📖 AI fiction is easy to distinguish from human writing
Researchers from the University of Maryland and Google DeepMind have proven that texts created by Claude, GPT, and Gemini have systemic flaws in narrative construction. Using a tool called StoryScope, scientists identified a tendency for models to use simplified structures: excessive moralizing, replacing action with philosophical dialogue, and using physical clichés instead of deep emotions.
🌍 This shifts the focus of the fight against AI content from simple stylistic analysis to a deep analysis of plot structure and narrative logic.
👤 The study confirms that modern LLMs are not yet capable of genuine creativity.
Source 1: https://www.404media.co/ai-fiction-is-easy-to-detect-because-its-stupid-and-bad-research-finds/