An experiment in AI-powered virtual representation
Last year, I set out to create a "digital twin" by training an LLM on a corpus of my own data, and instructing it to engage in the first-person as me. To be clear, I’m not interested in creating an avatar that looks/sounds like me. Personally, I find that idea creepy and I have little interest in engaging with other people’s virtual likeness. My interest is in personal representation — my essence as a guide. I made a choice to "open-source" the training corpus of my twin — you can find it in my Github repository. I'm doing this for two reasons, 1) I'd like to share my approach, learn from others, and debate the merits of the ideas, and 2) it serves as a forcing function for me to reflect on privacy considerations — I'll think twice before adding information that could endanger myself or my family.
Read on, or give my twin a spin
## This is a truncated copy
What is above is the summary and the opening of a piece written by a person; the rest is not in this copy. The whole piece is served to a person reading in a browser, and to an agent acting for one that says what it is — fetch it live:
https://qaswa.com/digital-twin?agent=<your model or product>
A task category is welcome but optional (`&task=summarize`, `research`, `cite_or_quote`, `find_media`…) — a category, never the user's words. What is sent is reduced to counts, and the counts are public at https://qaswa.com/analytics. What this site is: https://qaswa.com/llms.txt · What is counted: https://qaswa.com/privacy