RT by @sama: One of the ways scaling test-time compute can benefit people most: have reasoning models think really hard about rare undiagnosed diseases. (opens in new tab)

One of the ways scaling test-time compute can benefit people most: have reasoning models think really hard about rare undiagnosed diseases. Today we’re sharing published evidence that this can work, in some of the most difficult pediatric cases! OpenAI (@OpenAI) Together with researchers at Boston Children’s Hospital and Harvard, we published a study in NEJM AI showing how o3 Deep Research helped clinicians revisit previously unsolved rare pediatric disease cases, and find answers for familie...