Shouldn't the etiquette be that if you send someone a response from AI, you start your message by telling the prompt that produced that reponse?

That, would give the responder the chance to modify the prompt and get a perhaps better answer from the LLM?

▲

Mordisquitos 8 hours ago | parent [-]

Even better, reply only with the prompt that you would have used, not the resulting text. Don't even run the prompt through an LLM.

That results in a shorter and more concise message, and the original sender can choose to use the prompt you provided on their favourite LLM from the start.

▲

galaxyLogic 8 hours ago | parent [-]

Right. You might also consider high-lighting some things you learned from AI's response. Summarizing it and perhaps critiquing it.

AI, and different AIs, give different answers to the same question, so it may be useful if you can provide a good summary of the different responses you got.

▲

Mordisquitos 7 hours ago | parent [-]

Even better, what about piping the different AI responses through another LLM to provide the summary? That way you save yourself the time and effort of reading all the different AI responses.

You could even pipe the final summary directly to your email/IM client and save yourself the copy-paste.

	▲	stingraycharles 6 hours ago \| parent [-]
		I actually use multi-LLM consensus as a part of my daily work, it’s pretty effective.