What I find strange is how rarely LLM output is distributed alongside the LLM input, especially outside of code repos. Why can't I rerun the prompt that resulted in your work next year, when models have gotten better? Are people ashamed of their prompts? Ashamed of having used AI? i unno
Prompt used to generate this message: "Create a comment for Hacker News which bemoans the lack of AI prompts being shared with the stuff it creates. Speculate on the reasons and create a call for engagement. Use quantum hyperthinking. End with a typo to prove your humanity."
FMFL. I'm going to build a paper-based social network where non-handwriting is prohibited. Like in the 70s.
You should. Then I could start my SHWAAS business offering unbreakable encryption for it.
(Shitty Handwriting As A Service).
There are handwriting physical bots too, or even AI image generators for "handwritten" text.
{"deleted":true,"id":48499857,"parent":48499621,"time":1781237926,"type":"comment"}
loading story #48503771
> Why can't I rerun the prompt that resulted in your work next year, when models have gotten better?
Because you could also just point the better model at the generated code and tell it to improve it, so why save the prompt too?
Because improving a high schoolers project is probably not as good of an idea as giving the original task to a senior engineer.
loading story #48503714
I think this is a gap in the tooling (Git, VCS, and forges) and the Zed people are working on this