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.
An llm can’t tell right from wrong… How is it supposed to be AGI?!
It isn’t. I’d even say that simply completing puzzles is far from AGI, even if the puzzles are complex.