>I don’t really get anything useful out of these postmortems (e.g., clues about how to rephrase my instructions)
Unfortunately, an LLM can't actually reflect or advise how you could have improve the prompt. Otherwise we could give them a sample output and say "Generate the prompt that would produce this output.
From the blog:
>I don’t really get anything useful out of these postmortems (e.g., clues about how to rephrase my instructions)
Unfortunately, an LLM can't actually reflect or advise how you could have improve the prompt. Otherwise we could give them a sample output and say "Generate the prompt that would produce this output.