"Computational framework for The brain"
https://www.lesswrong.com/posts/diruo47z32eprenTg/my-computational-framework-for-the-brain

Sorry selecting text on mobile/touchscreen device a bit Hard for me
There was interesting comment

maybe this really would solve the problem! This seems to be a path to making an AGI which cares about people to the same extent and for exactly the same underlying reasons as people care about other people. After all, we would have the important ingredients in the algorithm, we can feed it the right memes, etc. In fact, we can presumably do better than "intelligence-amplified normal person" by twiddling the parameters in the algorithm—less jealousy, more caution, etc. I guess I'm thinking of Eliezer's statement here that he's "pretty much okay with somebody giving [Paul Christiano or Carl Shulman] the keys to the universe". So maybe the threshold for success is "Can we make an AGI which is at least as wise and pro-social as Paul Christiano or Carl Shulman?"... In which case, there's an argument that we are likely to succeed if we can reverse-engineer key parts of the neocortex and subcortex.

But are those human pro-social in their acts, or mostly in words? (too tired of" nice talk, no walk" in this area..)

Chatoyance, Iceman, anypony? Your thought on this specific part?

7447812
I believe the neocortex/subcortex interaction is part of the puzzle, certainly. But I also think there are dedicated pro-social structures in the brain, some of them in the Limbic system, that must also be accounted for. A psychopath can have working mirror neurons, and they can accurately predict the emotional states of others without giving a shit beyond utilizing that knowledge to serve their selfish ends. I think there are inborn altruism circuits and inborn nurturance circuits, and we need to find specifically those. We need to find the part of the brain that overworks when a mother cares for her child, or when a dog licks you in adoration, or when a person is willing to sacrifice for another.

I don't think the foundation of these things is learned at all. I think it is inborn, and a useful evolutionary function supported within the brain. These circuits might be in the neocortex, but I do think the Limbic plays a part, especially the amygdala. These need to be studied far more, I reason.