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

How I write code using Cursor

arguingwithalgorithms.com

Post reply on HN
Print view View original

21–30 of 426 posts

Re: How I write code using Cursor

#21

Post by szundi »

forgotoldacc wrote: post #12
vishal-padia wrote: post #2

In the article, you mentioned that you've been writing code for 36 years, so don't you feel IDEs like cursor make you feel less competent? Meaning I loved the process of scratching my head over a problem and then coming to a solution but now we have AI Agents solving the problems and optimizing code which takes the fun out of it.

I feel like in the early stages of becoming a programmer, learning how to do all those little baseline problems is fun. But eventually you get to a point where you've solved variations of the problem hundreds of times before, and it's just hours of time being burnt away writing it again with small adjustments. It's like getting into making physical things with only a screwdriver and a hammer. Working with your hands…

Completely agreed. Don’t be afraid to embrace this. You have to give it an active month until it starts to work in your hands though.

Re: How I write code using Cursor

#22

Post by szundi »

ziofill wrote: post #7
vishal-padia wrote: post #2

In the article, you mentioned that you've been writing code for 36 years, so don't you feel IDEs like cursor make you feel less competent? Meaning I loved the process of scratching my head over a problem and then coming to a solution but now we have AI Agents solving the problems and optimizing code which takes the fun out of it.

I’ve been using cursor for a while now and I think that if a problem is simple enough for an LLM to work out on its own, it’s probably not worth scratching one’s head over…

Agreed with added experience of mine: sometimes Cursos gives me a simpler yet perfect solution. And I am grateful for it.

Re: How I write code using Cursor

#23

Post by bufferoverflow »

elashri wrote: post #16

My problem with all AI code assistants is usually the context. I am not sure how cursor fare in this regard but I always struggle to feed the model enough of the code project to be useful for me on a level more than providing line per line suggestion (which copilot does anyway). I don't have experience with cursor or cody (other alternative) and how they tackle this problem by using embeddings (which I suppose have s…

Cursor has 10K tokens context window. Which is quite low compared to the top LLMs.

https://forum.cursor.com/t/capped-at-10k-context-no-matter-a...

Re: How I write code using Cursor

#24

Post by benreesman »

I’m doing an experiment in this in real time: I’ve got a bunch of top-flight junior folks, all former Jane and Google and Galois and shit, but all like 24.

I’ve also been logging every interaction with an LLM and the exit status of the build on every mtime of every language mode file and all the metadata: I can easily plot when I lean on the thing and when I came out ahead, I can tag diffs that broke CI. I’m measuring it.

My conclusion is that I value LLMs for coding in exact the same way that the kids do: you have to break Google in order for me to give a fuck about Sonnet.

LLMs seem like magic unless you remember when search worked.

Re: How I write code using Cursor

#25

Post by abricq »

This last month I decided to try the Jetbrain equivalent of Cursor, for their IDEs (https://www.jetbrains.com/ai/). It's a pluging well integrated in the code editor that you can easily summon.

I work in Rust and I had to start working with several new libraries this month. One example of them is `proptest-rs`, a rust property testing library that defines a whole new grammar to define the tests. I am 100% sure that I spent much less time to get on-boarded with the librariy's best practices and usages. I just quickly went through their book (to learn the vocabulary) and asked the AI to generate the code itself. I was very surprised that it did not do any mistakes, considering that sort of weird custom grammar of the lib. I will at least keep trying for another months.

Re: How I write code using Cursor

#26

Post by dartos »

benreesman wrote: post #24

I’m doing an experiment in this in real time: I’ve got a bunch of top-flight junior folks, all former Jane and Google and Galois and shit, but all like 24. I’ve also been logging every interaction with an LLM and the exit status of the build on every mtime of every language mode file and all the metadata: I can easily plot when I lean on the thing and when I came out ahead, I can tag diffs that broke CI. I’m measurin…

> LLMs seem like magic unless you remember when search worked.

Yikes. I didn’t even think about this, but it’s true.

I’m looking for the kinds of answers that Google used to surface from stack overflow

Re: How I write code using Cursor

#28

Post by nopinsight »

benreesman wrote: post #24

I’m doing an experiment in this in real time: I’ve got a bunch of top-flight junior folks, all former Jane and Google and Galois and shit, but all like 24. I’ve also been logging every interaction with an LLM and the exit status of the build on every mtime of every language mode file and all the metadata: I can easily plot when I lean on the thing and when I came out ahead, I can tag diffs that broke CI. I’m measurin…

What domain/type of software do you and they work on? Cursor has been quite effective for me and many others say the same.

As long as one prompts it properly with sufficient context, reviews the generated code, and asks it to revise as needed, the productivity boost is significant in my experience.

Re: How I write code using Cursor

#29

Post by benreesman »

nopinsight wrote: post #28
benreesman wrote: post #24

I’m doing an experiment in this in real time: I’ve got a bunch of top-flight junior folks, all former Jane and Google and Galois and shit, but all like 24. I’ve also been logging every interaction with an LLM and the exit status of the build on every mtime of every language mode file and all the metadata: I can easily plot when I lean on the thing and when I came out ahead, I can tag diffs that broke CI. I’m measurin…

What domain/type of software do you and they work on? Cursor has been quite effective for me and many others say the same. As long as one prompts it properly with sufficient context, reviews the generated code, and asks it to revise as needed, the productivity boost is significant in my experience.

I get value out of LLMs on stock Python or NextJS or whatever where that person was in fact a lossy channel from SO to my diff queue.

If there’s no computation then there’s no computer science. It may be the case that Excel with attitude was a bubble in hiring.

But Sonnet and 4o both suck at why CUDA isn’t detected on this SkyPilot resource.

Re: How I write code using Cursor

#30

Post by Maxion »

zdragnar wrote: post #19
NitpickLawyer wrote: post #15

Earlier quoted context omitted.

> Is cursor considered a better solution? It's the best I've tried so far. I only tried copilot when it came out, so it might have improved a lot since then, perhaps someone using both now can chime in. There's two things I like about cursor - the overall multi-file edit -> I use this for scaffolding whatever I need, at a high level, and claude 3.5 seems a bit better than 4o for this. The tab thing really works, and…

Didn't sublime text have this with snippets? I vaguely recall setting some up with tab stops for the parts that need manual completion. Not AI, but it was nice to have back 10-ish or whatever years ago.

No, that was a completely different thing.
Post reply on HN