MacDorman isn’t splitting hairs with this analysis. It’s right there in the second paragraph of Turing’s landmark 1950 paper, “Computing Machinery and Intelligence,” published in 1950 in the journal Mind. He begins by describing a scenario where a man and a woman would both try to convince the remote, unseen interrogator that they are female, using type-written responses or by speaking through an intermediary. The real action, however, comes when the man in replaced by a machine. “Will the interrogator decide wrongly as often when the game is played like this as he does when the game is played between a man and a woman?” asks Turing.
Something that doesn't get mentioned enough in these discussions is that when Turing came up with his "test" (actually just a part of a groundbreaking paper on artificial intelligence) he was being forced to imitate a straight male. The notion of gender was much more central to Turing's ideas of identity than it was to intelligence... and so was the test.
It's giving me a 404. I think you mean this article? Edit: nice article. The Imitation Game seems to me like something a descendant of IBM's Watson could solve. It is indeed much more interesting to have an AI lie convincingly about characteristics it doesn't have. I don't think it has to be a gender thing specifically - that was chosen by Turing because it's part of his world. I think a test like this could be just as interesting if he had to pretend to be someone with a disability, or an illness of some sort.
Dammit, fixed. Thanks. The whole subject is interesting to me because the way Turing set it up, it wasn't about "if you can do this, you're self aware" it was "if you can do this, you're a great imitator and intelligence has nothing to do with it." One of these days I'll read the whole thing.