No, I wasn't trolling. I think we have a different concept of what an intuitive leap is. A neural net, as far as my understanding goes, needs training in the field that it makes decisions in. I think you believe that process itself contains intuitive leaps. Neural nets trained to walk develop weird walking styles, and I think that you think that is evidence of an intuitive leap. If that's what you mean, I would disagree.

You train it to walk, and it won't understand how to climb. You train it to climb on a climbing wall and it won't understand that it can't climb on glass, or string, or a waterfall without additional training.

Whereas you and I wouldn't need to try and fail to climb a waterfall. We would just know it isn't going to work. We would also understand, without having tested it, that those climbing skills would enable us to climb a tree, or a rope net, or ladder.

We might even be able to make a judgement about how well we could climb each before disaster.

If I were wrong on this, and I could see an AI trained to do X and then apply it to Y then it would cause me to review my beliefs on AI.

In fact, one might argue that's all they do -- depending on how one defines "intuition".

In a vary narrow sense, sure. But humans are great at generalizing across different domains, and finding new connections and patterns.