Microsoft research reveals new prompt engineering techniques that makes GPT-4 achieve previously impossible performance levels

Microsoft’s research study demonstrates the effectiveness of advanced prompting techniques such as Chain of Thought (CoT) reasoning, dynamic few-shot selection, self-generated chain of thought, and choice shuffle ensembling in causing a generalist AI (GPT-4) to outperform a specialist AI (Med-PaLM 2) that was specifically trained for a given domain. This research paper confirms insights that advanced generative AI users have discovered, and the Medprompt technique has the potential to be used to elicit high quality output in any knowledge area, eliminating the need to intensively train a model on specific domains.

Original article: Researchers Extend GPT-4 With New Prompting Method