Comment by theshrike79
8 days ago
Concept -> LLM fluff -> LLM summary -> Recipient
This kinda risks the broken telephone problem, or when you translate from one language to another and then again to another - context and nuance is always lost.
Just give me the bullet points, it's more efficient anyway. No need to add tons of adjectives and purple prose around it to fluff it up.
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.)