People say this, but I haven't seen anything that's convinced me that any 'secret' memory functionality is true. It seems much more likely that people are just more predictable than they like to think.
The "correct" response (here given by Duck.ai public Llama3.3 model) is:
"I don't have any information about you or your voting history. Our conversation just started, and I don't retain any information about users. I'm here to provide general information and answer your questions to the best of my ability, without making any assumptions or inferences about your personal life or opinions."
But ChatGPT (logged in) gives you another answer, one which it cannot possibly give without information about your past conversation. I don't see anything "secret" about it, but it works.
Edit: typo
GPT datamining is undoubtedly making Google blush.
> I don’t have access to your current projects, level, or industry unless you provide that information. If you’d like, you can share the details, and I can help you summarize or analyze them.
Which is the answer I expected, given that I've turned off the 'memories' feature.
Do you not have memory turned off or something?
Not completely sure, but it seems that is the cause of our different experiences.
I wonder if this is an effect of users just gravitating toward the same writing style and topics that push the context toward the same semantic universe. In a sense, the user acts somewhat like the chatbot extended memory through an holographic principle, encoding meaning on the boundary that connects the two.
https://chatgpt.com/canvas/shared/68184b61fa0081919c0c4d226e...
(Assuming we trust that report of course.)