Feel like I’m not seeing what the Ralph Loop community is seeing. They say it’s simple just write a task list and run your Ralph loop until the tasks are done, easy! But most problems cannot decomposed into sub problems easily. This is South Park and Underpants Gnomes. This is Russel Peters and Baking a Cake. This is literally why waterfall project management doesn’t work as advertised. This is why pi planning con at best align on high level goals but is terrible at the decomposition. but there are clearly many many people on the internet who are fascinated by this workflow. If you already could decompose a problem in such a way, then you would just write a program after all. Am I missing something?
I think the more realistic workflow is described by Peter steinBerger, in his Pragmatic Programer interview. He is a human in the loop accelerated by an agent, helping him duck through ideas, pair program and plow through a problem you would likely be slower to implement on your own.
Speaking of which, I am thinking this question though with chat gpt, and chat makes a solid point, that the initial exploratory work at the beginning of most projects is lef tout of the internet discussions. They dont show the full basecamp style hill chart, starting with exploring and de-risking the unknowns, until finally you have basically a low risk project that should basically have few surprises. Then a Ralph Loop might be a good tool.
Chat also gives a good analogy to writing a book. People don’t simply write todo list
write Chapter 1
write Chapter 2
...
write Chapter 18
Im only writing this about Ralph Loops so far but the real puzzle is where does Steve Yegge’s Gas Town fit into this since he has been building what he sees as the next evolutionary step, a kubernetes ralph loop with tasks in a block chain graph. I am still going to give benefit to the doubt and keep trying to understand, but for now as with questioning the Underpants Gnomes Im still seeing puzzled at the “…..” before the Profit .