Would you mind sharing 1 example how you do it? Or any web link?

I have spent a lot of time reading through prompt engineering, but coding examples to adapt to latest versions are rare to find.

They gave an example of this in the launch live stream, about 12 minutes in: https://www.youtube.com/live/outcGtbnMuQ

I don’t bother much with prompt engineering. I just treat ChatGPT as a pair programmer who can’t see my editor. I tell it where files are, what I’m using, copy and paste relevant code in, and it just works.

The big “breakthrough” for me was unlearning all of my search engine habits of thinking I need to be precise and talk to it like a machine. I use compliments like “that’s great” and it seems to reinforce good answers well enough.

Just treat it like a human on the other side of the screen and adjust as necessary.

Also pay the $20 - GPT-3.5 is not good, GPT-4 is junior engineer good. Most of my time is now spent describing problems to it and code reviewing what it does.

Edit: I do use prompt engineering when I’m building AI enabled products to help keep things on the rails. But for my personal use of ChatGPT I just let ‘er rip.

But with that type of usage don’t you hit the message cap on gpt4?

Have you tried and compared phind.com?

Remember you are not an AI. You are a human, so it takes you significantly more time to read a response and produce another query. 25 messages every 3 hours is a lot when you're doing what parent described. When I'm programming, I also do other things too. 3 hours goes by fast.

Have you tried phind.com ? It scrapes sites so it can get additional context

Try bing then, gpt-4 but up to date.