AIBearisharXiv – CS AI · Mar 167/10
🧠
Experimental evidence of progressive ChatGPT models self-convergence
Research reveals that recent ChatGPT models show declining ability to generate diverse text outputs, a phenomenon called 'model self-convergence.' This degradation is attributed to training on increasing amounts of synthetic data as AI-generated content proliferates across the internet.
🧠 ChatGPT