Code & Cure
#54 - The Cancer Exam That AI Failed
26:05
What happens when the models everyone keeps calling "doctor-level" have to actually take the test? We put that claim under pressure with a study that lands uncomfortably close to real life: six popular large language models were handed 137 multiple-choice questions on colorectal cancer and forced into a strict zero-shot format — no examples, no reasoning shown, just the letter. Performance came…