Using a LLM to compress text

{
  "by": "alexmolas",
  "descendants": 63,
  "id": 40245261,
  "kids": [
    40261540,
    40262622,
    40261833,
    40260370,
    40261840,
    40245530,
    40261860,
    40261821,
    40262990,
    40261900,
    40270584,
    40272209,
    40262879,
    40254565,
    40262905,
    40264131,
    40262023
  ],
  "score": 132,
  "time": 1714722712,
  "title": "Using a LLM to compress text",
  "type": "story",
  "url": "https://o565.com/llm-text-compression/"
}

{
  "author": "Julian",
  "date": "2026-06-01T01:40:50.000Z",
  "description": "Introduction Large language models are trained on huge datasets of text to learn the relationships and contexts of words within larger documents. These relationships are what allows the model to generate text. Recently I’ve read concerns about LLMs being trained on copyrighted text and reproducing it. This got me thinking:",
  "image": null,
  "logo": "https://o565.com/content/images/size/w256h256/format/png/2023/07/favicon.svg",
  "publisher": "o565",
  "title": "DRINK ME: (Ab)Using a LLM to compress text",
  "url": "https://o565.com/llm-text-compression/"
}

null