One possible advantage would be that this takes us back to the polarity insensitive and bidirictional current flow inherent in a relay. Back when logic was routinely made from relays, those attributes were routinely taken advantage of to create systems that weren't strictly boolean in nature. The result was fewer relays (and lower power consumption).
You must be joking... THIS is where we're headed? Somehow, I doubt that Intel and others are too worried about the potential competition. Still, it does cause one pause, and in thinking about it, I can see all sorts of low-end applications that beg for as close to zero power if were possible to achieve. This may help.
No matter how small you make a mems switch, the switching speed is still in kHz or at best barely reaching MHz. Although it is small, there is still inertia associated with the metal that is being moved. For those applications that are okay with kHz clock rates but almost no power consumption and extraordinarily radiation hard, this could be what you are waiting for.
This is actually not true; the UC Berkeley group has already demonstrated ns response times and sub-micron features. The technology promises to scale well. The issues are really system-level: device advantages often get lost when the constraints of an entire system are considered.