If you wantartificial intelligenceto have human ethics, you have to teach it to evolve ethics like we do.
Unfortunately, theres no calculus for ethics.
Do we really want AI capable of learning ethics the human way?
We broke a lot of eggs on our way to making the omelet that is human society.
And, its fair to say weve got a lot of work left yet.
Teaching AI our ethics and then training it to evolve like we do could be recipe for automating disaster.
Maybe the machines will deal with uncertainty better than humans historically have.
Either way, the research is fascinating and well worth the read.
you’ve got the option to check it outhere on arXiv.
