How to Build a Machine That Breaks the Rules

There are many schools of thought as to how do you approach to build machine ethics ethical reason. You can either have a machine that gradually learns to follow the some some rules and then it comes up with something or you can take a known ethical theory that is developed to a certain satisfactory level but break it down into simple actions and cases. The work of Moore who says that well you can have ethical implicit ethical agents and explicit ethical agents for example. It's more talking about what is common sense reasoning rather than some high level entity or so right?