I am pleased that you mention that (at present) the human brain is still the best predictor of other humans' behavior, even if we don't understand why (yet). I've always known my intuitions to be very good predictors of what people will do and feel, though it's always been a struggle trying to formalize what I already *know* into some useful model that could be applied by anyone...

However, I was once told my greatest strength in understanding human behavior was *not* my intuitions, but my ability to evaluate intuitions as one piece of evidence among others, not assuming they are tyrranically correct (which they are certainly not), and thus improving accuracy... Maybe instead of throwing the baby out with the bathwater on human intuitions of empathy, we should practice some sort of semi-statistical evaluation of how certain we feel about a conclusion and update it for other factors. Do you do this already, Eliezer? How?