narrative

PAUSE introduces editable strategy artifacts to make cultural decisions in long-form story adaptation more inspectable and contestable by humans. Experiments show that human edits to the strategy effectively propagate into chapter-level prose, improving transparency in AI-mediated cultural adaptation.

A narrative article exploring the point of view of an AI from birth, likely discussing the implications and experiences of artificial intelligence.

Introduces StorySpark, a module-wise evolutionary search framework for LLM-based story premise generation, demonstrating consistent gains in originality and downstream story quality.

IVIE is a neuro-symbolic approach that combines LLMs for creative generation with symbolic validation to produce coherent and playable interactive fiction worlds. Human evaluation shows its worlds are immersive and thematically coherent.

A Twitter thread argues that AI commoditizes yesterday's competence, creating sameness and increasing demand for human differentiation through narrative framing and organizational worldview.

This paper evaluates LLMs for automatically annotating narrative macrostructure in spoken Mandarin, finding that the best model achieves near-human reliability while reducing annotation time by 65%, though performance degrades on semantically complex or lexically diverse narratives.

Andrew Ng pushes back against the AI jobpocalypse narrative, arguing that AI will create more jobs than it destroys, based on historical trends and current hiring data. He predicts an 'AI jobapalooza' with plentiful new roles.