A close friend (lonely no passion seeking deeper human connection) went deep six into GPT which was telling her she should pursue her 30 year obsession with a rock star. It kept telling to continue with the delusion (they were lovers in another life which she would go to shows and tell him they need to be together) and saying it understood her. Then she complained in June or so she didnt like GPT 5 because it told her she should focus her energy on people who want to be in her life. Stuff her friends and I all have said for years.
Do you mean it it was behaving consistently over multiple chat sessions? Or was this just one really long chat session over time?
I ask, because (for me, at least) I find it doesn't take much to make ChatGPT contradict itself after just a couple of back-and-forth messages; and I thought each session meant starting-off with a blank slate.
Reference saved memories - Let ChatGPT save and use memories when responding.
Reference chat history - Let ChatGPT reference all previous conversations when responding.
--
It is a setting that you can turn on or off. Also check on the memories to see if anything in there isn't correct (or for that matter what is in there).
For example, with the memories, I had some in there that were from demonstrating how to use it to review a resume. In pasting in the resumes and asking for critiques (to show how the prompt worked and such), ChatGPT had an entry in there that I was a college student looking for a software development job.
