I’ve had a few conversations with ChatGPT that imply this is a possibility, and also this link confirms it.
I think this opens up some doors. Anyone know the simplest way to accomplish this without being a coding expert?
You don’t need to be an expert, but there’s no free lunch here. You’d have to use the API, or at the very least some no-code tool to do it.
The article you linked probably refers to the @ functionality. That doesn’t allow gpts to converse with each other, just allows you to query a specific gpt with the existing context.
chatgpt isn’t a reputable authority on anything. for your consideration:
1 Like
True, but I’ve found it to be a step up from homosapiens.
But yes, it seems the API would be the best route…just wondering if anyone had any recent experience with that.
just a model talking to itself has some merit (call it reflection/reflexion), but it depends on what you’re trying to achieve. In any case, you’re gonna have to figure out how you’re going to manage the conversation so you don’t just endlessly burn tokens or enter hallucinationland.
1 Like
I think it’s within my reach now that I’m studying Python in-depth…it’s on my list. I’ll update on my progress.
1 Like
good luck 
starting with jupyter might be a good idea if you’re new and you want to iteratively try stuff out
1 Like
Hmmm…I prefer Pycharm to Jupyter; is there a difference in functionality there with the OpenAI API?
1 Like
When using the OpenAI API in Python, there is no difference whether you use an IDE or Jupyter Notebook.
Starting with Jupyter might be more convenient for trying things out easily.
1 Like
I think pycharm supports ipynb, so it wouldn’t make much of a difference. It’s just that the notebook format might be helpful when rapidly iterating though stuff, as opposed building and restarting a python app every time
But! do what feels most comfortable to you, doing something is more important than how you do it
1 Like
Yes, hopefully there are some alternative ways to save data.