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

211–220 of 492 posts

Re: Cursor 1.0

#211

Post by davedx »

bravesoul2 wrote: post #173
JimDabell wrote: post #123

Earlier quoted context omitted.

The market for AI-assisted development is exploding and token costs are plummeting all the time. It makes sense for them to subsidise usage to capture market share in the short-term with the expectation that servicing their users will cost them less in the future.

There is no loyalty or lock in though. There is little real uniqueness. And everyone in AI is trying to make everyone else on AI the "commodity complement" It's like a horse race. But yeah enjoy the subsidies. It's like the cheap Ubers of yesteryear.

The winners will be those that climb the abstraction ladder. The more sophisticated and useful the abstractions, the more lockin/sticky it will be

Re: Cursor 1.0

#212

Post by eloisant »

paulddraper wrote: post #176
flawn wrote: post #159

Earlier quoted context omitted.

Can you elaborate why Claude Code is that much better in regard to also the missing in built IDE functionality?

It’s smarter. And as of the latest release, has VSCode/Cursor/Windsurf integration.

How can it be smarter? Cursor can use Claude 4 as model, so it should be the same?

Re: Cursor 1.0

#213

Post by eloisant »

Avalaxy wrote: post #197
josefrichter wrote: post #192

Earlier quoted context omitted.

Honestly, $200 is not expensive. Even just offloading some small tasks to a junior dev every now and then is incredibly cheap at $200.

Did you choose to not read his full reply? I'll repeat it again for you: > Except that in most of the world outside SV

Even in a European with lower wages compared to US, total cost of a developer will be minimum 5000 euros/per month. And that's just salary with all taxes, not accounting laptop costs, office space, etc.

You just need a 4% increase of productivity to make those $200 worth it.

Re: Cursor 1.0

#214

Post by SerCe »

delbronski wrote: post #163

Anyone tried Junie from JetBrains? Im super happy with it. I’m not sure how it compares to other coding agents though.

I use it pretty much daily and am pretty happy with it, especially its ability to do very targeted edits rather than leaving random changes everywhere.

I believe it’ll get much better as LLMs start editing code by invoking refactoring tools (rename, change signature, etc.) rather than rewriting the code line by line, as this will let them perform large-scale changes reliably in a way that's similar to how software engineers do them now using IDE tools

Re: Cursor 1.0

#215

Post by hn_throw2025 »

elAhmo wrote: post #203
BudaDude wrote: post #13

I love Cursor, but it feels like a ticking time bomb with extensions not being updated at the same rate as VSCode. Also another issue I am starting to see is the lack of shared MCP servers. If I have VSCode, Cursor, and Claude open, each one is running its own instance of the MCP server. You can imagine that with a dozen or so MCP's, the memory footprint becomes quite large for no reason.

TIL that it doesn't have the same extensions as VSCode. I thought they share the same directory.

This is only effectively a problem for a handful of MS vendored extensions.

Re: Cursor 1.0

#216

Post by ramraj07 »

eloisant wrote: post #212
paulddraper wrote: post #176

Earlier quoted context omitted.

It’s smarter. And as of the latest release, has VSCode/Cursor/Windsurf integration.

How can it be smarter? Cursor can use Claude 4 as model, so it should be the same?

The system prompt, agent landscape and fundamental behavior is different. Its just like using chatgpt vs openai api. A single chatgpt conversation can go forever because it's not just doing one call for each message you send.

Re: Cursor 1.0

#217

Post by meowface »

smcleod wrote: post #75
demosthanos wrote: post #57

Earlier quoted context omitted.

Because at some point we have to stop riding the treadmill and just pick a tool and use it to make stuff. Cursor was the first to really arrive at a useful agent mode. It does everything I need it to and more. It's not worth it to me to keep hopping to new tools every time a new one becomes the hyped up hot thing. Like it or not, we're hitting the slope of enlightenment and some of us are ready to be done with the ch…

Cline was agent based from day one and doesn't try to do copilot style tab completes at all. It's been our go to agentic coding app across the majority of our large clients since mid-late 2024. Cursor has been trying to play catch up but has not delivered us the same results.

Cursor Tab is like 60% of the reason why it's so good.

Cursor Agent works great, too.

Most importantly, everything is $20/month, instead of possibly $20/day with Cline or Roo.

Re: Cursor 1.0

#218

Post by raincole »

gazagoal wrote: post #154

As someone who has two annual subs of Cursor Pro (one from student account and another from Lenny's newsletter), I just spent $100 on Claude Code and I haven't touched Cursor AI for any coding tasks since. If you already spend anything near or over $100 on Cursor, it's no brainer. The agent experience is night and day. No more wrong tool-calling, premature ending of conversation, failure to apply changes or overwriti…

Claude Code is always quite slow for me. I'm on Windows though so I'm not sure if the performance hit comes from WSL. Anyone experienced differences between Windows/Mac/Linux?

Re: Cursor 1.0

#219

Post by m101 »

shafyy wrote: post #186
ai_assisted_dev wrote: post #116

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 min…

> I still don't understand how cursor is making any money at all. They don't make any money. They are burning VC money. Anthropic and OpenAI are probably also not making moeny, but Cursor is making "more no money" than others.

Are anthropic and openai making money (including training and infra costs)?

Re: Cursor 1.0

#220

Post by hn_throw2025 »

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...

Because if you’re paying for your own subscription, it’s a way to control costs. If you know how to use it properly, it’s possible to stay within the $20/month spend. Just not if you are tossing trivial tasks to Claude4/GeminiPro and forever topping up tokens.
Post reply on HN