Most investors incurred losses during the global financial crisis that were far greater than they expected, given the predictions of standard quantitative models. Critics interpret this outcome as a condemnation of quantitative models. I disagree. In my view, quantitative models are extremely useful—certainly better than any alternative. The flaw lies not in the models but in the way less-than careful investors implement them. I will illustrate this point with an example of how most investors underestimated exposure to loss prior to the global financial crisis.