The first time I felt confused about morality was as a child. I was about six, and saw a D&D-style role-playing magazine; On the cover, there were two groups preparing to fight, one dressed as barbarians, the other as soldiers or something1. I asked my brother “Which are the goodies and which are the baddies?”, and I couldn’t understand him when he told me neither of them were.
When I was 14 or so, in the middle of a Catholic secondary school, I discovered neopaganism; instead of the Bible and the Ten Commandments, I started following the Wiccan Rede (if it doesn’t hurt anyone, do what you like). Initially I still suffered from the hubris of black-and-white thinking, even though I’d witnessed others falling into that trap and thought poorly of them for it, but eventually my exposure to alternative religious and spiritual ideas made me recognise that morality is shades of grey.
Because of the nature of the UK education system, between school and university I spent 2 years doing A-levels, and one of the subjects I studied was philosophy. Between repeated failures to prove god exists, we covered ethics, specifically emotivism, AKA the hurrah/boo theory, which claims there are no objective morals, and that claims about them are merely emotional attitudes — the standard response at this point is to claim that “murder is wrong” is objective, at which point someone demonstrates plenty of people disagree with you about what counts as murder (abortion, execution, deaths in war, death by dangerous driving, meat, that sort of thing). I don’t think I understood it at that age, any more than I understood my brother saying “neither” when I was six; it’s hard to be sure after so much time.
Then I encountered complicated people. People who could be incredibly moral in one axis, and monsters in another. I can’t remember the exact example that showed it first, but I have plenty to choose from now — on a national scale, the British empire did a great deal to end slavery, yet acted in appalling ways to many of the people under it’s rule; on an individual scale, you can find scandals for Gandhi and Churchill, not just obvious modern examples of formerly-liked celebrities like Kevin Spacey and Rolf Harris. In all cases, saying someone is “evil” or “not evil”, or even “0.5 on the 0-1 evil axis” is misleading — you can trust Churchill 100% to run 1940 UK while simultaneously refusing to trust him (0% trust) to care about anyone who wasn’t a white Protestant, though obviously your percentages might be different.
I’ve been interested in artificial intelligence and artificial neural networks for longer than I’ve been able to follow the maths. When you, as a natural neural network, try to measure something, you do so with a high-dimensional vector-space of inputs (well, many such spaces, each layered on top of each other, with the outputs of one layer being the inputs of the next layer) and that includes morality.
When you ask how moral someone else is, how moral some behaviour is, what you’re doing is essentially a dot-product of your moral code with their moral code. You may or may not filter that down into a single “good/bad” boolean afterwards — that’s easy for a neural network, and makes no difference.
1 I can’t remember exactly, but it doesn’t matter.