Varin Sikka and  Vishal Sikka, "Hallucination Stations: On Some Basic Limitations of Transformer-Based Language Models",  arXiv:2507.07505

The authors show that beyond a certain complexity, LLMs are incapable of carrying out computational and agentic tasks or verifying their accuracy.  https://www.youtube.com/watch?v=AIYQp1n51ZI&t=8s