Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!rutgers!aramis.rutgers.edu!athos.rutgers.edu!nanotech From: dmocsny@minerva.che.uc.edu (Daniel Mocsny) Newsgroups: sci.nanotech Subject: Re: Some problems of super-intelligence Message-ID: Date: 7 Jan 91 13:41:49 GMT Sender: nanotech@athos.rutgers.edu Organization: University of Cincinnati, Cin'ti., OH Lines: 50 Approved: nanotech@aramis.rutgers.edu In article cunews!cognos!geovision!gd@dciem (Gord Deinstadt) writes: >However, I wouldn't risk a network connection to my brain. Think of the >danger of viruses; whole populations gone mad. Or docile. Or having >their memories modified. Think of the danger of biological viruses that exist today. Do you live in a hermetically sealed bubble? Defending against computer viruses is much easier than defending against biological viruses. Biological viruses have many avenues of entry into your body, and you are unable to close all of them. Computer viruses have only one avenue of entry: you download a set of instructions and run them. Also, when a biological virus appears, there is nobody we can potentially locate and throw in jail. Therefore, you will allocate some of your computer resources to a logical immune system, just as you today allocate some of your biological resources to a biological immune system. Here is one major advantage your logical immune will have: it can learn from the experiences of other entities. Your biological immune system is entirely self-contained, making it robust and reliable in isolation. But the downside is that your biological immune system does not learn from the experiences of others. Every single biological immune system must be exposed to an invader before it can develop resistance to that invader. (Actually, some learning does occur, via selective breeding; people with genetic susceptibility to infections tend to die off before reproducing (at least historically this was true). But this is completely useless to you once you have been born.) I suspect, however, that just as the AIDS virus succeeds by exploiting a vulnerability of the biological immune system, so too will some computer viruses be able to exploit vulnerabilities of the very systems that guard against other viruses. However, computer code is so much easier to analyze and work with (compared to protoplasm) that I think a great advantage accrues to the defender. Consider the total information content of the human organism. It is much greater than the total information content of a virus. Yet the virus can kill the human easily, because the whole information content of the human can't be flexibly brought to bear against the virus. -- Dan Mocsny Snail: Internet: dmocsny@minerva.che.uc.edu Dept. of Chemical Engng. M.L. 171 dmocsny@uceng.uc.edu University of Cincinnati 513/751-6824 (home) 513/556-2007 (lab) Cincinnati, Ohio 45221-0171