Paul Smolensky has recently announced that the problem of explaining t
he compositionality of concepts within a connectionist framework is so
lved in principle. Mental representations are vectors over the activit
y states of connectionist ''units'', but the vectors encode Classical
trees, whose structural properties in turn ''acausally'' explain the f
acts of compositionality. This sounds suspiciously like the offer of a
free lunch, and it turns out, upon examination, that there is nothing
to it.