11–20 of 270 posts
So, so, so curious how they are implementing this.
That was a common hack for the LLM context length problem, but now that context length is "solved" it could be more useful to align output a bit better.
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…
Personally, I always expect every "conversation" to be starting from a blank slate, and I'm not sure I'd want it any other way unless I can self-host the whole thing. Starting clean also has the benefit of knowing the prompt/history is in a clean/"known-good" state, and that there's nothing in the memory that's going to cause the LLM to get weird on me.
This matters a lot for prompt injection/hijacking. Not that I'm clamoring to give OpenAI access to my personal files or APIs in the first place, but I'm definitely not interested in giving a version of GPT with more persistent memory access to those files or APIs. A clean slate is a mitigating feature that helps with a real security risk. It's not enough of a mitigating feature, but it helps a bit.
Anyway, it seems to be implemented quite well with a lot of user controls so that is nice. I think it's possible I will soon upgrade to a Team plan and get the family on that.
A habit I have is that if it gets something wrong I place the correction there in the text. The idea being that I could eventually scroll down and find it. Maybe in the future, they can record this stuff in some sort of RAGgable machine and it will have true memory.
OpenAI's terminology and implementations have been becoming increasingly more nonstandard and black box such that it's making things more confusing than anything else even for people like myself who are proficient in the space. I can't imaging how the nontechnical users they are targeting with the ChatGPT webapp feel.
OpenAI's terminology and implementations have been becoming increasingly more nonstandard and black box such that it's making things more confusing than anything else even for people like myself who are proficient in the space. I can't imaging how the nontechnical users they are targeting with the ChatGPT webapp feel.
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…
Oddly, the spoken version of ChatGPT4 does implore, listens and responds to tones, gives the same energy back and does ask questions. Sometimes it accidentally sounds sarcastic “is this one of your interests?”
I'll have try it out though to know for sure
So, so, so curious how they are implementing this.