> It’s often been assumed that accuracy and ‘correctness’ would be easy to implement on computers because they operate on logic, in some sense. It’s originality and creativity that would be hard

More fundamental than the training data is the fact that the generative outputs are statistical, not logical. This is why they can produce a sequence of logical steps but still come to incorrect or contradictory conclusions. This is also why they tackle creativity more easily since the acceptable boundaries of creative output is less rigid. A photorealistic video of someone sawing a cloud in half can still be entertaining art despite the logical inconsistencies in the idea.