The hermeneutic spiral is the process of understanding a text (or more generally, anything big and confusing) by passing over it again and again, each time using what you've learned to more deeply understand the workings and roles of each part and grow a truer image of the whole. The hermeneutic spiral is not depth-first search; it's more like bread-first search, but it can also involve depth, and altering the ordering you use to search, and expanding the set you're searching over.
The hermeneutic spiral involves noticing landmarks, principles, cruxes, and generators.
It involves logogenesis.
It's an aspect of how Alexander Grothendieck did math.
It's the Unix philosophy of programming.
It's a way to make a pattern language (of rationality).
Compare the expectation–maximization algorithm.
GPT-2 uses the transformer architecture, which is a sort of toy version of a hermeneutic spiral.
"The sun was sinking in the sky, for Harry had been thinking for some hours now, thinking mostly the same thoughts over and over, but with key differences each time, like his thoughts were not going in circles, but climbing a spiral, or descending it." HPMOR, ch. 63.