I have my identity, which I call "Brian", my brain stored in a series of markdown files currently occupying around 50KB. I can transfer those to an AI model, public or private as a pre-prompt to align the model I'm using with me.
The brain substrate (LLM) doesn't matter too much, you can switch substrates on the fly using API's, OpenRouter or your own LLM(s).
I am tending to agree with Yann LeCun that LLM's cannot evolve beyond human thought as they are simply the compressed sum of all human thought. Future AIs will evolve way beyond us, but LLMs are a dead end.
If you're interested in my project, I posted some notes on NOSTR, but I'm also posting my research on my own website mikehardcastle.com
nostr:naddr1qvzqqqr4gupzp6pmv65w6tfhcp73404xuxcqpg24f8rf2z86f3v824td22c9ymptqy2hwumn8ghj7un9d3shjtnyv9kh2uewd9hj7qgkwaehxw309a5xjum59ehx7um5wghxcctwvshsqxnzw45kcerfdenj6cnjd9skuttd0ykkz6fdvfexz6twfdzt0a
