one, based on recent surveys, 80-90% of developers globally use IDEs over CLIs for their day-to-day work.

I have absolutely no horse in this race, but I turned from a 100% Cursor user at the beginning of the year, to one that basically uses agents for 90% of my work, and VS Code for the rest of it. The value proposition that Cursor gave me was not able to compete with what the basic Max subscription on anthropic gave me, and VS Code is still a superior experience to Claude in the IDE space.

I think though that Cursor has all the potential to beat Microsoft at the IDE game if they focus on it. But I would say it's by no way a given that this is the default outcome.

[dimitri-vs]

This is me. Was a huge Cursor fan, tried Claude Code, didn't get it, tried it again a year ago and it finally clicked a week later I cancelled my Cursor sub and now using VS Code.

I don't even like using CLI, in fact I hate it, but I don't use CLI - Claude does it for me. Using for everything: Obsidian vault, working on Home Assistant, editing GSheets, and so much more.

[Sleaker]

How does company X dependant on company Y product beat company Y in what is essentially just small UI differences? Can cursor even do anything that vscode can't right now?

[the_mitsuhiko]

> Can cursor even do anything that vscode can't right now?

Right now VSCode can do things that Cursor cannot, but mostly because of the market place. If Cursor invests money into the actual IDE part of the product I can see them eclipsing Microsoft at the game. They definitely have the momentum. But at least some of the folks I follow on Twitter that were die-hard Cursor users have moved back to VSCode for a variety of reasons over the last few months, so not sure.

Microsoft itself though is currently kinda mismanaging the entire product range between GitHub, VS Code and copilot, so I would not be surprised if Cursor manages to capitalize on this.

[selestify]

How is Microsoft mismanaging things?

[the_mitsuhiko]

GitHub, Copilot and VS Code are I believe the same org. Or at least, that’s what the branding implies. Copilot / VS Code lost all headstart and barely catch up, GitHub is currently largely being seen as a leader less organization that has lost it’s direction. The recent outrage about pricing changes being an excellent example of this.

[redox99]

Hard disagree.

Composer is extremely dumb compared to sonnet, let alone opus. I see no reason to use it. Yes, it's cheaper, but your time is not free.

[aqme28]

> Yeah, hard disagree on that one, based on recent surveys, 80-90% of developers globally use IDEs over CLIs for their day-to-day work.

This is a pretty dumb statistic in a vacuum. It was clearly 100% a few years ago before CLI-based development was even possible. The trend is very significant.

[pjmlp]

CLI based development predates IDEs for a couple of decades, and we moved away for very good reasons.

[noodletheworld]

Strawman.

Imaginary situation: People are using claude instead of cursor, and you can run claude in a terminal, so this is going back to the days of not using an IDE for the people that do it.

Straw man shake down: Terminal based development like vim and emacs are old and shit, and we moved away from that for a reason, and so (although totally unrelated) this means 'using claude' means going back to using a terminal for everything, which is similarly old and shit.

...but, obviously wrong.

- There's a claude desktop app that isn't done via the terminal.

- Agents use the terminal/powershell to do lots of things, even in cursor because that's the only way to automate some things, eg. running tests.

- Terminal environments like vim and emacs are ides. :face-palm:

- It literally makes no difference what interface you copy and paste your text prompt into and then walk off to get a coffee in agent mode.

Anyone who's seriously arguing that IDE integrated LLM chat windows somehow beat command line LLM chat windows is either a) religiously opposed to the terminal window, or b) hasn't actually tried using the tools.

...because, you'll find it makes no difference at all.

Why is cursor getting involved with graphite? ...because the one place where is makes a difference is reviewing code, where most CLI based tools (eg. `git diff`) are just generally inferior to visual integrated code review tools.

You know what that is?

An acknowledgement that cursor, in terms of code generation has nothing that qualifies as the 'special sauce' to use it over any other tool. CLI or not.

So they're investing in another company that actually has a good, meaningful product.

[pjmlp]

Lets see how that holds in five years time.

I am betting it won't.

By the way, there are OS APIs, I am yet to write a CLI driven agent, as part of iPaaS deployments, which are basically SaaS IDEs.

vi and Emacs are certainly not IDEs, they are programmer editors, although with enough effort they may pretend to be one.

[wredcoll]

Now I want to see the goal posts for what makes an IDE...

That being said, surely the point here is about "agent driven development" vs "ai autocomplete". As they say, whether you type your command into a web window or a terminal window presumably doesn't change the flow that much.

[bhl]

It does not matter what 80-90% of developers do. Code development is heavily tail-skewed: focus on the frontier and on the people who are able to output production-level code at a much higher pace than the rest.

[trollbridge]

No kidding. Arguing "90% of devs do this" makes it that much more likely that it's something that the bottom 90% of devs do.

[freeone3000]

I use an IDE. It has a command line in it. It also has my keybinds, build flow, editor preferences, and CI integrations. Making something CLI means I can use it from my IDE, and possibly soon with my IDE.

[jstummbillig]

Say more? It's the first time I see Composer 1 being talked about outside of the Cursor press stuff, with high praise no less.

What are we talking about? Autocomplete or GPT/Claude contender or...? What makes it so great?

[infecto]

GPT contender. There has been talk on the cursor forums. I think largely people have e slept on coding models and stick with Anthropic thinking it’s the best. Composer fit that niche of extremely fast and smart enough. Sometimes you just want a model that has a near instant response. The new Gemini preview is overtaking my usage of Composer.

[enraged_camel]

I used it extensively for a week and gave it an honest chance. It’s really good for quickly troubleshooting small bugs. It doesn’t come anywhere close to Opus 4.5 though.

[infecto]

Apples and oranges comparison. I don’t think it’s the same and good for you for waiting on Opus to respond. I don’t have the energy.

[baq]

> Waiting for Opus

Sir Opus is the fast one of the bunch. Try GPT 5.2 high.

[infecto]

Sir I don’t use GPT 5.2. I value speed and accuracy. Not accuracy alone.

[bangaladore]

The problem is companies like OpenAI have the upper hand here as they show with the Codex models.

Which is what I was mentioning elsewhere. They build huge models with infinite money and distill them for certain tasks. Cursor doesn't have the funding, nor would it be wise, to try to replicate that.

[infecto]

Why do you think so? Cursor has raised what north of $3bn. That’s enough money to train or tune a model for coding. With their pricing changes I suspect they are trying to get at least to breakeven as quick as possible. They have massive incentives both on the quality of the model for tool chain use and from a cost perspective to try and run their own model generation.

[k4rli]

Kilocode as an IDE plugin has completely removed Cursor from my toolkit.

Cursor has been both nice and awful. When it works, it has been good. However for a long time it would freeze on re-focus and recently an update broke my profile entirely on one machine so it wouldn't even launch anymore.

Kilocode with options of free models has been very nice so far.