Code for fine-tuning davinci (GPT-3): https://github.com/rchikhi/GPT-is-you

Great write-up! Here's a similar experiment but instead fine-tuned on WhatsApp 1-on-1 chats, technically simpler with OpenAI APIs: https://github.com/rchikhi/GPT-is-you/blob/main/README.md

maybe paranoidly, but i just didn't trust openai with my highly personal message data. it would certainly have been easier + probably cheaper to do it this way, but it just gave me the willies.