Comment by duskdozer
7 days ago
Some day someone brilliant will discover the idea of "sharing prompts" to get around this issue. So, instead of sending the clean and summarized LLM output, you'll just send your prompt, and then the recipient can read that, and in response, share their prompt back to the original sender.
Venkat Rao's "Sloptraptions" essays (https://contraptions.venkateshrao.com/s/sloptraptions) are the version of this that isn't pithy. (https://contraptions.venkateshrao.com/p/to-know-is-to-stage is particularly good.)