heh... A science blog is now writing about "AI Boxing" ...
> March 01, 2012: Humanity Must 'Jail' Dangerous AI to Avoid Doom, Expert > Says from LiveScience.com via Google News > Keeping the artificial intelligence (AI) genie trapped in the proverbial > bottle could turn an apocalyptic threat into a powerful oracle that solves > humanity's problems, said Roman Yampolskiy, a computer scientist at the > University of Louisville in Kentucky. One starting solution might trap the > AI inside a "virtual machine" running inside a computer's typical operating > system an existing process that adds security by limiting the AI's access to > its host computer's software and hardware. If all else fails, researchers > could always slow down the AI's "thinking" by throttling back computer > processing speeds, regularly hit the "reset" button or shut down the > computer's power supply to keep an AI in check. "The Catch-22 is that until > we have fully developed superintelligent AI we can't fully test our ideas, > but in order to safely develop such AI we need to have working security > measures," Yampolskiy told InnovationNew sDaily. (info) > Of course, many of you will remember that Eliezer Yudkowsky, Justin Corwin and many others wrote a lot about this on some futurist mailing lists a decade ago, e.g. http://www.sl4.org/archive/0508/12112.html http://www.sl4.org/archive/0207/4935.html and Stefan Pernar wrote an interesting SF novel with this idea at the core.. http://www.amazon.com/Jame5-Stefan-Pernar/dp/B00183V3U4 -- Ben ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-c97d2393 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-2484a968 Powered by Listbox: http://www.listbox.com
