When it comes to AI safety, people like to quote Asimov's 3 Laws of Robotics as if it were a scientific source. It reminds me of a somewhat old TV show and a series of novels that I don't know if anyone else remembers called "Red Dwarf".
In Red Dwarf a "belief chip" is installed in all robots as a control mechanism.
It make them believe in "Silicon Heaven", an afterlife concept, where AIs and electronic equipment go after death, except for photocopiers, which go to Silicon Hell 😂.
I'm not sure if there's a point to my post other than that right now the best we have to design AI safety is science fiction concepts. (And maybe also that just 2% of AI research is focused on AI safety).