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

Cursor CLI

cursor.com

Post reply on HN
Print view View original

101–110 of 275 posts

Re: Cursor CLI

#101

Post by fastball »

teaearlgraycold wrote: post #100
mrcwinn wrote: post #98

I went from years of vscode to "Cursor is the future" to never using Cursor at all. Claude Code, even with new limits, is just too good. If I were to switch to gpt-5, why wouldn't I just use Codex? I'm struggling to understand the value of what they're presenting.

Why is Claude Code better than Cursor?

In my experience, it is much better at tool-calling, which is huge when we're talking about agentic coding. It also seems to do a better job of keeping things cleaning and not going off on tangents for anything that isn't accomplished in one shot.

Re: Cursor CLI

#102

Post by byronic »

extr wrote: post #94
byronic wrote: post #85

I'm having trouble finding a use for this outside of virtualized unused environments. Why not instead give me a virtual machine that runs this in a confined storage space? I would _never_ give an LLM access to any disk I own or control if it had anything more than read permissions

Why not? Have you ever actually used these things? The risk is incredibly low. I run claude code with zero permissions every day for hours. Never a problem.

I have (not an exhaustive list) SSH keys and sensitive repositories hanging out on my filesystem. I don't trust _myself_ with that, let alone an LLM, unless I'm running ollama or similar local nonsense with no net connectivity.

I'm a few degrees removed from an air gapped environment so obviously YMMV. Frankly I find the idea of an LLM writing files or being allowed to access databases or similar cases directly distasteful; I have to review the output anyway and I'll decide what goes to the relevant disk locations / gets run.

Re: Cursor CLI

#103

Post by AdieuToLogic »

When I saw this, the question which immediately came to mind was:

  Who would turn loose arbitrary commands (content)
  generated by an LLM onto their filesystem?
Then I saw the installation instructions, which are:

  curl https://cursor.com/install -fsS | bash
And it made sense.

Only those comfortable with installing software by downloading shell commands from an arbitrary remote web site and immediately executing them would use it.

So what then is the risk of running arbitrary file system modifications generated from a program installed via arbitrary shell commands? None more than what was accepted in order to install it.

Both are opaque, unreviewed, and susceptible to various well known attacks (such as a supply chain attack[0]).

0 - https://en.wikipedia.org/wiki/Supply_chain_attack

Re: Cursor CLI

#104

Post by mrits »

rapind wrote: post #72
stillsut wrote: post #70

Earlier quoted context omitted.

Yeah I suspect some of these providers will become Microsoft in the '90s type bully holdouts on implementing the emerging conventions. But ultimately with CLI interface you have workarounds to all the major providers read in your system guidelines. But in an IDE - e.g. like MS had with VisualStudio - you more lock-in potential for your config files. Yesterday, I was writing about a way I found to pass the same guidel…

Isn't think just a symlink?

I'm at a point where I symlink differnet sets of docs to try to focus context so much I feel like maybe I need a git submodule with different branches of context I want. I left managing people to now manage AI

Re: Cursor CLI

#105

Post by esafak »

dgunay wrote: post #90
thehamkercat wrote: post #21

I wonder when all of them will adopt AGENT.md and stop using gemini.md/claude.md/crush.md/summary.md/qwen.md https://agent.md [redirect -> https://ampcode.com/AGENT.md ] https://agent-rules.org

I just wish the AGENTS.md standard wasn't a single file. I have a lot of smaller context documents that aren't applicable to every task, so I like to throw them into a folder (.ai/ or .agents/) and then selectively cat them together or tell the agent to read them.

You can put them in subdirectories like CODEOWNERS files. https://ampcode.com/AGENT.md#multiple-agent-files

Re: Cursor CLI

#106

Post by Touche »

byronic wrote: post #102
extr wrote: post #94

Earlier quoted context omitted.

Why not? Have you ever actually used these things? The risk is incredibly low. I run claude code with zero permissions every day for hours. Never a problem.

I have (not an exhaustive list) SSH keys and sensitive repositories hanging out on my filesystem. I don't trust _myself_ with that, let alone an LLM, unless I'm running ollama or similar local nonsense with no net connectivity. I'm a few degrees removed from an air gapped environment so obviously YMMV. Frankly I find the idea of an LLM writing files or being allowed to access databases or similar cases directly dista…

They don't have arbitrary access over your file system. They ask permission for doing most everything. Even reading files, they can't do that outside of the current working directory without permission.

Re: Cursor CLI

#107

Post by swader999 »

byronic wrote: post #102
extr wrote: post #94

Earlier quoted context omitted.

Why not? Have you ever actually used these things? The risk is incredibly low. I run claude code with zero permissions every day for hours. Never a problem.

I have (not an exhaustive list) SSH keys and sensitive repositories hanging out on my filesystem. I don't trust _myself_ with that, let alone an LLM, unless I'm running ollama or similar local nonsense with no net connectivity. I'm a few degrees removed from an air gapped environment so obviously YMMV. Frankly I find the idea of an LLM writing files or being allowed to access databases or similar cases directly dista…

Your obviously skilled, spending the money on a Claude only machine would pay for itself in less than three weeks. If I was your employer, it would be a no brainer.

Re: Cursor CLI

#108

Post by Touche »

stavros wrote: post #40
gorjusborg wrote: post #14

Earlier quoted context omitted.

Flip your thinking around for a second and consider why an IDE is required for an agent that codes for you? The IDE/editor is for me, the agent doesn't need it. That also means I am not forced to used whatever imperfect forked IDE the agent is implemented against.

I don't really need an IDE, but I do need a great code review interface.

I use lazygit for that. But any diff tool you like will work.

Re: Cursor CLI

#109

Post by didibus »

lvl155 wrote: post #76
didibus wrote: post #73

Earlier quoted context omitted.

I'm actually starting to think the opposite. If Cursor can build the better UX for all the use-cases, mobile/desktop chatbot, assistant, in IDE coding agent, CLI coding agent, web-based container coding agent, etc. In theory, they can spend all their resourcing on this, so you could assume they could have those be more polished. If they win the market-share here, than the models are just commodity, Cursor lets you pi…

No, model providers are not going to let Cursor eat their pie. The biggest cost in AI is in developing LLM models and inference. Players incurring those costs will basically control this market.

I don't think we'll have more than 2 players. I think it's like AMD and Intel, the LLM is almost like providing hardware. The software that exposes the LLM capabilities to the user is the layer that will be able to differentiate.

The models are just going to be fighting performance/cost. And people will choose the best performance for their budget.

And that's ignoring how good local models are getting as well.

It's not that they'll have their launch eaten by Cursor, it's just that they can't be as focused on user experience when they're also laser focused on improving the models to stay competitive.

Re: Cursor CLI

#110

Post by benbayard »

fastball wrote: post #101
teaearlgraycold wrote: post #100

Earlier quoted context omitted.

Why is Claude Code better than Cursor?

In my experience, it is much better at tool-calling, which is huge when we're talking about agentic coding. It also seems to do a better job of keeping things cleaning and not going off on tangents for anything that isn't accomplished in one shot.

I have had the exact opposite experience. Claude Code in any meaningful codebase for me gets stuck in loops of doing the wrong thing. Then when that doesn't work it deletes files and makes its own that don't have the problem it's encountering.

Cursor on the other hand, especially with GPT-5 today but typically with Sonnet 4.1, has been a workhorse at my company for months. I have never had Claude Code complete a meaningful ticket once. Even a small thing like fixing a small bug or updating the documentation on the site.

Would love any tips on how to make Claude Code not a complete waste of electricity.

Post reply on HN