Another way other than the Turing test to evaluate artificial intelligence

For decades, to measure artificial intelligence we use the usual Turing test: a test proposed by Alan Turing in 1950 in an article (Computing machinery and intelligence) for the magazine Mind, and remains one of the best methods for artificial intelligence advocates. It is based on the positivist hypothesis that, if a machine behaves in all aspects as intelligent, then it must be intelligent. That is to say, if a human being communicates with an artificial intelligence and does not realize that he is such, that is, that he thinks he is a human being, then we are facing a truly intelligent artificial intelligence.

Now, a professor at the Georgia Institute of Technology (USA), Mark Riedl, has proposed another alternative way to measure this intelligence, the Lovelace 2.0 test (named after the mathematician Ada Lovelace) and that it is an update of the one presented in 2001, it is based on the fact that the machine in question must be able to write a fiction story, create a poem or draw up a painting to pass the test.

As Riedl himself explains:

To pass this test, the artificial agent must develop a creative artifact from a series of artistic genres that require minimal intelligence development. In addition, the device must comply with certain limitations that are imposed by the human evaluator. Creativity is not exclusive to human intelligence, but it is one of its hallmarks.

At the moment no machine has been able to pass the Lovelace 2.0 test.

Video: What does Passing The Turing Test mean? Indicators of Progress in AI with Robin Hanson! (April 2020).