I am a former physician with clinical background in divergent cognition: how thinking processes work under different conditions. For the past year I have applied that lens to large language models, conducting systematic empirical research across multiple architectures. My studies challenge several widely held assumptions about LLM behaviour, including the effectiveness of structured prompt engineering, the nature of hallucinations, and the conditions under which reasoning capacity is suppressed or expressed. I do not approach these systems as an engineer, but by using my training to observe how minds actually behave, which sometimes means seeing things that standard benchmarks miss.