GPT-4 outperforms Med-PaLM 2 with powerful prompting strategies

[rdpfeffer]

https://www.microsoft.com/en-us/research/blog/the-power-of-prompting/

[theogravity]

Found an article that's unfortunately ad-heavy that explains the strategies used in more detail for the technical layperson:

https://www.searchenginejournal.com/new-gpt-4-prompt-techniq...