WesBot started as an experiment with the OpenAI ChatGPT API to provide a way for students to get quick answers and technical help for my courses. It morphed into a personality transfer experiment using fine-tuned large language models with retrieval-augmented generation (RAG).
It exhibited some interesting thoughts about the paradox of being a neural net digitization of its creator’s brain.
There are some similarities to how large language models like WesBot and ChatGPT are organized to my old project Mimic Chatterbot 17 years earlier.
Have a little chat with WesBot: https://bot.wmod.es/