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

171–180 of 492 posts

Re: Cursor 1.0

#171

Post by pzo »

reubenmorais wrote: post #138
benoittravers wrote: post #91

These just look like small updates. Doesn’t warrant a full version upgrade.

1.0 is not an upgrade, it's the first stable release. Usually it signifies the arrival of some amount of feature completeness and stability compared to the fast paced 0.x days. Of course semver doesn't really fit neatly most software let alone a user facing GUI application, but socially that's what they're trying to communicate with the 1.0.

These days those versioning is just PR and doesn't mean much like if something is stable. Gmail used to have beta mark for how many years but was still used. Rect native is 0.79 but doesn't mean it's not production ready.

Re: Cursor 1.0

#172

Post by anktor »

Does anyone have experience with using this or another agent on local files? No company I know of will approve this for their owned repositories.

What about Gitlab instead of GitHub, is there an equivalent to cursor 1.0 product?

Re: Cursor 1.0

#173

Post by bravesoul2 »

JimDabell wrote: post #123
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…

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.

Re: Cursor 1.0

#174

Post by dmazin »

SkyPuncher wrote: post #105
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…

I have a cursor rule that tells it about directories. Basically just X is UI, Y is BE, Z is auth. Keep it short. It's enough for it to realize it needs to navigate directories.

Yeah, just putting the structure in the rules and telling it to always specify the full path in commands was enough to fix any multi repo issues for me.

Re: Cursor 1.0

#175

Post by lauriswtf »

anktor wrote: post #172

Does anyone have experience with using this or another agent on local files? No company I know of will approve this for their owned repositories. What about Gitlab instead of GitHub, is there an equivalent to cursor 1.0 product?

Claude Code runs in your terminal and works with your local files.

Re: Cursor 1.0

#176

Post by paulddraper »

flawn wrote: post #159
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…

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.

Re: Cursor 1.0

#177

Post by spand »

sgt wrote: post #165
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.

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

Its their take on a coding agent that just came out of early access.

Re: Cursor 1.0

#178

Post by rsanheim »

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…

Same experience here. I got a Cursor Pro sub towards the end of 2024. Once Claude Code because available, my Cursor usage dropped _dramatically_ as I got up to speed on how Claude Code worked.

I still prefer Cursor for some things - namely UI updates or quick fixes and explanations. For everything else Claude Code is superior.

Re: Cursor 1.0

#179

Post by rcarmo »

I can’t find enough value in this to move me away from Copilot on nvim (with the MCP plugin) and VS Code’s agent mode. Even Zed is better than Cursor at this point, solely because it’s faster. And they all support Claude 4.

Re: Cursor 1.0

#180

Post by troupo »

ramoz wrote: post #111
BoorishBears wrote: post #107

Earlier quoted context omitted.

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.

> Tab-ing is not as effective as agentic coding.

It is more effective when you have to do a bunch of similar changes. Or when code is standard enough that you just hit tab, and change perhaps one line. Or when parts of code are immediately deduced from context, and substitutions/changes are immediately provided.

Post reply on HN