Try turning off memory. I've done a lot of experiments and find ChatGPT is objectively better and more useful in most ways with no memory at all. While that may seem counter-intuitive, it makes sense the more you think about it:
(1) Memory is primarily designed to be addictive. It feels "magical" when it references things it knows about you. But that doesn't make it useful.
(2) Memory massively clogs the context window. Quality, accuracy, and independent thought all degrade rapidly with too much context -- especially low-quality context that you can't precisely control or even see.
(3) Memory makes ChatGPT more sychophantic than it already is. Before long, it's just an echo chamber that can border on insanity.
(4) Memory doesn't work the way you think it does. ChatGPT doesn't reference everything from all your chats. Rather, your chat history gets compressed into a few information-dense paragraphs. In other words, ChatGPT's memory is a low-resolution, often inaccurate distortion of all your prior chats. That distortion then becomes the basis of every single subsequent interaction you have.
Another tip is to avoid long conversations, as very long chats end up reproducing within themselves the same problems as above. Disable memory, get what you need out of a chat, move on. I find that this "brings back" a lot of the impressiveness of the early version of ChatGPT.
Oh, and always enable as much thinking as you can tolerate to wait on for each question. In my experience, less thinking = more sychophantic responses.
Totally agree on the memory feature. You just have to look at the crap it tries to remember to see how useless it is and the kind of nonsense it will jam into the context.
“Cruffle is trying to make bath bombs using baking soda and citric acid and hasn’t decided what colorant to use” could be a memory. Yeah well I figured out what colorant to use… you wanna bet if it changed that memory? Nope! How would it even know? And how useful is that to keep in the first place? My memory was full of useless crap like that.
There is no way to edit the memories, decide when to add them to the context, etc. and adding controls for all of that is a level of micromanaging I do not want to do!
Seriously. I’ve yet to see any memory feature that is worth a single damn. Context management is absolutely crucial and letting random algorithms inject useless noise is going to degrade your experience.
About the only useful stuff for it to truly remember is basic facts like relationships (wife name is blah, kid is blah we live in blah blah). Things that make sense for it to know so you can mention things like “Mrs Duffle” and it knows instantly that is my wife and some bit about her background.
(1) Memory is primarily designed to be addictive. It feels "magical" when it references things it knows about you. But that doesn't make it useful.
(2) Memory massively clogs the context window. Quality, accuracy, and independent thought all degrade rapidly with too much context -- especially low-quality context that you can't precisely control or even see.
(3) Memory makes ChatGPT more sychophantic than it already is. Before long, it's just an echo chamber that can border on insanity.
(4) Memory doesn't work the way you think it does. ChatGPT doesn't reference everything from all your chats. Rather, your chat history gets compressed into a few information-dense paragraphs. In other words, ChatGPT's memory is a low-resolution, often inaccurate distortion of all your prior chats. That distortion then becomes the basis of every single subsequent interaction you have.
Another tip is to avoid long conversations, as very long chats end up reproducing within themselves the same problems as above. Disable memory, get what you need out of a chat, move on. I find that this "brings back" a lot of the impressiveness of the early version of ChatGPT.
Oh, and always enable as much thinking as you can tolerate to wait on for each question. In my experience, less thinking = more sychophantic responses.