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

341–350 of 492 posts

Re: Cursor 1.0

#341

Post by carefulfungi »

fragmede wrote: post #227
prennert wrote: post #196

Earlier quoted context omitted.

Does anyone know how Claude code compares to using Aider with anthropic API? I have been using the Claude.ai interface in the past and have switched to Aider with Anthropic API. I really liked Claude.ai but using Aider is a much better dev experience. Is Claude Code even better?

Claude Code (and Cursor, for that matter) don't commit to git. Fundamentally that's just bonkers to me. Aider does, so each prompt can be /undo 'd. I had a chance to use Cursor at work, and if that's how people are interacting with LLMs, it's no wonder we can't agree on this whole "are LLMs useful for programming" thing. ChatGPT Codex is on another level for agentic workflow though. It's been released to (some?) "plu…

I haven't used Jujutsu / jj much at all. But it seems like a great match to Aider. I wonder how the surrounding dev tooling ecosystem changes as agentic coders become more popular.

Re: Cursor 1.0

#342

Post by deadbabe »

sunaookami wrote: post #169
deadbabe wrote: post #96

Earlier quoted context omitted.

Other professions pay a lot for their tools, and developers are loaded with cash.

>developers are loaded with cash Maybe in the US? I will never pay 100$ for a subscription and I despise that people normalized it by even buying this stuff instead of saying "no, that's way too expensive".

Well bucko it’s time to open your wallet. There’s creatives out there who spend at least $1000/month in subscriptions for tools, but without those tools they could never do most of the work they do. And some who buy physical gear like photographs and videographers pay even way more than that for equipment.

Soon it will be the same for developers. Developers really are a spoiled bunch when it comes to paying for things, many will balk at paying $99/year just to publish stuff on an App Store. Everyone just wants free open source stuff. As expectations on developer productivity rises, you will be paying for these AI tools no matter how expensive they get, or you will just be gentrified out of the industry. The choice is yours.

Re: Cursor 1.0

#343

Post by Jenk »

pembrook wrote: post #339
tuesdaynight wrote: post #334

I trust that Claude Code is good, and I believe that most people commenting here are truthful to their experiences. However, I have a strange feeling that companies are using bots on these announcements comments. Maybe I'm being overcautious, but one of the worst things (for me) that came from the AI rush of these past years is this feeling that everything is full of bots. I know that people have preferences, but I f…

Totally agree, but that said, I just fired up Cursor on a paid account and after a few chats immediately hit the same issue I've been facing for weeks: 'Connection failed. If the problem persists, please check your internet connection or VPN' I've contacted support and they have been no help. You can see tons of people having this issue in user forums. Meanwhile, bypassing the giant monstrosity that is VScode (and th…

> So I wouldn't be so dismissive that anyone frustrated with Cursor is a bot.

Not GP, but my suspicions are actually of the other end of the spectrum - i.e., it's the glowing reviews of AI things that make my bot-sense tingle.

Though I usually settle on the idea that they (the reviewers) are using LLMs to write/refine their reviews.

Re: Cursor 1.0

#344

Post by deadbabe »

lopatin wrote: post #311
deadbabe wrote: post #30

Earlier quoted context omitted.

Would you pay $400?

That's a great question. Probably not. IDK. I'm also only paying this much to maintain momentum on a personal project. I also know in a year, these LLM products will change drastically, pricing tiers will transform, etc.. So I can't predict what will happen in a year but things will probably be cheaper. Edit: On the other hand, the state of the art tools will also be much better in a year, so might keep that high pri…

I think there is definitely room to price AI tools way higher. Developers are being slowly boiled like frogs right now. Getting addicted to AI tools to the point they can’t work without them, that’s when you raise the price.

Re: Cursor 1.0

#345

Post by threetonesun »

mhmmmmmm wrote: post #274
koolba wrote: post #263

Earlier quoted context omitted.

Not quite. You pay ala carte for it with API pricing. The $100/mo max plan lets you use a Claude Code with a fixed bill. There’s some usage limits though.

They add Claude Code to the pro plan yesterday: https://x.com/_catwu/status/1930307574387363948

I'm not sure an x.com link to a GIF really helps clarify the status of Claude Code on Pro plans. Here's the actual anthropic docs on it: https://support.anthropic.com/en/articles/11145838-using-cla...

Re: Cursor 1.0

#347

Post by verelo »

pembrook wrote: post #339
tuesdaynight wrote: post #334

I trust that Claude Code is good, and I believe that most people commenting here are truthful to their experiences. However, I have a strange feeling that companies are using bots on these announcements comments. Maybe I'm being overcautious, but one of the worst things (for me) that came from the AI rush of these past years is this feeling that everything is full of bots. I know that people have preferences, but I f…

Totally agree, but that said, I just fired up Cursor on a paid account and after a few chats immediately hit the same issue I've been facing for weeks: 'Connection failed. If the problem persists, please check your internet connection or VPN' I've contacted support and they have been no help. You can see tons of people having this issue in user forums. Meanwhile, bypassing the giant monstrosity that is VScode (and th…

I’ve hit this error many times. Oddly closing and reopening cursor typically fixes it…

Re: Cursor 1.0

#348

Post by max_on_hn »

davedx wrote: post #300
yard2010 wrote: post #248

Earlier quoted context omitted.

That's a really smart observation. It's hard to add sophisticated abstractions though, because they are all selling text by the pounds (kilos?). So it feels the same as vendor lock for a cucumber seller, doesn't it? The seller can sell you an experience that would lock you in, but aside from it there is no moat since anyone can sell cucumbers.

To try and give examples: an autonomous agent that can integrate with github, read issues, then make pull requests against those issues is a step (or maybe two) above an LLM API (cucumber seller). It doesn't take much more of a stretch to imagine teams of agents, coordinated by a "programme manager" agent, with "QA agents" working to defined quality metrics, "architect" agents that take initial requirements and break…

This exactly. I built CheepCode to do the first part already, so it can accept tasks through Linear etc and submit PRs in GitHub. It already tests its work headlessly (including with Playwright if it’s web code), and I am almost done with the QA agent :-)

Re: Cursor 1.0

#349

Post by rgbrenner »

tuesdaynight wrote: post #334

I trust that Claude Code is good, and I believe that most people commenting here are truthful to their experiences. However, I have a strange feeling that companies are using bots on these announcements comments. Maybe I'm being overcautious, but one of the worst things (for me) that came from the AI rush of these past years is this feeling that everything is full of bots. I know that people have preferences, but I f…

All of these reviews are irrelevant anyway because of the variations in the problems, skillset, project attributes (size, structure, etc), human variations in prompting, and a million other reasons.

You should just set aside some time to try out different tools and see if you agree there's an improvement.

For trying models, OpenRouter is a big time saver.

Re: Cursor 1.0

#350

Post by ignoramous »

brushfoot wrote: post #324
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…

Copilot at $10/mo. lets you use Sonnet 4 in VS Code, which has been working very well for me in agent mode. Curious what Claude Max offers that sets it apart.

I believe Copilot Agent isn't yet generally available outside of GitHub (the website)?

Also, Copilot's paid version is free for developers of popular FOSS projects.

Post reply on HN