How has the way that we write text messages or emails changed over time with autocomplete or smart reply functionalities? This talk will cover topics centered around building such writing assistants with language models (LMs) as well as understanding collaborative writing processes between humans and LMs, with the goal of provoking discussions on existing and future forms of interactions. Concretely, I will first focus on building and evaluating autocomplete and thesaurus systems. Then, I will transition to a more fundamental question of “how can we reason about interaction between humans and LMs?” and introduce our recent work on using a human-LM collaborative writing dataset to understand the capabilities and limitations of LMs.