This reminds me of the classic results showing Turing completeness of things like sendmail.cf and CSS+HTML. The trick of using directory nesting depth as a counter is clever — it essentially turns the filesystem into a tape. I wonder if there is a practical upper bound from filesystem limits (e.g. PATH_MAX) that would make this more like a bounded automaton in practice.

They explicitly state that using `-execdir` to change the working directory avoids issues with PATH_MAX; though I didn't see any mention of the working directory itself having a limit (which I assume it does, for Linux processes?)

I think we're closer than most people realize, but the hard part isn't generating the code — it's testing it. Drivers need to handle edge cases that only show up under specific hardware conditions, timing issues, power states, etc. An AI can write a first draft pretty fast, but validating it still requires actual hardware in the loop. The FreeBSD case worked because brcmfmac is well-documented and the author could test on real hardware. For more obscure chipsets with no public datasheets, we're still stuck.