The problem with theorizing about artificial intelligence is that we’re assuming things about the nature of cognition and intelligence that I'm not sure we know yet. So far we have not created an artificial intelligence of any kind–super or even 'stupid'. Watson, Deep Blue and other supercomputer programs simply boil down to being able to do extremely intensive searches through sets of data that we already know. The rules of Chess are very straight forward, and Googling most questions gets you close to the answer. This is a part/form of intelligence, but this may be completely different from how the actual intelligent cognitive creativity that lets us come up with ideas works.
Until we understand how our minds come up with completely new ideas, it may be impossible to purposefully design a computer that is *actually* intelligent as measured by an ability to come up with completely new ideas that show an actual understanding of the real problems that ineptly succinct directives like “prevent human suffering” are intended to convey.
We will know we have a real artificial super-intelligence when we ask it, “What can be done to end human suffering?” and it replies with, “I could give you an answer, but you’re asking the wrong question. What you really want to know how to do is…”
No comments:
Post a Comment