Natural Language Programming: Rethinking Language, Memory, and Cognition in the Era of Generative AI

The classical paradigm of Natural Language Processing (NLP), language has primarily been treated as an object of computation: something to analyse, classify, translate, or generate. The emergence of Large Language Models (LLMs) challenges this perspective by enabling natural language to function increasingly as an executable cognitive medium through which humans can structure reasoning, orchestrate problem solving, and regulate hybrid human–AI workflows.
This paper introduces the concept of Natural Language Programming (NLPg) as a theoretical and epistemological extension of traditional NLP. Rather than focusing on language understanding alone, NLPg conceptualises prompts as dynamic cognitive artefacts that externalise goals, constraints, assumptions, validation criteria, and intermediate reasoning states. In this perspective, prompting is not reduced to a technical interaction technique, but becomes a form of dialogic cognitive programming operating within distributed human–AI memory architectures. Building on theories of distributed cognition, extended mind, metacognition, and dialogic learning, the paper proposes the notion of Dialogic Working Memory, describing how prompts and conversational states function as temporary external memory structures supporting reasoning continuity and reflective regulation. We further map existing memory architectures (BTMA, SKGE, RMR) onto this framework, illustrating how episodic, semantic, and metacognitive layers support long-horizon conversational coherence. Finally, implications for computational linguistics and AI-mediated knowledge systems are discussed, suggesting the emergence of a post-symbolic and post-interface paradigm in which natural language operates simultaneously as communication medium, executable specification, cognitive scaffold, and distributed memory architecture.