I realise it's super impressive, it really is. But don't over state what GPT-4 actually is. How on earth would you think an LLM could "copy itself" to anything? What even is "itself" in this context? The weights? Source code or binaries for inference? How about the training parts? You're filling in your gaps of understanding with exciting sci-fi concepts that you half remember, and while that's fun in a 4am dorm-room discussion kind of way it's not useful for thinking about reality.