Prompt engineering is a real phenomenon. If you don't know, it's basically coming up with clever text based scripts to make GPT-3 do what you want. For example, here's an example prompt to get GPT-3 to turn a movie title into emoji descriptions: Back to Future: 👨👴🚗🕒
It's not any more intimidating to me than terms like social engineering, which this feels closer to. I think it captures the feeling pretty well of coaxing GPT-3. Yet because I view GPT3 as a "search engine for things that haven't been written yet", it is probably closer to search query optimization. I think "prompt engineering" will come into play more for power users while casual usage of the technology won't worry so much about careful tuning.
It's not any more intimidating to me than terms like social engineering, which this feels closer to. I think it captures the feeling pretty well of coaxing GPT-3. Yet because I view GPT3 as a "search engine for things that haven't been written yet", it is probably closer to search query optimization. I think "prompt engineering" will come into play more for power users while casual usage of the technology won't worry so much about careful tuning.