News for hackers. Stuff that matters.
Re:I trained ChatGPT on my childhood journal entries to talk... by Mizza on Wednesday December 21, 2022 @07:19AM (#34079697)
After playing with the APIs, it seems there's something annoying happening with the terminology right now. "ChatGPT" and "davinci-003" aren't equivalent, but it isn't entirely clear how.

The biggest difference is that ChatGPT can remember earlier parts of our "conversation", davinci can't. I suspect that this is just the result of the interface, that it is being presented with our conversation history has an input. However, I haven't found anywhere that actually makes it clear how this aspect works. Can anybody shed some light?

Re:I trained ChatGPT on my childhood journal entries to talk... by kgwgk on Wednesday December 21, 2022 @07:22AM (#34079730)
Re:I trained ChatGPT on my childhood journal entries to talk... by danuker on Wednesday December 21, 2022 @07:28AM (#34079795)
If you copy the past queries in davinci's current input, such as prefixing lines with Q: A: or -, it could understand when it was its turn, and when it was yours.
Re:I trained ChatGPT on my childhood journal entries to talk... by Baloo on Wednesday December 21, 2022 @08:15AM (#34080290)
To make it with davinci-003 you can store all the conversation history and prefix it to your prompt as you mentioned. It does mean that you're limited to a history of about 3.5k words, which you could summarize into a smaller chunk to help make the conversations longer. I have a basic demo of a chatbot that remembers here:

github.com/dylnbk/chatty

Re:I trained ChatGPT on my childhood journal entries to talk... by zn44 on Wednesday December 21, 2022 @08:52AM (#34080718)
I'd recommend following author of this thread for technical analysis of chatgpt and other models https://twitter.com/goodside/status/1598874674204618753?t=5W...