News for hackers. Stuff that matters.
Re:Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generat... by d4rkp4ttern on Tuesday March 28, 2023 @09:30PM (#35350860)
Thank you for clarifying this mystery. My mental model of how ChatGPT works is now clearer. I was somehow thinking that in chat mode it would either (a) need to “update state”, or (b) be fed increasingly longer history. I thought (b) would slow down later responses but I guess with their ginormous compute it’s not perceptible to users.
Re:Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generat... by Datagenerator on Tuesday March 28, 2023 @11:27PM (#35351979)
Someone made a version with a buffer which only has a fixed size context history so it stays in constant speed mode. It will only focus on the latest questions.