A tycoon is seeking a new advisor , and to do so he invites three wise world to his castle . He tell them he will place a lid on each of their heads that will be either bloodless or drab , and at least one of the hats will be blue . The wise human race must work out the color of their own hat they are wearing without talking to each other to become the consultant . After a few minutes of sitting in muteness , one of the impudent man stands up and estimate right .
This brain-teaser ( you’re able to read the solutionhere ) is a famous test of logic and ego - awareness , and a mathematical group of researchers have nowrecreateda interchangeable psychometric test in robots to prove the ability of artificial intelligence to be self - aware – within , of path , restriction .
Three humanoidNao robotswere programmed to think that two of them had been given a “ dumbing oral contraceptive pill ” that prevent them from verbalize . All of them were asked “ which tablet did you receive ? ” but as two of them were mute , only one was capable to answer , saying : “ I do n’t have intercourse . ” It then put to work out that , as it can talk , it must not have been given the pill , so it changes its answer to : “ Sorry , I know now . I was able-bodied to demonstrate that I was not given a dumbing pill . ”
answer of the test , carried out by the Rensselaer Artificial Intelligence and Reasoning ( RAIR ) Laboratory , will be presented in a newspaper atRO - MAN 2015later this class . Selmer Bringsjor from the Rensselaer Polytechnic Institute , one of the test ’s administrators , toldVicethat it showed that a “ logical and a mathematical correlative to ego - consciousness ” was possible , suggesting that robots can be designed in such a way that their activity and determination resemble a grade of self - awareness .
Before you bug out preparing for an attack of Terminator - style killer robot , though , it should be noted that this test was obviously rather circumscribed . Nonetheless , it suggests that self - awareness is something that can be programmed , and may spread out up new avenues for artificial intelligence . Just being able-bodied to understand the query and hear their own voice to reset the puzzle is an important science for robot to demonstrate .
“ There are myriad additional steps that need to ultimately be taken , ” the researchers compose in theirpaper , “ but one step at a time is the only way forrard . ”
