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

101–110 of 114 posts

Re: Tips for better coding with ChatGPT

#101

Post by lannisterstark »

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.

>incredible yet useless.

I almost always begin my tasks with ChatGPT, by asking it for a framework. "Design a x request that gets me results in form of this JSON, and now display it on y table according to this criteria"

It gives me framework, I adjust and expand upon it. Works wonderfully.

I even have a 'bot' running on one of the IRC channels that was almost 100% self written by ChatGPT.

Re: Tips for better coding with ChatGPT

#102

Post by paulmooreparks »

apples_oranges wrote: post #13
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.

I think they should use a different name altogether for chatGPT 4 as it is very different and superior to 3.5. And when people say chatGPT doesn't work for me, I would like to know which one they tried.

I've been seeing this "try ChatGPT 4" advice all over HN. I am using 4, and it still hallucinates and generates quite useless code. It's only marginally better in my experience.

Re: Tips for better coding with ChatGPT

#103

Post by agentcoops »

boringuser2 wrote: post #100
weinzierl wrote: post #99

Earlier quoted context omitted.

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.

When I use ChatGPT, I find anything but GPT4 unusable; when I'm programming against the API, I actually tend to find myself using GPT3.5. I still haven't had a chance to experiment with the opensource LLMs, but that's my project for next month.

Re: Tips for better coding with ChatGPT

#104

Post by glau »

throwaway4aday wrote: post #72
glau wrote: post #51

Earlier quoted context omitted.

Personally, I’M terrified of people using ChatGPT for serious coding work. They will be seeding the future with vulnerable/buggy software that no one understands. Granted, us humans are doing that now. Just many orders of magnitude slower. Probably slow enough that we can find/fix the important stuff. The other aspect that terrifies me is the potential for nation state entities with deep pockets to inject vulnerabili…

LLMs are also capable of analyzing, describing, and debugging software. There have been several papers published on this. So I wouldn't worry too much about any new buggy software being produced. In a few years, LLMs will probably be issuing PRs on your repos to fix things you haven't gotten around to or noticed yet.

This actually seems like a great use case. Read and flag potential bugs for review. Although if it wrote the code in the first place how would it identify the bug? What it produced was something close to the most likely result given what it has seen so far

Re: Tips for better coding with ChatGPT

#105

Post by glau »

mym1990 wrote: post #75
glau wrote: post #51

Earlier quoted context omitted.

Personally, I’M terrified of people using ChatGPT for serious coding work. They will be seeding the future with vulnerable/buggy software that no one understands. Granted, us humans are doing that now. Just many orders of magnitude slower. Probably slow enough that we can find/fix the important stuff. The other aspect that terrifies me is the potential for nation state entities with deep pockets to inject vulnerabili…

Are you able to back up the claim that ChatGPT code, when refined and deployed to production, is more buggy than code that is patchworked together by 10-20 stack overflow posts until something sticks?

I didn’t make that assertion. My fears are based on the speed that code of unknown quality, which is also poorly understood can be produced. I specifically said:

Granted, us humans are doing that now. Just many orders of magnitude slower. Probably slow enough that we can find/fix the important stuff.

Re: Tips for better coding with ChatGPT

#106

Post by boredemployee »

agentcoops wrote: post #103
boringuser2 wrote: post #100

Earlier quoted context omitted.

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.

When I use ChatGPT, I find anything but GPT4 unusable; when I'm programming against the API, I actually tend to find myself using GPT3.5. I still haven't had a chance to experiment with the opensource LLMs, but that's my project for next month.

I have preferred GPT3.5. GPT4 is slow and verbose, I only resort to this model when all my prompts in 3.5 didn't give the expected result.

Re: Tips for better coding with ChatGPT

#107

Post by GiselaWag12 »

I never thought I would get back my funds since I already lost hope until I found a hacker and a recovery agent, RecoveryNerd who I contacted via email at (recoverynerd@mail.com) and gave me a leap of faith in finding my funds. I personally would recommend Recovery Nerd since this is the least I could do for him after he saved my life by helping me recover my 47,000 USD worth of Bitcoin in less than three weeks from an online scammer. If you want to recover your lost funds or have any questions in regards to recovery, feel free to contact and be a hundred percent sure never to regret it.

Re: Tips for better coding with ChatGPT

#108

Post by throwaway4aday »

glau wrote: post #104
throwaway4aday wrote: post #72

Earlier quoted context omitted.

LLMs are also capable of analyzing, describing, and debugging software. There have been several papers published on this. So I wouldn't worry too much about any new buggy software being produced. In a few years, LLMs will probably be issuing PRs on your repos to fix things you haven't gotten around to or noticed yet.

This actually seems like a great use case. Read and flag potential bugs for review. Although if it wrote the code in the first place how would it identify the bug? What it produced was something close to the most likely result given what it has seen so far

This paper explains it better than I could in a comment https://arxiv.org/abs/2304.05128

Re: Tips for better coding with ChatGPT

#109

Post by braindead_in »

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 looks cool. Gonna try it out today. Have you tried out StarCoder or Replit-code?
Post reply on HN