Nesov suggested in a comment that we can solve uploading without scanning via predicting important decisions of a possible person:
They might persistently exist outside concrete instantiation in the world, only communicating with it through reasoning about their behavior, which might be a more resource efficient way to implement a person than a mere concrete upload.
Agree. I also suggested 'philosophical landmines'—secret questions posted on the Internet that may halt any advanced AI that tries to solve them. Solving such landmines maybe needed to access the resources which rogue AI may need. Real examples of such landmines should be kept secret, but it may be something like what is the meaning of life or some Pascal mugging calculations.
Recently, I asked a question to Sonnet and the correct answer to it was to output an error message.
When one is working on a sideload (a mind-model of a currently living person created by LLM), one's goal is to create some sort of "Janet". In short, one wants a role-playing game with AI to be emotionally engaging and realistic, especially if one wants to recreate a real person.
I heard (25 years ago) about a friend of a friend who started to see complex images about any word. Even draw them. Turns out it was brain cancer, he died soon after.
Chemical preservation may not be that difficult. I tried to organize this for my cat with a taxidermist, but - plot twist - the cat didn't die.
Why don't you preserve its brain? Also, it may be interesting to try the sideload of a cat (LLM-based mind model based on a list of facts about the person).
It is possible to create a good model of a person with current LLMs who will behave 70-90 percent like me. The model could even claim that it is conscious. I experimented with my model, but it is most likely not conscious (or all LLMs are conscious).
However, the efficiency in the world may be exponentially better for those who spend a lot of time getting marginally better. This is because they are better than others. For example, having ELO 2700 [not the exact number, just an illustration of the idea] in chess will put you near the top of all human players and allow earning money and ELO 2300 is useless.
Try to put it into Deep Research with the following prompt: "Rewrite in style of Gwern and Godel combined".