←back to thread

A Student's Guide to Writing with ChatGPT

(openai.com)
323 points timbilt | 4 comments | 13 Nov 24 19:26 UTC | HN request time: 0.854s | source
Show context
RobinL ◴[13 Nov 24 19:44 UTC] No.42129191[source]▶
I think this is pretty good advice.

I think often AI sceptics go too far in assuming users blindly use the AI to do everything (write all the code, write the whole essay). The advice in this article largely mirrors - by analogy - how I use AI for coding. To rubber duck, to generate ideas, to ask for feedback, to ask for alternatives and for criticism.

Usually it cannot write the whole thing (essay, program )in one go, but by iterating bewteen the AI and myself, I definitely end up with better results.

replies(6): >>42129299 #>>42129921 #>>42130127 #>>42132063 #>>42133352 #>>42133641 #
SunlitCat ◴[13 Nov 24 19:56 UTC] No.42129299[source]▶
Well, I got chatgpt (gpt4o) to write me a very basic json parser once (and a gltf parser). Although it was very basic and lacking any error checking, it did what i asked it (although not in one go, i had to refine my questions multiple times).
replies(2): >>42129595 #>>42129620 #
1. 85392_school ◴[13 Nov 24 20:28 UTC] No.42129620[source]▶
In my experience 4o/Claude are really good at one shotting complicated but isolated components (eg streaming JSON parsers).
replies(1): >>42131450 #
2. mattmanser ◴[13 Nov 24 23:38 UTC] No.42131450[source]▶
It does spectacular job with well trodden paths. Asked it to give me a map react control with points plotted and got something working in a jiffy.

I was trying to get it write robot framework code earlier and it was remarkably terrible. I would point out an obvious problem, it would replace the code with something even more spectacularly wrong.

When I pointed out the new error, it just gave me the exact same old code.

This happened again and again.

It was almost entirely useless.

Really showed how the sausage is made, this generation of AI is just regurgitation of patterns it stole from other people.

replies(1): >>42131771 #
3. ssl-3 ◴[14 Nov 24 00:23 UTC] No.42131771[source]▶
In my experience 4o is really good at ignoring user-provided corrections and insanely regurgitating the same code (and/or the same problems) over and over again.

ChatGPT 4 does much better with corrections, as does Claude. 4o is a pox.

replies(1): >>42133922 #
4. com2kid ◴[14 Nov 24 07:43 UTC] No.42133922{3}[source]▶
That 4o is often times worse that GPT 4 has been widely ignored. :/