One of things I do with LLMs is to ask them for problems similar to the one I’m solving. This is something I’ve picked from reading Claude Shannon’s Creative Thinking: reasoning by analogy.

This is how and why it works in its own words:

A very similar device is seeking similar known problems. I think I could illustrate this schematically in this way.

You have a problem P here and there is a solution S which you do not know yet perhaps over here. If you have experience in the field represented, that you are working in, you may perhaps know of a somewhat similar problem, call it P’, which has already been solved and which has a solution, S’, all you need to do – all you may have to do is find the analogy from P’ here to P and the same analogy from S’ to S in order to get back to the solution of the given problem.

— Claude Shannon, Creative Thinking (1952).

In Shannon’s time, the mental matrix of known problems was only as big as your career — the set you had encountered or studied. Today, that’s a small collection compared with what an LLM has seen.

This heuristic is a multiplier. You solve your current problem faster, and you come away knowing about a few others you’d never have run into.