That's the real dichotomy. Habits never change, vs habits instantly change to be consistent with the new world. And most reasonable economists would want to go somewhere in between those two extremes. If you expect the new habits to change instantly, and be consistent with the new world, then people really would have to understand the true model, or listen to someone who did.
Read the whole thing, in order to get the context.
The way I would put it is that I think that in what I called local markets (such as the labor market), habits about the way expectations are formed change slowly. We are closer to the extreme of "habits never change." In contrast, in what I called national markets (the foreign exchange market, the bond market), habits can change more rapidly.
Changing rapidly and changing correctly are two different things. I would argue that most of the time people's habitual expectations in local markets work out reasonably correctly. There is little need for them to change habits rapidly. In financial markets, I think that expectations are more volatile and more often off by large amounts.
Although I think of national markets as having model-based expectations, I am not committed to national market expectations being rational. Maybe what you get is a lot of trading on the basis of bad models, so that somebody who has a really good model of what the true value ought to be can make a profit if and only if you can stay solvent longer than the market stays irrational.
As a final note, I would caution against using equations if what the equations tell you to do is express these ideas in terms of a single parameter. I think that's a road to perdition.