Many domains of machine learning, from language modeling to computer vision, have recently undergone a shift towards generalist models, whose broad generalization abilities are fueled by large and diverse real-world training datasets and high-capacity model architectures. In robotics, however, it has been challenging to apply the same recipe: after all, we cannot easily scrape millions of hours of robot data from the internet and existing model architectures for scalable learning in vision or language modeling are not designed for the continuous control tasks we need to solve in robotics. In this talk, I will describe my work on unlocking scalable robot learning in the real world. I will discuss important differences between robotics and other machine learning domains, and describe how we can adapt scalable learning approaches for robotics to yield robot policies that generalize out-of-the-box to unseen environments, and can be quickly adapted to new tasks or robot embodiments. Through a combination of community-wide data sharing efforts, improved model design and training objectives, my work has enabled the construction of the largest robot learning datasets to date, and the training of generalist robot policies that can perform a range of complex, long-horizon manipulation tasks simply by prompting them in natural language. I will close with a description of current limitations and open challenges towards building truly general robot control policies.