Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Cursor 1.0

cursor.com

Post reply on HN
Print view View original

111–120 of 492 posts

Re: Cursor 1.0

#111

Post by ramoz »

BoorishBears wrote: post #107
ramoz wrote: post #101

Earlier quoted context omitted.

It’s not silly at all. There is a lot of hyper activity going in terms of social influence. I didn’t say cursor has poor UX. I tab too. And use agent for cheaper work I don’t care too much about. That said, the best autocomplete is arguably evolving and cursor does not own that.

Someone said "I don't really see why people still use Cursor over tools like Cline / Roo Code" And your answer is "A lot of power in social influence.", which is a bit silly when autocomplete is the first form of AI assistance a critical mass of people found intuitive + helpful and Cursor has the best implementation of it... meanwhile Cline/Roo Code don't provide it.

You don’t get it - autocomplete is evolving from keyboard clicks to prompts. Tab-ing is not as effective as agentic coding.

Your beloved cursor will go all in on this front, less and less priority on focused cursors in the editor.

Re: Cursor 1.0

#112

Post by techpression »

blixt wrote: post #108

I keep switching away from and back to Cursor (mainly due to frontier models explicitly fighting their apply model, the first few times it’s funny to see the LLM itself write “this is frustrating” but I digress). And every time I find it having diverged further from VSCode compatibility. This wouldn’t be so bad if it was an intentional design choice but it seems more that Microsoft is starting to push them out? Like…

I fully expect MS to change the VS Code license in the not so far future to make applications like Cursor not possible. Forking might be a thing initially but will quickly fade since without the backing of MS the ecosystem around it will die.

Re: Cursor 1.0

#113

Post by Salgat »

Vilian wrote: post #93
thegrim33 wrote: post #90

It's an IDE but they don't bother to list on their website what languages you can use the IDE to develop for? I feel like I'm going crazy here. How can they not bother to mention that on their website / marketing?

Vs code also don't advertise what language it's for, isn't the same case here?

On VS Code's front page it explicitly lists 12 languages and that it "supports almost every major programming language. Several ship in the box, like JavaScript, TypeScript, CSS, and HTML, but extensions for others can be found in the VS Code Marketplace."

Re: Cursor 1.0

#114

Post by SparkyMcUnicorn »

jen729w wrote: post #102
smcleod wrote: post #56

I don't really see why people still use Cursor over tools like Cline / Roo Code. I'm guessing it's as they clearly have a larger viral marketing department than engineers, as the application itself doesn't perform nearly as well, requires you to have another IDE installed and their subscriptions nerf the models context sizes etc...

Remember, not everyone is a pro dev. I'm certainly not: and in that context I find Cursor to be incredibly simple and useful. It's just like VSC, which I was using, but it has these magical abilities. I was using it within a minute of downloading it. Unlike Cline, I guess, whatever that is.

Install Roo Code (or Cline) in VS Code, plug in your API key(s), and start using them. It's that simple.

Re: Cursor 1.0

#115

Post by feldstein »

curiousElf wrote: post #95

I wish they had proper support for multi root repos (even though the last update promised better support, it was just a line in the release notes with no docs - which seems to be their usual change management style). Its so painful - the model never knows the directory in which it is supposed to be and goes on a wild goose chase of searching in the wrong repo. I have to keep guiding it to the right repo. Anyone here…

Dev here, Can you give me more details about whats going on here? Screenshots or request ids (or both) would be best You can email me directly at feldstein at anysphere.co

Re: Cursor 1.0

#116

Post by ai_assisted_dev »

I still don't understand how cursor is making any money at all. I spend so much time inside cursor, that I am spending 10-20$ per day on additional requests. Now if I connect model provider APIs to windsurf, I'd be spending upwards of 100$ due to amount of tokens I use through the API per day. And if I connect my own API key to Cursor, I immediately get rate limited for any request, because I go well above 50 per minute. And I did try claude code, but its just not on par with my experience with Cursor.

I could probably go much lower, and find a model that is dirt cheap but takes a while; but right now the cutting edge (for my own work) is Claude 4 (non-max / non-thinking). To me it feels like Cursor must be hemorrhaging money. The thing that works for me is that I am able to justify those costs working on my own services, that has some customers, and each added feature gives me almost immediate return on investment. But to me it feels like the current rates that cursor charges are not rooted in reality.

Quickly checking Cursor for the past 4 day period:

Requests: 1049

Lines of Agent Edits: 301k

Tabs accepted: 84

Personally, I have very little complaints or issues with cursor. Only a growing wish list of more features and functionality. Like how cool would it be if asynchronous requests would work? Rather than just waiting for a single request to complete on 10 files, why can't it work on those 10 files in parralel at the same time? Because now so much time is spend waiting for the request to complete (while I work on another part of the app in a different workspace with Cursor).

Re: Cursor 1.0

#117

Post by jprokay13 »

AstroBen wrote: post #50
CuriouslyC wrote: post #42

Earlier quoted context omitted.

The benefit of Aider is that you can configure a very involved static analysis toolchain to edits which directly triggers new edits in response, and everything is a git commit so it's easy to revert bad edits quickly. I have used both and I find Aider provides more control and produces code faster due to leaner prompts (it's also easier to run multiple Aider instances than Cursor instances), while Cursor has a pretti…

what are the most useful changes you've made to the configuration? This could be it - I haven't played with that a whole lot

Create a file like conventions.md in the root of your repository with specific commands for common tasks: running tests, linters, formatters, adding packages Set this as part of the files it reads on startup. Then ask aider to look at your codebase and add to it :) Aider has a lot of slash commands to familiarize yourself with. Ask and web are crucial commands to get the most out of it.

My recommendation to anyone is to use ask the most then tell it to “implement what we discussed” when it looks good.

Hope that helps

Re: Cursor 1.0

#118

Post by evo_9 »

techpression wrote: post #112
blixt wrote: post #108

I keep switching away from and back to Cursor (mainly due to frontier models explicitly fighting their apply model, the first few times it’s funny to see the LLM itself write “this is frustrating” but I digress). And every time I find it having diverged further from VSCode compatibility. This wouldn’t be so bad if it was an intentional design choice but it seems more that Microsoft is starting to push them out? Like…

I fully expect MS to change the VS Code license in the not so far future to make applications like Cursor not possible. Forking might be a thing initially but will quickly fade since without the backing of MS the ecosystem around it will die.

This is why I’m using Zed now, and Claude Code. I like to keep Zed pretty minimal and I’m slowly weening off of Cursor in favor of Claude Code when I need it

Re: Cursor 1.0

#119

Post by namanyayg »

jameslk wrote: post #98

Cursor wishlist item for any PM listening: When reviewing the changes made from agent mode, I don’t know why the model made the change or whether the model even made the change versus a tool call making the change. It’s a pain to go fish out the reason from a long response the model gives in the chat. Example: I recently asked a model to set up shadcn for a project, but while trying to debug why things looked pretty…

Was just discussing this a friend today

Hand written code needs to be distinguishable and considered at a higher priority for future code generation context

Re: Cursor 1.0

#120

Post by Hyperboreanal »

steveklabnik wrote: post #87
ramoz wrote: post #79

Earlier quoted context omitted.

I think about this daily. More devs are starting to pick up on Claude Code. The initial “not an IDE!” scare is usually diminished within the initial session. I don’t think the future of agentic software development is in an IDE. Claude Code gives me power to orchestrate - the UX has nothing to do with terminal; it just turns out an agent that lives on the OS and in the filesystem is a powerful thing. Anthropic can an…

You might find this post interesting: https://steipete.me/posts/2025/claude-code-is-my-computer It… sure is something. I’m still thinking about if it’s horrible, visionary, or both.

Note: the text of that article itself is AI generated.

> Automate Content: Like this very post. I use Wispr Flow to talk with Claude, explain the topic and tell it to read my past blog posts to write in my style.

Post reply on HN