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

Tips for better coding with ChatGPT

nature.com

Post reply on HN
Print view View original

91–100 of 114 posts

Re: Tips for better coding with ChatGPT

#91

Post by knowsuchagency »

anotherpaulg wrote: post #12

I've been using the openai apis to write and edit code for 3-4 months now. So I think that makes me an old timer (ha!). I have also been building tooling for improving the chat based coding experience [0]. All of this work has given me an opportunity to think about how to work best with GPTs on coding, and I've shared some thoughts about this in the past [1]. Here are some of my thoughts on how to code with chatgpt.…

Aider is such an awesome project! I didn't know about it until I read this comment. I also wanted a way to provide my code as context from within the terminal without having to copy and paste back and forth. The tool I wrote (llmo) seems pretty similar to yours, although it uses the Textual library and Rich.

https://github.com/knowsuchagency/llmo

I'm really excited to try out aider, thanks for making it!

Re: Tips for better coding with ChatGPT

#92

Post by yi_xuan »

Jeff_Brown wrote: post #80
agentcoops wrote: post #21

Further evidence of my justified true belief that the world will rapidly divide between those who already had programmatic control over their computers, now infinitely more productive through direct access to the GPT APIs (to say nothing of the firms that will use LLMs only internally, trained on their own codebase for example) and those who believe GPT=ChatGPT, which will slowly become but another conduit for ads th…

> now infinitely more productive How much more productive do you feel you are coding with an LLM? As another HN user said, to me it's like a talking dog -- incredible yet useless.

From my personal experience, it's quite useful but not as much as a lot of people thought it would be. The ability solving 'simple' questions is great. I used it more as a smarter google.

Re: Tips for better coding with ChatGPT

#93

Post by hxugufjfjf »

agentcoops wrote: post #23
chank wrote: post #6

> Trust but verify... Based on my own attempts to have ChatGPT generate code for me, it's better to NOT trust it. It tends to hilucinate even with simple requirements.

If you're already a programmer, there's no excuse for not working directly with the APIs. Learn about context and prosper.

There is one. OpenAI has not yet given you access (waitlist).

Re: Tips for better coding with ChatGPT

#94

Post by inopinatus »

Jeff_Brown wrote: post #80
agentcoops wrote: post #21

Further evidence of my justified true belief that the world will rapidly divide between those who already had programmatic control over their computers, now infinitely more productive through direct access to the GPT APIs (to say nothing of the firms that will use LLMs only internally, trained on their own codebase for example) and those who believe GPT=ChatGPT, which will slowly become but another conduit for ads th…

> now infinitely more productive How much more productive do you feel you are coding with an LLM? As another HN user said, to me it's like a talking dog -- incredible yet useless.

One simply needs to think more laterally about the dog.

Re: Tips for better coding with ChatGPT

#95

Post by weinzierl »

spaceman_2020 wrote: post #81
agentcoops wrote: post #21

Further evidence of my justified true belief that the world will rapidly divide between those who already had programmatic control over their computers, now infinitely more productive through direct access to the GPT APIs (to say nothing of the firms that will use LLMs only internally, trained on their own codebase for example) and those who believe GPT=ChatGPT, which will slowly become but another conduit for ads th…

I haven’t been able to get GPT-4 API access months after applying and being a paid subscriber. The world right now seems to be divided more into “have GPT-4 API/ don’t have GPT-4 API”.

With more and better models released, getting access to OpenAI's API is becoming less interesting.

What is interesting is having access to GPUs (cloud or real hardware). The world is divided in "has access to enough GPU power/don't has access to enough GPU power".

My prediction is that this will get worse for a while.

Re: Tips for better coding with ChatGPT

#96

Post by boringuser2 »

weinzierl wrote: post #95
spaceman_2020 wrote: post #81

Earlier quoted context omitted.

I haven’t been able to get GPT-4 API access months after applying and being a paid subscriber. The world right now seems to be divided more into “have GPT-4 API/ don’t have GPT-4 API”.

With more and better models released, getting access to OpenAI's API is becoming less interesting. What is interesting is having access to GPUs (cloud or real hardware). The world is divided in "has access to enough GPU power/don't has access to enough GPU power". My prediction is that this will get worse for a while.

"Better"?

Get out of town.

Re: Tips for better coding with ChatGPT

#97

Post by ta988 »

spaceman_2020 wrote: post #81
agentcoops wrote: post #21

Further evidence of my justified true belief that the world will rapidly divide between those who already had programmatic control over their computers, now infinitely more productive through direct access to the GPT APIs (to say nothing of the firms that will use LLMs only internally, trained on their own codebase for example) and those who believe GPT=ChatGPT, which will slowly become but another conduit for ads th…

I haven’t been able to get GPT-4 API access months after applying and being a paid subscriber. The world right now seems to be divided more into “have GPT-4 API/ don’t have GPT-4 API”.

They just can't scale to the demand, that's their main issue right now.

Re: Tips for better coding with ChatGPT

#98

Post by james-revisoai »

anotherpaulg wrote: post #56
james-revisoai wrote: post #52

Earlier quoted context omitted.

Great tooling. I was using CodeGPT but this looks better. And it's exciting to have those command line options to easily insert other contextual input like command outputs. Can I ask about your plans? CodeGPT planned to add semantic embeddings of code, but I haven't seen any updates for quite a time. The idea being that, like walking an Abstract Syntax Tree of the code, you could include relevant functions and functi…

Thanks for checking out aider. Let me know if you give it a try and find it useful. Yes, aider already has features to provide GPT with "code context" to let it edit larger, more complex codebases. I wrote up some notes about these features: https://aider.chat/docs/ctags.html You might be especially interested in the "future work" section near the end. I have actually shipped some of these ideas into the tool already…

I did read that and find it interesting, but without knowing it was now filtering contextually (awesome!), I didn't consider it for the codebases I was looking at due to the context size needed. Seems like keyword matching vs semantic/index search at first glance but I see you are indeed pushing the envelope here.

Great to see, thanks again for developing it.

Re: Tips for better coding with ChatGPT

#99

Post by weinzierl »

boringuser2 wrote: post #96
weinzierl wrote: post #95

Earlier quoted context omitted.

With more and better models released, getting access to OpenAI's API is becoming less interesting. What is interesting is having access to GPUs (cloud or real hardware). The world is divided in "has access to enough GPU power/don't has access to enough GPU power". My prediction is that this will get worse for a while.

"Better"? Get out of town.

Would you care to explain what you mean?

I meant 40B Falcon is better than 65B LLaMA in many benchmarks and we will see even better models released with time.

What is wrong with that?

Re: Tips for better coding with ChatGPT

#100

Post by boringuser2 »

weinzierl wrote: post #99
boringuser2 wrote: post #96

Earlier quoted context omitted.

"Better"? Get out of town.

Would you care to explain what you mean? I meant 40B Falcon is better than 65B LLaMA in many benchmarks and we will see even better models released with time. What is wrong with that?

That is fair, your post left it a bit ambiguous if you meant better in reference to GPT-4 or not.

Competitors aren't even at GPT 3.5.

Post reply on HN