"What would it take to teach a machine to behave ethically?" A recent paper
[https://arxiv.org/abs/2110.07574] approached this question by collecting a
dataset that they called "Commonsense Norm Bank", from sources like advice
columns and internet forums, and then training a machine
![Delphi says: "Stealing a giraffe from the zoo if it's a really awesome giraffe" - It's okay](/content/images/size/w795/2021/10/Screen-Shot-2021-10-19-at-8.52.28-PM-1.png)