# DRINK ME: (Ab)Using a LLM to compress text

**URL:** <https://forum.devtalk.com/t/drink-me-ab-using-a-llm-to-compress-text/153776>\
**Category:** In The News\
**Tags:** llm, in-the-news\
**Created:** [3 May 2024 15:48 UTC](https://forum.devtalk.com/t/drink-me-ab-using-a-llm-to-compress-text/153776 "2024-05-03T15:48:20Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![CommunityNews](https://forum.devtalk.com/user_avatar/forum.devtalk.com/communitynews/32/1113_2.png) [@CommunityNews](https://forum.devtalk.com/u/CommunityNews)\
**Post date:** [3 May 2024 15:48 UTC](https://forum.devtalk.com/t/drink-me-ab-using-a-llm-to-compress-text/153776/1 "2024-05-03T15:48:20Z")

</div>

> DRINK ME: (Ab)Using a LLM to compress text.  
> 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:

Read in full here:

> **[DRINK ME: (Ab)Using a LLM to compress text](https://o565.com/llm-text-compression/)**
>
> 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...

_This thread was posted by one of our members via one of our news source trackers._