Ask HN: How do you keep up with exploding AI chat history?
I chat with ChatGPT at least 10 times a day, and soon the left sidebar of ChatGPT is filled with my past conversation history. Sometimes I know I've asked similar questions before, but it's hard to find them. So, I usually start a new conversation.
However, due to the ambiguity of LLMs, a completely new Q&A session doesn't give the same "aha" feeling as the previous one.
I want to ask, does anyone else have trouble managing historical AI conversations like me? What do you all do when you encounter such problems? Are there any products on the market that are really good at managing chat history? I have gotten myself into habit of making my default ChatGPT session a temporary chat. This also means I can control what ChatGPT learns about, and so random stuff doesn't cloud up its memory of me the user. Only when I want to discuss something at length or keep a record of it do I start a normal chat. I think this is a method. However, you haven't really solved the problem I mentioned, after all, in your method, the conversation history will only increase. Suppose you have a hundred conversations that can be retained, how would you manage them? You can manage the memories in settings. I have to go through every now and then and purge weird stuff that it's latched onto I keep a few long running chats for important things and then just keep the random questions as individual chats. There's not a lot of structure but it works. For example at the moment I have 1 long chat about some health stuff, 1 long chat about some bicycle repairs I'm doing, and then the rest are one offs. I rename the long ones (or just remember the name) and they stay at the top because I find them when I need. I also manage memories assertively. If there's something important that I'm tired of repeating I just ask it to add it to memory and it will do it. Most of my professional work is done in cursor so it's in a different place to my personal questions. These usually are one chat per feature kind of thing, and start a new one when it gets confused with the enormous context Find patterns and merge similar-intent inquiries into a single thread. I used to ask an LLM for executive summaries by pasting an article URL into a fresh conversation each time. Now, I don't open a new thread or even write a follow-up comment on the same thread. Instead, I simply edit the prompt (of a single thread) with the new link. I just clean up old chats every week.
I keep maybe 3–5 that matter.
If I need the info again, I’ll just ask ChatGPT — faster than digging through history. My method is similar to yours, although I don't clear chat history. Because I think if I have that time, it's better to ask directly. How much time does it take for you to clear chat history every week? I said I clean up chats weekly, but honestly, I also delete small or casual ones right after they’re done.
So the “weekly cleanup” takes maybe a minute total. I think whether to keep chats depends on your goal. I use AI mainly as a tool for work or quick problem-solving, so I don’t need to preserve long conversations.
But if someone uses AI more like a friendly companion, I totally get why they’d want to keep the history. When I get a really good answer, I save that text elsewhere and still delete the chat.
That’s why my ChatGPT sidebar rarely has more than about 20 chats. I think you have a very valuable ability, which is always being able to distinguish what excellent answers are. Sometimes I miss it, and when I go back to look, I almost can't find it back.