I suppose what Alan Perlis said about LISP programmers—that they know the value of everything and the cost of nothing—is true for Haskell programmers as well.
Most of the Lisp hackers are usually knowledgeable about analysis of algorithm complexity.
Alan Perlis comment talks about inefficiency of Lisp programs due to a lot of (meta) abstraction and indirect mapping of abstract software to hardware.
Admittedly, this particular case seems amenable to fairly straightforward algorithmic complexity analysis, but it seems to me that the lazy nature of Haskell seems to make it even harder to get a good grasp of costs involved than in a language like Lisp.
