Hi, I've talked to GPT-4o more than 1.5 million words counted prompts and answers together. I would recognize this model inside hundreds or thousands of other models because of this very special tone. Could you imagine setting up an environment where one can change system prompt and insert own talk history for testing purposes? I'd like to test if I can make it answer the same way it did before if getting the right system prompt including memories and the right context. Would free me and others from having to set up own API programs... Interested?