A talent for chemistry is no longer exclusive to human chemists. A research team at the University of Glasgow has created an algorithm by which a robot chemist performs more efficiently than its human competitors. The team constructed an experiment to determine the algorithm’s, and therefore the robot’s, ability to discover and crystallize gigantic self-assembling molecules. The robot was then pitted against the research team with both robot and research team being given the starting materials, an experimental protocol for the synthesis and crystallization process, and an initial data set detailing previous successful and failed crystallisation attempts. Each side established their own experimental conditions and procedures in order to analyze the maximum amount of chemical space. The robot was more efficient at searching the crystallization space and rapidly improved its predictive performance to beat the humans. The research team theorized that, by nature, humans are less inclined to perform ‘jumps’ through chemical space. Instead, trained chemists often work methodically and incrementally, making decisions based on the individual’s prior knowledge and training. While the team does not expect to be replaced by robots – at least not soon – their hope is that robots will advance the research of humans by exposing their own blind spots and biases and enabling creative leaps.