Well, if the state of the world changes, then hanging on what you learned in the past can cause you to do the wrong thing. Sure, there is an old proof that the value of (true) information is greater than 0, you could say, but they could also remember that the state of the world has changed, so there is nothing bad about remembering, or the model could just discount data by how old it is, etc. All true. But the representation becomes more and more complex. I certainly find that I have to pull back and tell myself, wait, the world has probably changed since I learned that, hasn't it? Has it?