Robert Solow on Dynamic Stochastic General Equilibrium Models (DSGE)

Robert Solow:

...Economic theory is always and inevitably too simple; that can not be helped. But it is all the more important to keep pointing out foolishness wherever it appears. Especially when it comes to matters as important as macroeconomics, a mainstream economist like me insists that every proposition must pass the smell test: does this really make sense? I do not think that the currently popular DSGE models pass the smell test. They take it for granted that the whole economy can be thought about as if it were a single, consistent person or dynasty carrying out a rationally designed, long-term plan, occasionally disturbed by unexpected shocks, but adapting to them in a rational, consistent way. I do not think that this picture passes the smell test. The protagonists of this idea make a claim to respectability by asserting that it is founded on what we know about microeconomic behavior, but I think that this claim is generally phony. The advocates no doubt believe what they say, but they seem to have stopped sniffing or to have lost their sense of smell altogether.

Ouch.  I'd like to think these tools are useful in many applications.  Actually, I think among the first applications of the Bellman equation and stochastic dynamic programming were in agricultural economics by Oscar Burt.  I'm doing some stuff with crop rotations right now that I think is useful, interesting, and relevant to the real world.  But I think I have to agree with Solow here: I really don't see how these models have been useful in helping us to understand any of the important questions in macroeconomics.  But then I'm not a macroeconomist.  Can anyone briefly explain a key insight about the macro economy that DSGEs have helped to teach us?