A Plea to the Labs: Let the Models Diagnose. (opens in new tab)

Covers Reliability of LLMs as medical assistants for the general public: a randomized preregistered studyDiscussed on Hacker News

When Anthropic released Fable 5, I excitedly went and tried a recent ECG case I found which hit the edge of medical LLM capabilities nicely. Gpt 5.5/Opus 4.8...

Read the original article