Sounds like there are two misconceptions there: the idea that ChatGPT can read URLs (it can't - https://simonwillison.net/2023/Mar/10/chatgpt-internet-acces... ) and the idea that ChatGPT can remember details of conversations past the boundaries of the current chat.
This is something I've noticed too: occasionally I'll find someone who is INCREDIBLY resistant to learning that ChatGPT can't read URLs. It seems to happen mostly with people who have been pasting URLs into it for weeks and trusting what came back - they'd rather continue to believe in a provably false capability than admit that they've wasted a huge amount of time believing made-up bullshit.
I took “this thing isn’t nearly as smart as everyone’s making it out to be” from that session, but you’re the first person to make it clear that it’s not actually reading the rather simple page I directed it to.
This is an incredibly strong human tendency in general. We all do it, including you and I. It's one of the things that it's wise to be constantly on guard about.
For some people it borderline is a cult now, even here on HN, they'll give it intelligence, personality, character, &c.
On my side I now search for the most relevant Q&A pair based on the embedding of user's input and QA and jam as much as I can into the token limit. It provides accurate answers 99% of the time. If it can't find a suitable answer, it may create a plausible response on the spot, but that's getting rarer as training set grows.
To prevent the bot from providing incomplete information, you can instruct it to ask users to contact support via email if it doesn't have enough information - either prompt engineering or examples in training set. Alternatively, you can have the bot insert a token like "%%TICKET%%" which you can later use to open a support ticket, summarizing the conversation and attaching relevant chat history, logs, etc.