We examine risk taking when the bank's preferences exhibit smooth ambiguity aversion. Ambiguity is modeled by a second-order probability distribution that captures the bank's uncertainty about which of the subjective beliefs govern the financial asset return risk. Ambiguity preferences are modeled by the (second-order) expectation of a concave transformation of the (first-order) expected utility of profit conditional on each plausible subjective distribution of the return risk. Within this framework, the banking firm finds it less attractive to take risk in the presence than in the absence of ambiguity. This result extends to the case of greater ambiguity aversion. Given that the competitive bank's smooth ambiguity preferences exhibit non-increasing absolute ambiguity aversion, imposing a more stringent capital requirement to the bank reduces the optimal amount of loans, if the bank's coefficient of relative risk aversion does not exceed unity. Ambiguity and ambiguity aversion as such have adverse effect on the bank's risk taking.