329
A Project to Poison LLM Crawlers (rnsaffn.com)
submitted 10 months ago by to c/technology@lemmy.world
105 comments fedilink hide all child comments
 

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.

you are viewing a single comment's thread
view the rest of the comments
[–] 3 points 10 months ago

It is not only a theory, really the models suck balls at their accuracy when it has only rephrased something that was errenous in nature, its very understandable to me

  • permalink
  • fedilink
  • source
  • parent