A study from New York University and the University of Texas at Austin identified six linguistic patterns that make AI-generated text difficult for humans to read. Researchers suggest this issue stems from AI models being trained on code and mathematical content, where precise correctness is prioritized over human-readable clarity. In contrast, smaller AI models tend to produce text that more closely resembles human writing. AI
IMPACT AI models may need to prioritize human readability in training to improve user experience and comprehension.
RANK_REASON Academic research paper detailing findings on AI text generation. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →