As artificial intelligence continues to develop, a professor from the Georgia Institute of Technology has proposed a new way to see if the technology can match up to the capabilities of the human brain.
The test, called Lovelace 2.0, would focus on challenging a robot's creativity, asking it to create a painting, architectural design, poem, or story, according to BBC News. Prof. Mark Riedl developed this test as a new version of the Lovelace Test, which had an A.I. create something that it wouldn't be able to explain how it did so.
"For the test, the artificial agent passes if it develops a creative artefact from a subset of artistic genres deemed to require human-level intelligence and the artefact meets certain creative constraints given by a human evaluator," Riedl said, adding that while A.I.s have already been shown to be able to create poems and paintings. "No existing story generation system can pass the Lovelace 2.0 test."
The Turing test is used today to see what A.I.s are capable of, challenging it to convince a judge in series of five-minute keyboard conversations that it is a human. The robot passes the test if the judge mistakes it for a human 30 percent of the time.
Riedl's new test has received some criticism, such as from David Wood, chairman of the London Futurists, who says most people believe humans are different from AIs because they possess creativity while robots do not, BBC News reported.
"This is a comforting view, but I think it's wrong," Wood added. "There are already robots that manifest rudimentary emotional intelligence and computers can already write inspiring music."
However, Lovelace 2.0 has also received praise, with Prof. Alan Woodward from the University of Surrey saying it can be helpful in understanding what humans are capable of as well.
"I think this new test shows that we all now recognize that humans are more than just very advanced machines, and that creativity is one of those features that separates us from computers – for now," Woodward added.
