Elephants have large complex brains [1], exhibit complex social behavior [2], show a facility with tools [3], and are generally thought to be highly intelligent [4]. Cognitive studies have demonstrated that elephants are capable of visual symbol discrimination and long term memory [5], means-end recognition [6], relative quantity judgment [7], mirror self-recognition [8], tool use [3], tool manufacture [9], and an understanding of cooperation [10]. Compared to the vast amount of cognitive research in other species, such as primates and birds, a full accounting of the elephant's cognitive abilities is far from complete [11]. However, these studies indicate advanced cognition in elephants. In light of these findings, it is surprising that elephants have been reported to perform poorly in spontaneous or insightful problem solving tasks [12], [13]. This cognitive deficit is unexpected because spontaneous and insightful problem solving has been shown in various species [14]–[17] that show comparable cognitive abilities to elephants. For example, in Köhler's classic studies [17], chimpanzees solved problems suddenly, without trial and error, by using boxes and sticks to acquire bananas hung overhead beyond their reach. Köhler claimed this was indicative of insight.

To further investigate elephants' capacity for insightful problem solving, we initially tested whether three elephants, two adult females, a 33-year-old and a 61-year-old, and a 7-year-old juvenile male (ages at time of testing), at the Smithsonian National Zoological Park, Washington, D.C., USA, would use bamboo sticks as tools to obtain fruit placed out of reach on the opposite side of the bars of their indoor enclosure. At no time did any of the elephants attempt to reach for the food using the sticks, although they manipulated them in tool-like ways within their enclosures: they used the sticks to scratch themselves, hit the floors, walls, and hanging enrichment items, and pried the doors.

The question arose as to whether the elephants' failures resulted from a lack of problem solving ability, or rather that the bars were impeding the elephants' performance or that the tasks were not ecologically valid. To account for these possibilities, we conducted a second series of tests in the elephants' outdoor yard. See Table S1 for an overview of the experiments. A bamboo branch baited with fruit was hung out of trunk-reach, loosely suspended from an overhead cable. The cable was stretched between the roof of the elephant house and a tree in the elephants' yard. The branches' position varied along the length of the cable for each trial. We provided the elephants with sticks and a large movable object, placed at a distance from the food, which could be moved and used as a tool on which to stand to reach the baited branch. The male elephant, Kandula, was provided with a large, movable plastic cube with which he had previous experience as an enrichment object. The females were provided with an aluminum tub on which they and Kandula had been trained to stand for husbandry examinations. Both objects could accommodate and support the elephants' front two feet. (See Figure 1A for experimental setup.) The females had prior training in pushing large objects (Table S2). Kandula did not receive this training but had previously been observed pushing objects. However, the elephants were neither trained to move objects in order to stand on them nor to use this behavioral sequence to obtain food or other items. Neither the 7-year-old male nor the 61-year-old female had ever been observed moving objects to stand on to obtain food. The 33-year-old female had been observed moving and standing on objects to reach items several times in her adolescence, but not since then, nor since the birth of her son, Kandula.

These results provide experimental evidence that an elephant is capable of insightful problem solving through tool use. Evidence for this ability is indicated by the suddenness of Kandula's problem solving behavior without evidence of prior trial and error learning. His persistent use of this problem solving technique in subsequent sessions and his transference to other objects is consistent with the definition and other criteria that some have set for insightful problem solving [13], [18]. Elephants in the field [19] and those in this study have been observed standing on stationary objects to attain items. However, Kandula's movement of the cube for use as a platform to attain otherwise unreachable food was a novel and spontaneous solution to the problem. It could be argued that the elephant had prior training in a component of the novel problem solving task, standing on an object. However, the sequence of behavior exhibited by Kandula, moving the cube and standing on it to reach food, constitutes a more complex series of events that cannot be accounted for by past training. Kandula's use of the cube and other objects is also consistent with a current definition of tool use [20] in that the object was moved and effectively oriented by the user prior to use to alter the position of the user itself. The onset of the elephant's stacking behavior may not be indicative of insight as it was preceded and followed by trials in which he persisted in trying to use single blocks. Kandula's behavior suggests, however, that he was actively trying to use different objects and strategies for food acquisition. Each time a method was unsuccessful, he switched strategies. Table 1 presents the sequential order of behavior that Kandula exhibited.

We believe that the problem in previous studies has been in treating the elephant trunk as a grasping appendage analogous to a primate hand. Although the trunk is a highly manipulable appendage, in food foraging its function as a sensory organ may take precedence. The elephant has an extraordinary sense of smell [21], and the tip of the trunk is as highly enervated as a human fingertip [22]. The trunk has been described as a “refined eating tool. [21]” It is a superb appendage to locate, examine and acquire food and other objects as it provides the animal with the interaction of olfactory and tactile information. The elephant's eye has a fovea directed at the end of the trunk [23] further facilitating the sensory interaction with visual information. When a stick is held in the trunk, the tip is curled backwards and may be closed, prohibiting olfactory and tactile feedback. These deficits might not deter the elephant from using a trunk-held tool for other tasks but they may inhibit the use of such tools to acquire food. Although elephants have shown the greatest frequency and diversity of tool use of any non-primate mammal, they use tools primarily for skin care [3]. In an extensive review of elephant tool use, only one example of an elephant using a trunk-held tool to acquire food was found [3], [24]. Kandula's placement of the cube to use as a platform brought his trunk closer to the food allowing him to take advantage of his trunk's sensory abilities. We posit that previous failures to observe insightful problem solving in elephants [12] is not indicative of a lack of cognitive ability but rather is due to the reliance on problem solving tasks that precluded the use of the trunk as a sense organ.

The neuromorphology of the elephant brain has been implicated by some researchers [12] as the cause for the apparent lack of insightful problem solving ability. The elephant brain has been described as having neurons that are larger and less densely packed than the primate brain [25]. Hart et al [12] have speculated that elephant cortical neurons may have longer axons traversing more distant cortical regions. It has been further hypothesized that this may result in decreased local compartmentalization resulting in increased time of information processing. Such slower processing has been posited as an explanation for the elephant's poor performance in cognitive tasks. However, a more recent study [26] has shown that the elephant's neural morphology is more complex than previously thought, possibly suggesting greater integration of information, enabling advanced cognitive abilities such as insightful problem solving.

Whether the behavior described herein is truly “insightful” is, of course, a point for discussion. Insight has been controversial since the word Einsicht was first translated from Köhler's German [17].Thorpe later defined insight as the “sudden production of new adaptive responses not arrived at by trial behavior…or the solution of a problem by the sudden adaptive reorganization of experience [18].” Although this definition has been used as a standard, some have found it lacking in not addressing the possible cognitive processes underlying insight [27] such as the use of mental trial and error in problem solving [28]. Others have proposed that the term insight implies a causal explanation and should be abandoned entirely in behavioral studies [29], [30]. Gallistel et al. [31] have proposed a model of learning based on evidence gathering in which an animal changes abruptly to a different strategy when evidence exceeds a decision threshold. Durstewitz et al. [32] have supported this model in rats by demonstrating neurological evidence corresponding to the sudden shifts in behavioral strategies as seen in insightful problem solving. They concluded that their results “support the idea that rule learning is an evidence based decision process perhaps accompanied by moments of sudden insight.”

Although the specific cognitive processes underlying the precipitousness of Kandula's behavior remain in question, this study demonstrates that elephants are capable of insightful problem solving. When given the proper circumstances, elephants, like humans and several other species, can demonstrate “aha” moments.