Its the closest terminology we have to describe that process.

https://github.com/cobusgreyling/loop-engineering

Its hard to come up with new names for novel processes, you mostly reuse what is close enough and well known.

Loop engineering, whatever that is, is obviously just a way to get people to increase the amount of tokens required per task/request. They did the same thing with Ralph loops, they just need more revenue. Just write your code and use it to search and clarify, it can't build that magical thing you think it can.

	▲	kamaal 3 hours ago \| parent [-]
		The heuristic is this- Given a problem P- 1. Provide a list(S) of solutions(S1, S2 ... SN) ordered in the most efficient(For some definition of efficiency) implementation means possible. 2. Execute S1, ... SN. 3. If P is fixed by a solution in the list, halt. 4. Else for each S1 ... SN , execute steps 1 through 4 until, all dependencies and sub problems are resolved to eventually solve P. This obviously needs lots of tokens, which is all the more reason why we need AI to run locally on our machines.