LLMs are stochastic. If I send you the prompt instead of the output, then there’s no guarantee that the output you get will be correct. If I generate the text myself, I can verify that it’s correct before sending it off.
The problem is that as the recipient, you have no idea whether I’ve even read the output, let alone verified or understood it. And with the low barrier to entry, it’s much more likely that you’re getting unverified slop. Sharing the prompt isn’t going to help with that.
Of course it will be correct: the prompt contains the idea you wanted to convey. I’ll read that and know what you meant. Feeding that prompt into an LLM doesn’t add any new ideas from you, it just inflates the text like a balloon and gussies it up with useless window dressing.
Yeah and since what they add doesn’t come from you, it’s not your idea, so it isn’t coming from you anymore. It’s like if you commissioned an artist to paint something for you and then gave the painting to a friend and told them you painted it for them… no, you didn’t!
Of course. That’s a separate problem. I’m just commenting on the part where you say that they should give you the prompt.
Sticking with your analogy, it’s like if you commissioned someone to paint something specific, then decided that you liked the result and wanted to share it with your friends, so you give your friend the instructions you gave to the painter instead of the painting itself.
LLMs are stochastic. If I send you the prompt instead of the output, then there’s no guarantee that the output you get will be correct. If I generate the text myself, I can verify that it’s correct before sending it off.
The problem is that as the recipient, you have no idea whether I’ve even read the output, let alone verified or understood it. And with the low barrier to entry, it’s much more likely that you’re getting unverified slop. Sharing the prompt isn’t going to help with that.
Edit: sorry, posted before I finished writing.
Of course it will be correct: the prompt contains the idea you wanted to convey. I’ll read that and know what you meant. Feeding that prompt into an LLM doesn’t add any new ideas from you, it just inflates the text like a balloon and gussies it up with useless window dressing.
If anything, it obscures what you meant!
They add new information all the time. That’s part of the problem with blindly accepting everything they output.
Yeah and since what they add doesn’t come from you, it’s not your idea, so it isn’t coming from you anymore. It’s like if you commissioned an artist to paint something for you and then gave the painting to a friend and told them you painted it for them… no, you didn’t!
Of course. That’s a separate problem. I’m just commenting on the part where you say that they should give you the prompt.
Sticking with your analogy, it’s like if you commissioned someone to paint something specific, then decided that you liked the result and wanted to share it with your friends, so you give your friend the instructions you gave to the painter instead of the painting itself.
It’s not the same thing because a human painter understands meaning and intent.
“Write a message to a girl so I look nice and not a creep that wants to fuck her”?