I'm confused; how is writing a shell command (using shortcuts like those in the article!) "wasting time", but describing what you want to an LLM, having it make a plan, reading the plan, editing it, and running it is somehow not a waste of time?

You also mention there being "little value", when your proposed approach costs literal money in form of API/token usage (when using hosted models).

> Now I've moved to coding in Haskell

You might like https://hackage.haskell.org/package/turtle or http://nellardo.com/lang/haskell/hash/