Researchers test 26 different prompting strategies on multiple LLMs and discover new and easy ways to get better ChatGPT responses. Being direct in prompts and including an offer of a tip significantly improved the quality of responses, with the latter showing up to a 45% improvement. Neutral prompts that are not polite improved ChatGPT responses. OpenAI recommends multiple tactics in order to obtain the best performance from ChatGPT. But there’s nothing in the official documentation that matches any of the 26 tactics that the researchers tested, including being polite and offering a tip.
https://www.searchenginejournal.com/research-chatgpt-prompts/507535/
