[iCarrot]

Try telling GPT-4 that the translation is bad, and ask it to proofread the result for a more natural French

[leumon]

I actually did a bit of research and found this prompt: Please translate the user message from {src} to {tgt}. Make the translation sound as natural as possible.

This actually gives much better results, and now I think I actually changed my mind and like GPT4 better.

[ssl-3]

I find pleasantries like "please" are wasted on bots like GPT4. Remember, it's a machine -- not a human: It doesn't get upset if it doesn't hear "please," "thank you," and "atta-boy".

It just needs some commands to follow.

Something like: "Fluently translate this text, from {here} to {there}, while preserving details" seems to be fine for me.

If the style then needs tweaked, then I edit the original command and tweak it to have it start anew: "Fluently translate this text as a peasant baker from Rhode Island in 1810, from {here} to {there}, while preserving details"

[leumon]

actually from a prompt engineering perspective it makes sense to use words like "please" because the llm is more likely to give better results (which it learnt from the texts it was trained on)

[thorum]

I’ve found telling it to pay attention to nuance helps as well.

[jiggawatts]

You can also ask it to rewrite the result to be more "idiomatic", formal, less formal, whatever...