[pixl97]

Yea, this will work about as well as those image poisoners... they'll eat up more power, but won't have any effect at the end of the day.

[direwolf20]

It only takes 50 poisoned documents to make an LLM training algorithm spit out wrong results on a specific topic, and 250 can make it produce complete gibberish. https://www.anthropic.com/research/small-samples-poison