ChatGPT is pretty damn good at anything creative, but for hard-truth questions it's eh at best. Which is quite ironic when you think about what we imagined Robots would end up like.

Btw, I just asked ChatGPT to give me a list of five-letter words that a child could draw. At one point it conceded that it's suggested words were indeed not five letters long, but it couldnt correct it's error. To tie back into the point I made above: All of the suggested words were actually good choices (creative), they just werent five letters long (truth)