Tuesday, August 21, 2007
Toward a General Logicist Methodology for Engineering Ethically Correct Robots
A bit of light reading: Toward a General Logicist Methodology for Engineering Ethically Correct Robots: "It's hard to deny that robots will become increasingly capable and that humans will increasingly exploit these capabilities by deploying them in ethically sensitive environments, such as hospitals, where ethically incorrect robot behavior could have dire consequences for humans. How can we ensure that such robots will always behave in an ethically correct manner? How can we know ahead of time, via rationales expressed clearly in natural language, that their behavior will be constrained specifically by the ethical codes selected by human overseers?"
Subscribe to:
Post Comments (Atom)
This post got me thinking about the possibilities that robots might take over the world. I was reminded of Dr. Steven Hawking, math professor at Cambridge, who said because technology is advancing so quickly, 'computers double their performance every month'. Humans, in contrast, are developing much more slowly, and so must change their DNA make-up or be left behind. 'The danger is real,' he said, 'that this [computer] intelligence will develop and take over the world.' He made these remarks September 1st, 2001 (just 10 days before the infamous 9-11-01; does Hawking know something we don't?).
ReplyDeleteI was just kidding about that last remark, but here are some other articles about this that I found interesting:
Could Robots Take Over the World?
Will Robots Take Over the World? (Interesting case study)
Why Robots Won't Rule the World
(13 pgs w/ references)
just my thoughts, J