AI SAFETY & ETHICS

Infinite ethics and UDASSA

LessWrong AI

Reading the first post of the sequence ( Probabilities are not the right concept ) is recommended but not required for understanding this post. Infinite ethics Once you start looking at infinities, all ethical systems get confusing. Intuitively, it's good to plant an apple tree. But if the universe already has infinitely many apple trees, why bother? Infinity plus one is still infinity. And there are the classic paradoxes: an infinite grid of houses, each with three happy people and one unhappy person, seems better than the reverse.