Live data from Hacker News

Cursor 1.0

cursor.com

181–190 of 492 posts

Re: Cursor 1.0

#181
post #92

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?

You should be good as long as you use one of the mainstream languages: Python, JS, Java, C++, Golang, Ruby, Rust etc

Elixir has noticeably improved with recent releases

Re: Cursor 1.0

#182
post #155

Earlier quoted context omitted.

I use Aider with Openrouter and I keep wondering about the pricing of LLMs after providers decide to be profitable. Can we still afford a model which knows Python, Java and how to disrupt snail biology without poisoning mammals?

The answer to that depends on when the VC bubble bursts- if it lasts long enough costs will eventually drop far enough. Pets.com was a .com-boom era joke but today I actually buy my pet-food online and I'm pretty sure nobody is subsidising me doing that.

The.global food market is so heavily subsidized that is almoat impossible that your dog food is not subsidized. Animal feed is even more subsidized.

Re: Cursor 1.0

#183

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…

This here, exactly. Cursor is late to the party with their IDE-based approach, especially after the MS-blocked extension fiasco.

Re: Cursor 1.0

#184
post #160

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…

Well, sure. Except that in most of the world outside SV, $200/month is expensive. At least Cursor is affordable to any developer. Because most of the time, even if it’s totally normal, companies act like they’re doing you a favor when they pay for your IDE so most people aren’t going to ask an AI subscription anytime soon. I mean, it will probably come but not today.

You can subcribe to the Max with 90€ a month, which isn't bad considering the effectiveness of Claude Code.

Re: Cursor 1.0

#185

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…

I was almost exclusively using Claude Code for a couple of weeks, and after recently trying Cursor with Sonnet 4 in MAX mode, I think it now comes close. Those are requests paid on top of the sub price though.

Re: Cursor 1.0

#186

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.

Re: Cursor 1.0

#187

I keep getting back and forth between Cursor and Zed, but Cursor autocomplete and next cursor prediction are still the best in class between all the competitors, I don't use chats and agents, yet I feel very productive and fast. I sometimes go back to Copilot too just to see how is it going but it has been very delusional so far regarding code suggestions. The only thing I hate about Cursor is the overwrite of some o…

I think not using agent chat is kind of a missing forest for the trees sort of thing. That said, I do continue to think that agents are in this weird zone where it's more natural to want to interact through ticketing layer, but you kind of want to editor layer for the final 5%.

Missing forest by chatting about a problem? I keep going back to agents from time to time, never worked for me, and I already spend a lot of time understanding boss tickets(via extra meetings and feedback loops) I don't want explain again down the line, my strong opinion is that I'm paid for doing real work augmented by AI, not assigning "tickets" to the AI

Re: Cursor 1.0

#189
post #165

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

What's Junie? I am currently trialing the AI assistant in IntelliJ but I didn't see that name anywhere.

this one - https://www.jetbrains.com/junie/

Re: Cursor 1.0

#190
post #159

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…

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

It can use any command line tool very well. I just told him "Look up the status of the created systemd servive". It ssh-d to the machine, run "systemctl status", read the output and fixed issues based on that! That was totally unexpected.
Post reply on HN