I can try!

I currently use ChatGPT for random insights and discussions about a variety of topics. The memory is basically a grown context about me and my preferences and interests and ChatGPT uses it to tailor responses to my knowledge, so I could relate better.

This is for me far more natural and easier than either craft a default prompt preset or create each conversation individually, that would be way too much overhead to discuss random shower thoughts between real life stuff.

This is my use case and I discovered that this can be detrimental to specific questions and prompts and I see that it can be more beneficial to have careful written prompts each time. But my use case is really ad hoc usage without the time. At least for ChatGPT.

When coding, this fails fast. There regular context resets seem to be a more viable strategy.

▲

wps 14 hours ago | parent [-]

I see what you mean, but I like having a clean slate even for those one off questions. I don’t want a differing answer to a philosophical inquiry just because the LLM remembers a prior position I’ve written about you know?

▲

Retr0id 10 hours ago | parent | next [-]

I have all the history settings off for this reason, but something that worries me is that there's a fair bit of information about me trained right into the model weights. I'm not "famous" by any stretch but claude has awareness of some of my HN-front-page-hitting projects, etc., which I think should be enough to bias responses (although I haven't tried to measure it).

I set my name to "User" in the settings, so in a clean-slate chat it has nothing to go on, but the moment claude code does something like `git log` it knows who I am again. I've even considered writing some kind of redaction proxy.

▲

e1g 14 hours ago | parent | prev [-]

FWIW, both OpenAI and Anthropic have a toggle to do a “Temporary/Incognito Chat” that does not use or update memory. I too wish this was the default, and then you could opt in at the end of the chat to save some long term aspects into memory.

	▲	pfix 14 hours ago \| parent [-]
		That would be interesting, also at the start. As an option what to pull in. ChatGPT memory "improved" and now you normally don't even see anymore what it commits to memory!