[nick_m]

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.

[knaik94]

She added a small write up, it was Davinci 2 as 3 wasn't out. https://twitter.com/michellehuang42/status/15977029748891443...

[ralfd]

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.

[visarga]

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.