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

Code Smarter, Not Harder: Developing with Cursor and Claude Sonnet

jstoppa.com

Post reply on HN
Print view View original

1–10 of 83 posts

Re: Code Smarter, Not Harder: Developing with Cursor and Claude Sonnet

#3

Post by brigadier132 »

I've been using cursor a bit, I don't know if it's because what I'm doing is not frontend web development but the results have not been as insane as others claim. I really don't have any difficulty creating basic web layouts or forms so an AI assistant doing that for me is nice but it does not transform my work.

Re: Code Smarter, Not Harder: Developing with Cursor and Claude Sonnet

#5

Post by simonw »

Something that's been amusing me about Cursor is that I feel a lot of the excitement about it isn't so much about Cursor, it's people realizing that LLMs have got REALLY good at writing code now. GPT-4 was good for the past year, but the latest models (especially Claude 3.5 Sonnet) are spectacular.

Those of us who've been copying and pasting LLM-generated code back and forth from ChatGPT and Claude.ai for the past year had figured this out already, so Cursor wasn't a huge surprise for us.

For a lot of people Cursor is the first time they've really appreciated how good this stuff has got - so it's getting a massive amount of buzz, much of which should really be credited to Claude 3.5 Sonnet.

(Cursor have done an excellent job designing editor features on top of that model and deserve credit for that, I'm just a bit tickled at some of the excitement which basically boils down to "Huh, LLMs can write good code now".)

Re: Code Smarter, Not Harder: Developing with Cursor and Claude Sonnet

#7

Post by DGCA »

brigadier132 wrote: post #3

I've been using cursor a bit, I don't know if it's because what I'm doing is not frontend web development but the results have not been as insane as others claim. I really don't have any difficulty creating basic web layouts or forms so an AI assistant doing that for me is nice but it does not transform my work.

I haven't done anything with Cursor that I wouldn't be able to do without it so far, but for me it's made certain tasks _much_ faster.

Re: Code Smarter, Not Harder: Developing with Cursor and Claude Sonnet

#8

Post by brigadier132 »

DGCA wrote: post #7
brigadier132 wrote: post #3

I've been using cursor a bit, I don't know if it's because what I'm doing is not frontend web development but the results have not been as insane as others claim. I really don't have any difficulty creating basic web layouts or forms so an AI assistant doing that for me is nice but it does not transform my work.

I haven't done anything with Cursor that I wouldn't be able to do without it so far, but for me it's made certain tasks _much_ faster.

The problem I have is when I ask it to do something that does not have 1 million examples on github from tutorials it will just output something completely non-functional.

I find it good for things that are completely derivative. Like, "implement a function that converts this type into another type"

Re: Code Smarter, Not Harder: Developing with Cursor and Claude Sonnet

#9

Post by hn_throwaway_99 »

OutOfHere wrote: post #6
samier-trellis wrote: post #2

To be clear, the main advantages over GitHub Copilot are ability to add other files as context and being able to have multiple chats going, right?

GitHub Copilot already includes open files in the context.

But not the whole repo - Cursor indexes all your files in a vector DB and then can use RAG when querying models. Perhaps the biggest benefit I get from Cursor is that I can ask it questions about the whole repo - when working with a sizable team in a large repo, this is hugely valuable.

Re: Code Smarter, Not Harder: Developing with Cursor and Claude Sonnet

#10

Post by dartos »

simonw wrote: post #5

Something that's been amusing me about Cursor is that I feel a lot of the excitement about it isn't so much about Cursor, it's people realizing that LLMs have got REALLY good at writing code now. GPT-4 was good for the past year, but the latest models (especially Claude 3.5 Sonnet) are spectacular. Those of us who've been copying and pasting LLM-generated code back and forth from ChatGPT and Claude.ai for the past ye…

I would love to see someone on stream use AI really effectively.

I really try, but for the life of me, I can’t get AI to generate anything useful beyond simple tests.

They’re still autocomplete++ for me.

Post reply on HN