The Tokyo Test
and the problem with human criteria.
At Japan’s National Institute of Informatics (NII), in Tokyo, a research team is trying to create an artificial intelligence program that has enough smarts to pass Japan’s most rigorous entrance exams. The AI will start by taking the standardized test administered to all secondary school students; once it masters that test, it will move on to the more difficult University of Tokyo exam.
By 2016, the team hopes its AI will achieve a high score on the national standardized test, which includes multiple-choice questions in subjects such as physics and world history and requires students to solve math problems. But the machine-learning and natural-language-processing tools Arai’s team is developing for that test won’t prepare it for the Todai exam, which includes written essays.
There really isn’t a feasable intelligence contest out there, is there?
Although this isn’t such a bad idea. One could enter any human intelligence test with an AI and ‘prove’ its intelligence without need for a contest.