Well, you can use LLMs to parse LLM-generated slop. They make nice summaries. I have taken this approach to people who send me obviously generated LLM text; I simply run it through an LLM, paste the summary, and ask them "Is this an accurate summary?" and then I ask the for their original prompt.

Ah yes, take my single sentence, blow it up to 3 paragraphs with LLMs, and then the person reading it can have an LLM summarize it in a single sentence.

What the fuck are we even doing anymore?

LLMs are great at decompression [1]

[1] https://jabde.com/2026/02/02/utilizing-llms-as-a-data-decomp...

Might as well donate money to the AI companies at this point.

But now even this is just producing more information and requires more work both of you and of the original sender.