Jan, Likewise I have questions. No doubt though, fooling the panel is a great achievement but pretending to be a non native english speaker seems like a work around. After all, did Turing imply the judges and subject had to both be native speakers of whatever language was being used?
As you say, there did not seem to be a control but the difficulty here is how knowledgeable the control would be. Still, a major achievement. Bobj Dr Bob Jansen Turtle Lane Studios PO Box 26 Erskineville NSW 2043 Australia Ph (Australia): +61 414 297 448 Ph (Korea): +82 10 4494 0328 Skype: bobjtls http://www.turtlelane.com.au > On 9 Jun 2014, at 9:04, Jan Whitaker <[email protected]> wrote: > > OK, this seems possible, but I'd like to see how an unknown set of > questions from a panel would determine that this was or wasn't a real > 13 y.o. boy. Anyone have more detail on how this test was actually > conducted? According to the article, they test 3 machines. That means > there wasn't a control -- e.g. a REAL 13 yo boy. > > > http://www.theguardian.com/technology/2014/jun/08/super-computer-simulates-13-year-old-boy-passes-turing-test > > > > > Melbourne, Victoria, Australia > [email protected] > > Sooner or later, I hate to break it to you, you're gonna die, so how > do you fill in the space between here and there? It's yours. Seize your space. > ~Margaret Atwood, writer > > _ __________________ _ > _______________________________________________ > Link mailing list > [email protected] > http://mailman.anu.edu.au/mailman/listinfo/link _______________________________________________ Link mailing list [email protected] http://mailman.anu.edu.au/mailman/listinfo/link
