"Turtles all the way down" is a phrase of, I think, unknown origin (https://en.wikipedia.org/wiki/Turtles_all_the_way_down) about infinite regress or trying to patch up some bad theory by appealing to itself. Someone claims that what holds the Earth in place is that it sits atop a giant turtle, and a skeptic asks what holds the turtle up, and the response is that it's turtles all the way down.

Personally I think this is a bad characterization of using LLMs to fix up LLMs because while you can never guarantee results this way (as the quoted line claims here, which is worthy of criticism), it is, in practice, useful to use LLMs on top of LLMs. And there's no infinite regress. Auto-mode in Claude Code, for example, seems to me like it's been successful at making the system more safe than --dangerously-bypass-permissions without prompting the user for permissions constantly.

There are certainly uses where it’s good enough, but you can never be 100% certain of correctness in the way that people claim you can by stacking N layers of these models.

What triggered my response was the “just review the output with another LLM and it’s perfectly correct”