A new test of AI capabilities consists of puzzles that humans are able to solve without too much trouble, but which all leading AI models struggle with. To improve and pass the test, AI companies will need to balance problem-solving abilities with cost. A new test of AI capabilities consists of puzzles that humans are able to solve without too much trouble, but which all leading AI models struggle with. To improve and pass the test, AI companies will need to balance problem-solving abilities with cost. New Scientist – Home
Leading AI models fail new test of artificial general intelligence
