[dheera]

Personally I think it will be fairly easy to convince an LLM to do prompt engineering not far from now. They just lack training data, because they are based on information from the web, but "how to prompt engineer" pages are spreading across the web and the next irritation of ChatGPT will probably pick all of that info up.

[toyg]

> the next irritation of ChatGPT

Every iteration of ChatGPT is a potential irritation, I agree.

[thornkin]

How would an LLM do prompt engineering for you? At some level, as others have stated, prompt engineering is about specifying the important details so the LLM can do the job. If you don't specify those details, how would the LLM know them? Some may be arbitrary and so whatever the LLM makes up might be good enough, but at the end of the day, you have to specify the important details.

[sam0x17]

Funny you mention that I've actually been using gpt 4 to write stable diffusion prompts for my own stuff