This study out of Cornell raises a lot of questions for me.
When the dust settled, researchers found that Google’s AI has an IQ of about 47.28, putting it slightly below the IQ of an average six-year old. Siri, in contrast, din’t fare all that well, with researchers finding that Apple’s AI checked in with an IQ of 23.9.
First, do people still consider IQ a thing worth comparing in people, let alone an artificial intelligence? Second, how can anyone seriously abstract from an A.I. I.Q. to a human I.Q.? This seems thin to me and really more about click-bait articles. Show me an A.I. with the imagination of a six year old.
I think the actual paper is more worthwhile than the many, many, articles linking to it.
As mentioned above, a unified model of intelligent systems should have four major characteristics, namely, the abilities to acquire, master, create, and feedback knowledge. If we hope to evaluate the intelligence and developmental level of an intelligent system, we need to be able to test these four characteristics simultaneously.
The I.Q. test seems insufficient for measuring an A.I. but I suppose these are early days.