Hacker News Reader

I would be glad to read anyone's prompts they use to generate AI text. I don't see why I need to necessarily read the output, though.

I can take the other person's prompt and run it through an LLM myself and proceed from there.

View on HN

I think that may be an insight to something quite profound. We used to measure the "doubling of knowledge" against number of peer-reviewed papers of scientific research etc. Now not so much. "Knowledge" has become more proprietary, and condensed into the AI models replacing the libraries of training data. We now measure "doubling of knowledge" as the next version or iteration of a model. In some kind of real sense, the prompt IS more powerful than the output.

Reply on news.ycombinator.com