@tomchapin - GPT-4, when prompted with this new “MedPrompt” technique

GPT-4, when prompted with this new “MedPrompt” technique, outperforms even Med-PaLM 2 https://www.microsoft.com/en-us/research/blog/steering-at… With Medprompt, GPT-4 achieves state-of-the-art results on all nine of the benchmark datasets in the MultiMedQA suite. The method outperforms leading specialist models such as Med-PaLM 2 by a significant margin with an order of magnitude fewer calls to the model. Steering GPT-4 with Medprompt achieves a 27% reduction in error rate on the MedQA dataset over the best methods to date achieved with specialist models and surpasses a score of 90% for the first time. Paper: https://arxiv.org/abs/2311.16452 GitHub: https://github.com/microsoft/promptbase