I provided GPT4 with 5 answers, and asked it to generate subtle hints that a human might use to guess the answer. It did a reasonable job, but did not adequately account for the difference between ubiquitous concepts, where most hints seemed too easy, and obscure concepts. For instance, in the above list, item 1 is a common everyday concept, 2 and 5 are from popular culture, but with varying penetration into non-nerd circles. Item 3 is a tough one to judge, as the concept is obscure but it is a combination of two common concepts. The first hint is quite poetic, but easier than what I had in mind. Item 4 would be impenetrable for me if I didn’t already know the answer, but it could be a decent starting point for a guessing game.
Still has a lot of room for improvement.
The next step is to get it to allow for how commonplace the concepts are.