X-Message-Number: 30215 From: Date: Wed, 26 Dec 2007 13:38:36 EST Subject: implications of "self development" Apologies to those who think all this is a waste of time, as it probably is. Anyway, Flavonoid wrote: >The simple fact is that no "malign conspiracy" is required for a >development team to engender a non-friendly super-AI. All they need do >is proceed on with their usual R&D, right to the point where their >software becomes self-developing. At that point, the computer is in >control, has more power than its developers, and will show the human race >just how "friendly" it is. He persists in assuming or implying a whole lot of unwarranted conclusions. First of all, many programs already are "self-developing" yet innocuous. What is crucial is precisely in what manner the self development occurs, and what unchangeable underlying rules, if any, there may be, and other aspects of the permitted relations between the computer and its environment. The mere fact of being self modifying does not automatically put a computer "in control" of anything except its permitted and required development. Flavonoid simply assumes, on no basis that I can see, that almost any kind of high level computer will at some point "go autonomous" or "wake up" and develop its own agenda, which will include an insatiable lust for power. In effect he is assuming in advance the very thing he is trying to prove. R.E. **************************************See AOL's top rated recipes (http://food.aol.com/top-rated-recipes?NCID=aoltop00030000000004) Content-Type: text/html; charset="US-ASCII" [ AUTOMATICALLY SKIPPING HTML ENCODING! ] Rate This Message: http://www.cryonet.org/cgi-bin/rate.cgi?msg=30215