News for hackers. Stuff that matters.
Re:Artist feeds childhood diary into GPT-3 to have a moving ... by nick_m on Tuesday November 29, 2022 @08:17PM (#33795687)
I'm curious about trying something like this myself - does anyone know which GPT-3 model she used? On their site, it looks like I have a choice of Ada, Babbage, Curie or Davinci. I'm new to GPT-3 - assuming that she started with a "base" model and then, trained it using her journals.
Re:Artist feeds childhood diary into GPT-3 to have a moving ... by visarga on Tuesday November 29, 2022 @08:32PM (#33795802)
I am also interested in this. For example how should we best formulate the input? Just our own messages, or including the parent message, or the whole chain to the top and the linked article. I think in the future we will have easier ways to train a persona.
Re:Artist feeds childhood diary into GPT-3 to have a moving ... by knaik94 on Tuesday November 29, 2022 @08:20PM (#33795709)
She added a small write up, it was Davinci 2 as 3 wasn't out. https://twitter.com/michellehuang42/status/15977029748891443...
Re:Artist feeds childhood diary into GPT-3 to have a moving ... by ralfd on Wednesday November 30, 2022 @09:00AM (#33800841)
Thanks for the link. That sounds more like prompt engineering? If I understand that correctly it is providing short journal entries (1K words) and GPT3 is imitating the vibe of that (or whatever it does). But it is not “training” a Modell on all the journal text.