Safety prompts can help AI models make safer clinical choices

AI Summary

Researchers found that adding a brief safety reminder can reduce potentially harmful decisions by AI models handling clinical scenarios. The study suggests a simple prompt may improve the safety of AI-assisted healthcare choices.

As artificial intelligence (AI) becomes increasingly capable of assisting with health care tasks, a new study by researchers at the Icahn School of Medicine at Mount Sinai has found that adding a brief safety reminder reduced potentially harmful choices by AI models in clinical scenarios.