[Edit: for reasons I still don’t understand, people dislike this post. Here is a version of the post that people like, you may want to read that one instead.]
There’s an idea described here that says: (some of) the neocortex is a mostly-aligned tool-like AI with respect to the brain of some prior ancestor species. (Note that this is different from the claim that brains are AIs partially aligned with evolution.) So, maybe we can learn some lessons about alignment by looking at how older brain structures command and train newer brain structures.
Here’s another analogy: female hominids make huge investments in their offspring, which are extremely neotenous. To provide the childcare that enables prolonged neoteny, females have to gain the loyalty of males. To gain loyalty of males, females have to suss out in detail whether a given male is reliable / trustworthy / allied, as well as capable, before mating with them. (Hence females tending on average to be relatively more interested in people over things, compared to males.)
So by some combination of hardwired skill and learned skill, females with some success determine the fundamental intentions of males. This determination has to be high precision. I.e., there can’t be too many false positives, because a false positives means trying to raise children without devoted support, though maybe with support of other tribe members. (I’m ignoring the complexity of tribal living, so this is all a somewhat cartoon picture.) This determination also has to be pretty robust to the passage of time and surprising circumstances.
This is disanalogous to AGI alignment in that AGIs would be smarter than humans and very different from humans, whereas males are pretty much the same as females. But there is some analogy, in that males are general intelligences, albeit very bounded ones, being kind of aligned with other general intelligences. So, women, what can you say about ferreting out the fundamental intentions of men?
The male AI alignment solution
[Edit: for reasons I still don’t understand, people dislike this post. Here is a version of the post that people like, you may want to read that one instead.]
There’s an idea described here that says: (some of) the neocortex is a mostly-aligned tool-like AI with respect to the brain of some prior ancestor species. (Note that this is different from the claim that brains are AIs partially aligned with evolution.) So, maybe we can learn some lessons about alignment by looking at how older brain structures command and train newer brain structures.
Here’s another analogy: female hominids make huge investments in their offspring, which are extremely neotenous. To provide the childcare that enables prolonged neoteny, females have to gain the loyalty of males. To gain loyalty of males, females have to suss out in detail whether a given male is reliable / trustworthy / allied, as well as capable, before mating with them. (Hence females tending on average to be relatively more interested in people over things, compared to males.)
So by some combination of hardwired skill and learned skill, females with some success determine the fundamental intentions of males. This determination has to be high precision. I.e., there can’t be too many false positives, because a false positives means trying to raise children without devoted support, though maybe with support of other tribe members. (I’m ignoring the complexity of tribal living, so this is all a somewhat cartoon picture.) This determination also has to be pretty robust to the passage of time and surprising circumstances.
This is disanalogous to AGI alignment in that AGIs would be smarter than humans and very different from humans, whereas males are pretty much the same as females. But there is some analogy, in that males are general intelligences, albeit very bounded ones, being kind of aligned with other general intelligences. So, women, what can you say about ferreting out the fundamental intentions of men?