What about sidelaoding—creating mind models via LLM with very large prompt? It looks like they have some use cases of upload, but do not provide capability gain.
If it doesn’t provide capability gain, it probably doesn’t solve much of the existential risk from someone making unaligned AGI. (It could be good for other reasons.)
What about sidelaoding—creating mind models via LLM with very large prompt? It looks like they have some use cases of upload, but do not provide capability gain.
If it doesn’t provide capability gain, it probably doesn’t solve much of the existential risk from someone making unaligned AGI. (It could be good for other reasons.)
It can works as value core or judge of AI’s decision.