Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Cursor 3

cursor.com

Post reply on HN
Print view View original

431–438 of 438 posts

Re: Cursor 3

#431

Post by fragmede »

wilkystyle wrote: post #103
fragmede wrote: post #95

Earlier quoted context omitted.

> have zero interest in these new "swarms of agents" they are trying to force on us from every direction. Good for you! Personally waiting for one agent to do something while I shove my thumb up my butt just waiting around for it to generate code that I'll have to fix anyway is peak opposite of flow state, so I've eagerly adopted agents (how much free will I had in that decision is for philosophers to decide) so ther…

I have personally found that I cannot context switch between thinking deeply about two separate problems and workstreams without a significant cognitive context-switching cost. If it's context-switching between things that don't require super-deep thought, it's definitely doable, but I'm still way more mentally burnt-out after an hour or two of essentially speed-running review of small PRs from a bunch of different s…

> Are your agents working on tangential problems?

Unrelated problems simultaneously in the same git tree. Worktrees are unnecessary overhead if the area they're working in are disjoint. My Agents.md has instructions to commit early and often instead of one giant commit at the end, otherwise it wouldn't work.

> how do you ensure you're still thinking at a sufficient level of depth and capacity about each problem each agent is working on?

The context switching is hell and I have to force myself to dig deep into the MD file and understand things and not just rubber stamp the LLM output. It would be dishonest of me to say that I'm always 100% successful at that though.

Re: Cursor 3

#432

Post by bodhiJhawken »

Oras wrote: post #335
teaearlgraycold wrote: post #332

Earlier quoted context omitted.

I think if you’re a professional and you’re actually coding for >4 hours per day it makes sense. Also if you’re one of those weirdos that likes to command an army of agents.

Well I’m a software engineer and code more than 4 hours per day. But I do check the generated code, make sure it doesn’t go banana. I wouldn’t do multiple features at the same time as I have no idea how people are checking the output after that. I like AI coding and it accelerated my work, but I wouldn’t trust their output blindly

This is my thoughts exactly.

It speeds up so much of what I do, simple tasks are amazing to delegate to AI and it leaves me with more time in the day to tackle the big tasks.

My general rule of thumb now is I never get AI to build the bones of something which I believe I will need to build something else on top of later. But if it’s some throw away dead end feature that won’t require me to build more tooling on top of in future I’ll happily spin up a cloud agent and use the result.

Re: Cursor 3

#433

Post by teaearlgraycold »

bodhiJhawken wrote: post #432
Oras wrote: post #335

Earlier quoted context omitted.

Well I’m a software engineer and code more than 4 hours per day. But I do check the generated code, make sure it doesn’t go banana. I wouldn’t do multiple features at the same time as I have no idea how people are checking the output after that. I like AI coding and it accelerated my work, but I wouldn’t trust their output blindly

This is my thoughts exactly. It speeds up so much of what I do, simple tasks are amazing to delegate to AI and it leaves me with more time in the day to tackle the big tasks. My general rule of thumb now is I never get AI to build the bones of something which I believe I will need to build something else on top of later. But if it’s some throw away dead end feature that won’t require me to build more tooling on top o…

They're really amazing for making one-off tools where you just need some clean output and can throw away the code afterwards. I had Claude Opus put together a data labeling web app with very little effort. Less work than creating an account on some SaaS and learning their system.

Re: Cursor 3

#434

Post by adityamwagh »

Archonical wrote: post #54
adityamwagh wrote: post #50

Earlier quoted context omitted.

How would they make money from the tokens then haha? The main revenue driver of these companies is to get people to use more tokens. That’s what they will optimise for. Getting the developers out of the way is the way to do it.

Isn’t Cursor’s business model mostly subscriptions? They’re the ones paying for inference, not the user directly, right? So wouldn’t they be incentivized to minimize token usage per unit of user value, not maximize raw tokens?

I think enterprise users have a API for the whole company do pay as you go? I believe that’s where they make the most money.

Re: Cursor 3

#435

Post by thewhitetulip »

bastawhiz wrote: post #371
thewhitetulip wrote: post #264

Earlier quoted context omitted.

It looks like they revamped the agents window. They will not remove vscode bits

Maybe I'm just behind on the features, I didn't even know there was an agents window. There's an agents sidebar.

Yeah, now there is a new agents portion on the left side I suppose. That window enables us to control cloud agents and the regular sidebar agents

Re: Cursor 3

#436

Post by mikestorrent »

zwaps wrote: post #251
mikestorrent wrote: post #174

Earlier quoted context omitted.

I feel like perhaps you haven't used Cursor. I use both CC and Cursor extensively and as far as I can tell there is nothing that the CC agent will do that Cursor won't do just as well (often using Opus as the backend) and at the same time I get the advantage of seeing the changes in a full IDE if I want to. Their new agent-forward UI hides the code if you don't want to see it as much, but I and many others think that…

Nobody is saying your workflow is wrong, it may even be better. However it is not how people use Claude Code or what its attraction is. What you mention as advantages and features is not something CC users use or require. On the other hand, Claude is trained on its harness (all but confirmed by Anthropic) so CC is likely just a bit better at its level of abstraction than in cursor. And at the end, you can’t yet best…

> What you mention as advantages and features is not something CC users use or require

See, this is ridiculous nonsense. I can absolutely code in Cursor without seeing the code, and I've used both extensively, and they're remarkably similar. Why would I not want to be able to paste screenshots? Why would I really not want to have an IDE for when it's time to be a Real Engineer and look at the code?

I get it if you can't code and don't know what all those funny punctuation marks mean but it's pretty helpful to be able to e.g. just select germane lines of code and feed them to the agent as context so that it doesn't have to piss away tokens finding it. I guess if you don't even know your codebase at all then you can't do that - but that doesn't mean it doesn't have an advantage to be able to do it, it just means you aren't capable :shrug:

Re: Cursor 3

#437

Post by ninininino »

babelfish wrote: post #149
ninininino wrote: post #106

Earlier quoted context omitted.

"having to type `/worktree` into every new chat isn't really a resolution" I don't know what you're talking about. My experience with Cursor (before this new v3) is that new Cursor agent tabs / cloud agents already intelligently manage worktrees to prevent conflicts.

Wow, maybe something is wrong with my setup. In Cursor 3, I am clicking "New Agent" at the top left. My root repository is correctly listed on top of the composer, and I clicked the icon to the right of it and selected 'Worktree'. Then, I instruct the model to run `pwd` and tell me it's git status. It's always just on `main` in my root repository. I dug through the settings and couldn't find anything, and after findi…

Wow, it seems I'm the fool here.

I'm on Version: 2.6.19.

Per https://cursor.com/docs/configuration/worktrees#how-is-this-...

They apparently removed this in 3.0. - I couldn't begin to guess why.

"Automatic management of worktrees was removed in Cursor 3.0 and replaced with the new commands /worktree and /best-of-n. We also have added worktree support for the Cursor CLI.

Management of worktrees is now fully agentic. This makes it simpler to support use cases such as starting an agent, and only doing work in a worktree later on in the chat's lifecycle.

/best-of-n makes comparing the results of multiple models much easier. The parent agent will provide commentary on the different results and you can pick the best one. Additionally, you can even ask the parent agent to merge different parts of the different implementations into a single commit.

If you had agents that were previously running in a worktree, those chats will still work. However, you will need to use the new commands to start new agents in worktrees."

Re: Cursor 3

#438

Post by limistah »

mstaoru wrote: post #429
limistah wrote: post #428

Earlier quoted context omitted.

My view about coding agents is that there can't be any human that types as fast as them with the same accuracy as their output, ever! Same as it is faster to take notes with a laptop than writing manually, it is faster and cheaper to have an agent give you the code you want to type than actually typing them, manually.

It's also faster to inject nutrients for your body intravenously. Are we, as an industry, really limited by "not typing fast enough"?

Well, software engineering is meeting people's needs and they care less how that happen, most times.

For me to enjoy code, I have side projects that can afford the speed. For work, where speed and accuracy are required, I pair with llms.

Post reply on HN