Guiding an AI through problem solving yields far better results, according to The Register:

First, a programming question is fed to the underlying large language model, and it’s asked to describe and summarize the problem. That information then guides how it should begin to solve the problem…The model then begins to generate code that aligns with the specifications it just described…If it doesn’t manage to match any of the outputs defined in any of the tests, the model generates different solutions until they pass all the tests or it fails.

This has the feel of a generalisable approach to a wide range of problem solving.

Read about it here.