Website operators are being asked to feed LLM crawlers poisoned data by a project called Poison Fountain.
The project page links to URLs which provide a practically endless stream of poisoned training data. They have determined that this approach is very effective at ultimately sabotaging the quality and accuracy of AI which has been trained on it.
Small quantities of poisoned training data can significantly damage a language model.
The page also gives suggestions on how to put the provided resources to use.
Source: trust me bro.
Nightshade tried the same thing and it never worked.
Here’s your source: https://www.anthropic.com/research/small-samples-poison
Nightshade did work on older models. Newer models adapted to prevent poisoning.
This is a new approach.
Ye, nightshade was defeated by a blur and sharpen iirc lol. Still, was a good first step.