Path: utzoo!attcan!utgpu!jarvis.csri.toronto.edu!mailrus!csd4.milw.wisc.edu!cs.utexas.edu!tut.cis.ohio-state.edu!att!dptg!rutgers!aramis.rutgers.edu!athos.rutgers.edu!nanotech From: ems%nanotech@princeton.edu Newsgroups: sci.nanotech Subject: Re: viruses, computer & bio (plus a fix) Message-ID: Date: 31 Jul 89 22:17:32 GMT Sender: nanotech@athos.rutgers.edu Lines: 88 Approved: nanotech@aramis.rutgers.edu >I admit that designing an artificial conscience is much tougher than >the capitalist nanovirus described earlier. I would attempt it this >way: First, map the neuron structure of a human brain using nanotech. >Next, use the virtually unlimited amounts of CPU available thru >nanotech to simulate the interaction of a computer model of this >brain with a (simplified) model of an "outside world". (You can run >this simulation very fast, and also run many copies in parallel). >Finally, "all" you do is treat this brain model as a black box, >and determine the set of outputs you want to avoid. Deciding when >the "outside world" has been harmed (by the brain model outputs) >could possibly be determined by examining increases in the >disorder of the "outside world" part of the simulation. > >Sounds simple? It's not, but it does outline at least one >approach to the job, that is more tractable than creating >complete theories of psychology & AI. (I started with CPUs having >a whole 8K. After a while, I learned to never make my machines >do anything that they don't have to. :-) [ Some signatures elided...] >[The simulation method for implementing the "conscience" seems unlikely > to work, primarily because (remember) the thing we're trying to protect > against is mischief done by complex nanosystems. I find it difficult > to believe that an nth-generation system could simulate (a) the designer's > thoughts, (b) the nth-generation CAD system, (c) the n+1st generation > system being built, and (d) enough of the real world, almost necessarily > at the molecular level, to detect craftily laid schemes. > Though offhand, I can't think of a better one... > --JoSH] (Brace yourself! More facile hand-waving "explanations" ahead ...:-) I think by focusing the "conscience" on a person's *intent* to commit technicide (killing/immoral acts via technology?) we could come up with something to do the job. Remember Burgess's "A Clockwork Orange"? Alex, the protagonist, was conditioned to become sick whenever he *thought* about violence. (In actuality his emotional state was monitored. This prevented Alex from outsmarting the conditioning just by dreaming up a new form of violence.) The techniques used were crude but effective. (Of course the rest of the society he was in was *not* conditioned, but that's another story.) Using our nanosimulations, we could do this in a vastly improved form, winding up with exactly the behavior controls that we want. By controlling those negative impulses from the onset of nanotechnology we could ensure that those killer nanoviri never get built. (This type of conditioning might not work on someone who was insane from the start, but I think that serious insanity would probably be apparent anyway). By the way, I'm not advocating making people sick whenever they think the dangerous thoughts. Something gentler could be just as effective. Perhaps the subjects would be conditioned to undergo a pseudo "religious" experience, controlled hallucinations along with emotional overtones, that would effectively steer them off of the wrong track. The simulations would help the leading force design the best techniques. However much I've sugar-coated it, I'm still talking about some form of "mind control". I've outlined a reasonable approach to the technical question of "how". A more important question is whether the leading force should undertake this task at all. If for instance, the leading force is not completely honest, and leaves back doors for themselves in the conditioning, the world might be worse off than before. Ed Strong email: att!mtuxo!ems1 or {princeton,mccc,attmail}!nanotech!ems [Remember that in Clockwork Orange, "violence" is defined to the victim by example, ie showing him violent films. However, when any more complex chain of reasoning is involved, people exhibit an amazing capacity to deceive themselves about the reasons and consequences of their actions. I think you are going to wind up needing something so complex, that you may as well discard the people and let your machine do whatever it is you were going to control them into doing. Like Eric wrote, a nanotech totalitarian state would probably discard us rather than enslaving us. I feel that if people are to remain anything like recognizably human, the answer lies more along the path of increasing their ability to withstand accidents, than of decreasing their ability to have them. --JoSH]