In case anyone's interested, here are some references for (a) the original Harsanyi (1955) axiomatization, and (b) the subsequent debate between Harsanyi and Sen about it's meaning. There is much more out there than this, but section 2 of Sen (1976) probably captures two key points, both of which seem equally applicable to Phil's argument.

(1) The independence axiom is seems more problematic when shifting from individual to social choice (as Wei Dai has already pointed out)

(2) Even if it weren't, the axioms don't really say much about utilitarianism as it is is commonly understood (which is what I've been trying, unsuccessfully, to communicate to Phil in the thread beginning here)

• Harsanyi, John (1955), "Cardinal Welfare, Individualistic Ethics and Interpersonal Comparisons of Utility", Journal of Political Economy 63.
• Diamond, P. (1967) "Cardinal Welfare, Individualistic Ethics and Interpersonal Comparisons of Utility: A Comment", Journal of Political Economy 61 (especially on the validity of the independence axiom in social vs. individual choice.)
• Harsanyi, John (1975) "Nonlinear Social Welfare Functions: Do Welfare Economists Have a Special Exemption from Bayesian Rationality?" Theory and Decision 6(3): 311-332.
• Sen, Amartya (1976) "Welfare Inequalities and Rawlsian Axiomatics," Theory and Decision, 7(4): 243-262 (reprinted in R. Butts and J. Hintikka eds. (1977) Foundational Problems in the Special Sciences (Boston: Reidel). (esp. section 2)
• Harsanyi, John (1977) "Nonlinear Social Welfare Functions: A Rejoinder to Professor Sen," in Butts and Hintikka
• Sen, Amartya (1977) "Non-linear Social Welfare Functions: A Reply to Professor Harsanyi," in Butts and Hintikka
• Sen, Amartya (1979) "Utilitarianism and Welfarism" The Journal of Philosophy 76(9): 463-489 (esp. section 2)

Parts of the Hintikka and Butts volume are available in Google Books.