AIThe Decoder8h ago
AI chatbots reading X-rays can be dangerously confident even when
AI chatbots reading X-rays can be dangerously confident even when they're wrong
The RadLE 2.0 benchmark tests whether AI models in radiology can tell when they should leave a diagnosis to a human. Many models deliver wrong findings with full confidence, and human radiologists are still well ahead. Before AI can diagnose on its own, it needs to learn when…
Read full articleSource: The Decoder · Opens in new tab