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

201–210 of 492 posts

Re: Cursor 1.0

#201

Post by raincole »

pjerem wrote: post #160
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…

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.

> so most people aren’t going to ask an AI subscription anytime soon

It's companies asking programmers to use AI, not vice versa.

Re: Cursor 1.0

#202

Post by TheYumasi »

rschiavone wrote: post #198
kissgyorgy wrote: post #190

Earlier quoted context omitted.

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.

I hope this question doesn't sound snarky, it's a legitimate concern that I want to address for myself: how do you ensure that once it ssh's to the machine, it does not execute potentially damaging commands?

Claude code asks you permissions for every command. It also gives you the possibility of marking commands as safe so next time it can use them without asking .

Re: Cursor 1.0

#203

Post by elAhmo »

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.

Re: Cursor 1.0

#204

Post by h1fra »

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…

they say they are making hundreds of millions, but they never say how much of it is going to GPU cost. If I had to guess, they are burning everything and far from being profitable

Re: Cursor 1.0

#205

Post by arberavdullahu »

I can’t try Background Agents yet because they aren’t available in Privacy Mode. I’m curious if—and how—they’ll roll this out to others, given their guarantee that no code is stored on their servers. According to their security page [1], about 50% of users have Privacy Mode enabled.

I’m also curious how this compares to OpenAI’s Codex. In my experience, running agents locally has worked better for large or complex codebases, especially since setting up the environment correctly can be tricky in those setups.

[1] https://www.cursor.com/security#privacy-mode-guarantee

Re: Cursor 1.0

#206

Post by wordofx »

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.

No.

Re: Cursor 1.0

#207

Post by arresin »

rfoo wrote: post #195
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…

Yeah, and it's stupid that I still have to pay $20/mo just for Cursor Tab.

I like cursor but I have this disabled 90% of the time.

Re: Cursor 1.0

#208

Post by dotancohen »

citizenpaul wrote: post #182
ido wrote: post #155

Earlier quoted context omitted.

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.

Commercial animal feed is subsidized. So are some forms of human food in many countries.

Pet food is not subsidized in my country nor the EU. If any countries do subsidize pet food, they are the exception. Maybe the US? Pet food is often manufactured from the waste of other processes, including the human food industry, but that is not a subsidiary.

Re: Cursor 1.0

#209

Post by therein »

TheYumasi wrote: post #202
rschiavone wrote: post #198

Earlier quoted context omitted.

I hope this question doesn't sound snarky, it's a legitimate concern that I want to address for myself: how do you ensure that once it ssh's to the machine, it does not execute potentially damaging commands?

Claude code asks you permissions for every command. It also gives you the possibility of marking commands as safe so next time it can use them without asking .

So these agents that people are so excited about spawning in parallel stop and ask you before executing each command they choose to execute? What kind of life is that. I'd rather do something myself than tell 5 AI agents what I want and then keep approving each command they are going to run.

I'm not saying it is better if they run commands without my approval. This whole thing is just doesn't seem as exciting as other people make it out to be. Maybe I am missing something.

It can literally be a single command to ssh into that machine and check if the systemd service is running. If it is in your history, you'd use ctrl+r to lookback anyway. It sounds so much worse asking some AI agent to look up the status of that service we deployed earlier. And then approve its commands on top of that.

Re: Cursor 1.0

#210

Post by meowface »

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…

As a long-time Cursor user, I just tried Claude Code for the first time two days ago and I found it:

- Burning tokens with constant incorrect command-line calls to read lines (which it eventually gets right but seemingly needs to self-correct 3+ times for most read calls)

- Writing the string "EOF" to the end of the file it's appending to with cat

- Writing "\!=" instead of "!="

- Charged me $7 to write like 23 lines (admittedly my fault since I forgot I kept "/model opus" on)

Minus the bizarre invalid characters I have to erase, the code in the final output was always correct, but definitely not impressive since I've never seen Cursor do things like that.

Otherwise, the agent behavior basically seems the same as Cursor's agent mode, to me.

I know the $7 for a single function thing would be resolved if I buy the $100/month flat fee plan, but I'm really not sure if I want to.

Post reply on HN