21–30 of 270 posts
This kind of just sounds like junk that will clog up the context window I'll have try it out though to know for sure
So, so, so curious how they are implementing this.
I wouldn't be surprised if they essentially just add it to the prompt. ("You are ChatGPT... You are talking to a user that prefers cats over dogs and is afraid of spiders, prefers bullet points over long text...").
Adding the entire file (or memory in this case) would take up too much of the context. So just query the DB and if there's a match add it to the prompt after the conversation started.
Earlier quoted context omitted.
I wouldn't be surprised if they essentially just add it to the prompt. ("You are ChatGPT... You are talking to a user that prefers cats over dogs and is afraid of spiders, prefers bullet points over long text...").
I think RAG approach with Vector DB is more likely. Just like when you add a file to your prompt / custom GPTs. Adding the entire file (or memory in this case) would take up too much of the context. So just query the DB and if there's a match add it to the prompt after the conversation started.
I could imagine that once there's too many, it would indeed make sense to classify them as a database, though: "Prefers cats over dogs" is probably not salient information in too many queries.
I love this idea and it leads me to a question for everyone here. I've done a bunch of user interviews of ChatGPT, Pi, Gemini, etc. users and find there are two common usage patterns: 1. "Transactional" where every chat is a separate question, sort of like a Google search... People don't expect memory or any continuity between chats. 2. "Relationship-driven" where people chat with the LLM as if it's a friend or colle…
This kind of just sounds like junk that will clog up the context window I'll have try it out though to know for sure
I've been finding with these large context windows that context window length is no longer the bottleneck for me — the LLM will start to hallucinate / fail to find the stuff I want from the text long before I hit the context window limit.
I love this idea and it leads me to a question for everyone here. I've done a bunch of user interviews of ChatGPT, Pi, Gemini, etc. users and find there are two common usage patterns: 1. "Transactional" where every chat is a separate question, sort of like a Google search... People don't expect memory or any continuity between chats. 2. "Relationship-driven" where people chat with the LLM as if it's a friend or colle…
For those cases there are quite a few things that I'd like it to memorize, like programming library preferences ("When working with dates prefer `date-fns` over `moment.js`") or code style preferences ("When writing a React component, prefer function components over class components"). Currently I feed in those preferences via the custom instructions feature, but I rarely take some time to update them, so the memory future is a welcome addition here.
Will memory provide a solution to that or will be a different thing to ignore?
So, so, so curious how they are implementing this.
Periodically "compress" chat history into relevant context and keep that slice of history as part of the memory.
15 day message history could be condensed greatly and still produce great results.
This kind of just sounds like junk that will clog up the context window I'll have try it out though to know for sure