>>40575699
LLM's suck at factual anything.
BUT they excel at exploring metaphors and associations, for example themes between narratives.

The key is to know you are not exploring "truth" but "possible patterns" which may or may not having anything to do with anything "factual" or "universal," *or may in some limited respects but not others.* Any analogy or comparison is by nature imperfect because different things are different. Also many things we don't even realize are analogies are analogies; analogies are not a special case but the core of cognition.

Here is a prompt that can help you explore this by programming personas: