ABSTRACT
To keep robots from doing us harm, they may have to be bound by internal safeguards akin to Asimov's inviolable first law of robotics (do no harm to humans). The discussion of robot consciousness became genuinely pressing with the advent of so-called artificial brains (electronic computers) mid-way through the 20th century. Minds might be a kind of halo around certain machines in the way dark matter is an invisible halo around visible galaxies. Where extreme ignorance persists, anything seems possible. But even in this case the robotic successors will have a real shot at understanding and confirming the truth. For though authors’ own biologically evolved mental models have been shackled through inheritance and learned interactions with organism-level reality, the mathematical constructs authors have devised, and which figure into the implementation of computer models, are significantly freer.
