##  [AI-slop and the World as we know it](/index.php/node/131) 

    *Submitted by Lennart on Fri, 21 Nov 2025 - 09:45*  

  ![AI-sjusk](/sites/default/files/styles/wide/public/2025-11/ai-sjusk.jpg.webp?itok=PGjMz1Dx)

 

AI slop is a growing issue online. About 50% of new online articles may be AI-generated. This means the internet is filling with content without human involvement.

People create AI content to make money. They can produce many articles quickly this way. This content is often filled with ads.

The goal often is to create websites with low cost. These sites are then filled with advertisements. Small amounts of money can then be earned.

Political reasons also drive AI content creation. People can spread their viewpoints. They can support or refute certain positions.

- Fake news and fake websites are increasing
- People's work is copied and monetized

Research indicates that up to 50% of articles might be AI-generated. This percentage is expected to increase as AI is becoming easier to use.

This rise in AI content makes it harder to find correct information. Search engines struggle to provide accurate results. This affects how people access information.

AI crawlers are similar to search engine web crawlers. They gather text from websites for training sets. So text increasingly includes AI-generated content. This impacts the training of AI models. Large language models are trained on internet text.

If AI-generated text contains AI "mannerisms," these will appear more often in training sets.

This circular process increases distance between content and reality.

- The percentage of accurate information on the internet could decrease
- The quality of text for AI training will also decline

In short: This creates a feedback loop of decreasing quality.

The self-referential tendency of LLM training will create a new need for human-written content.

Sources that are trusted and known to produce human-written text may become more important. People might also gravitate towards trusted sources for content consumption.

Human experts and trusted reporters will likely remain important.

At least until AI can go out into the world and truly experience it first hand.