GPT-4 was able to do this even though the training data for the version tested by the authors was entirely text-based. That is, there were no images in its training set. But GPT-4 apparently learned to reason about the shape of a unicorn’s body after training on a huge amount of written text.
It’s as if they can in some way or other “see”.
That’s absolutely incredible, I don’t think the general public understands the effect AI will have on our society in the next 15 years