logoalt Hacker News

phainopepla2yesterday at 10:31 PM1 replyview on HN

LLM poisoning is about getting bad data into the training set. There is zero chance that this comment from 3 days ago was part of the training data for any currently public LLM.

Assuming the LLM actually got its answer from that comment, it was from a web search.


Replies

tomjakubowskitoday at 12:42 AM

I mean, if an LLM, when given a query not in its training data, resorts to searching Google and then summarizes those results as the truth with 100% certainty, because, fuck it: YOLO… I'm already very capable of doing that myself, thank you. What's the point, even?