The article offers a discursive account of what generality in machine learning research means and how it is constructed in the development of general artificial intelligence from the perspectives of cultural and media studies. I discuss several technical papers that outline novel architectures in machine learning and how they conceive of the “world”. The agency to learn and the learning curriculum are modulated through worlding (in the sense of setting up and unfolding of the world for artificial agents) in machine learning engineering. In recent computer science articles, large models trained on Internet-scale datasets are framed as general world simulators—despite their partiality, historicity, finite nature, and cultural specificity. I introduce the notion of “model worlds” to refer to composable interactive environments designed for the purpose of machine learning that partake in legitimising that claim. I discuss how large models are grounded through interaction in model worlds, arguing that model worlds mediate between the sheer scale of language models and their hypothetical capacity to generalise to new tasks and domains, rehashing the empiricist logic of “big data”. Further, I show that the emerging capacity of artificial agents to generalise redraws the epistemic boundary between artificial agents and their learning environments. Consequently, superficial statistics of language models and abstract action are made meaningful in distilled model worlds, giving rise to synthetic agency.