I think this is more of a function of the harness and the environment than the LLM. I've seen some LLM interactions over complex environments like Godot and Unity that challenges the notion that there is no "jumping" going on at all.
An LLM in isolation from its environment might as well be a brain in a vat in some dark cave. You need an external environment to sample from and act upon to make forward progress.
Why does the cave need to be dark if its just a brain in a vat?
I'm also amazed at the degree an LLM can get the drift with a vague or incomplete prompt. The ability to perceive and operate based on patterns that go beyond the language in the text makes it seem like they would be unusually good at taking leaps that haven't occurred to us.