alt Hacker NewsI really like the point I read somewhere the other day; instead of sending me the AI output, just send me the prompt you used to generate it. That is the only part that contains only the information you are trying to convey. The rest is just guesses flowery language added, and it confuses the actual message being sent.
Replies
The prompt is the whole chat history. It would be like 10~20 times longer than the final output if the author gave the slightest amount of shit.
Would you prefer a 10k word discussion with an agent about a hypothesis with back and forth over data sources and such, analysis, etc, or a 2000 word AI essay condensate with the rough edges smoothed over manually?
I used to do that, but the person could be bad at prompting too (which is often why the LLM couldn't give a good answer in the first place).
So the polite version I use now is: "Hey, just to get a bit more context, what was the original problem you were trying to solve?".
That gets them to distill their own problem a bit further.
i personally prompt to produce a baseline then re-prompt to tweak then re-re-prompt to re-order, then re-re-re-prompt to expand certain parts, then re-re-re-reprompt to properly cross reference internally , then re-re-re-re-reprompt to proof read and add missing references . so there is no single prompt that produced the document and if i were to start from scratch the path would likely be different.
Somewhere in that wall of text is a single statement that might sink the entire project...
Not all AI content was created with one prompt.
I like how some people take offence at that
Yeah, my post is more than a year old at this point: https://blog.gpkb.org/posts/just-send-me-the-prompt/
A lot of people replying seem to be misunderstanding, though. The only point of human-to-human communication is to transmit thoughts from one brain to another. If you simply send me stuff from AI then I don't need you. I want to hear your thoughts. If you don't have any, then I don't need or want to hear from you. Your thoughts are entirely contained within your prompts. Just send me those.
Many people use many prompts and revisions or prompts or combinations or human and AI writing. Its not a simple as just making a single prompt and copying the output as the blog post.
[dead]
[dead]
That implies you think the output of an LLM is only a rewording of the prompt, and that it doesn't add anything from it's corpus of training data. That's obviously untrue.
How is this? https://claude.ai/share/99bfee0f-bab9-4593-aabb-377e71f1151d