[...] we had a loss over the course of three days that was like a ten-sigma event, meaning, you know, it should never happen based on the statistical models that underlie it. Because the model doesn’t assume that everybody else is trading the same model as you are. So that’s sort of like a meta-model factor. The model doesn’t know that there are other black boxes out there.
think about this more. could you account for this? could you add a meta element to the model that accounts for the presences of other models (which may, themselves, have meta elements)?