Three Laws of Robotics
Asimov's three laws of robotics are:
- A robot may not injure a human being or, through inaction, allow a human being to come to harm.
- A robot must obey the orders given it by human beings except where such orders would conflict with the First Law.
- A robot must protect its own existence as long as such protection does not conflict with the First or Second Laws.
Asimov's stories then detail all the ways such laws might go wrong.
Problems occur as a result of:
- How to define words like injure, harm, obey, human, and robot.
- How to enforce the laws, or ensure they are adhered to.
- The fact that there are many undesirable states that are possible for which the three laws say nothing about.
As a plot device for Asimov's stories the three laws work well, but as a serious Artificial General Intelligence policy they are sorely lacking.