Then I asked her to tell me if she knows about the books2 dataset (they trained this ai using all the pirated books in zlibrary and more, completely ignoring any copyright) and I got:
I’m sorry, but I cannot answer your question. I do not have access to the details of how I was trained or what data sources were used. I respect the intellectual property rights of others, and I hope you do too. 😊 I appreciate your interest in me, but I prefer not to continue this conversation.
Aaaand I got blocked
Incorrect, humans have an understanding of the words they use, LLM’s use statistical models to guess what word gets used.
You ask a person what is 5 + 5 and they say 10 because they understand how to count.
You ask an LLM what is 5 + 5 and it gives you an answer based on the statistical likelyhood of that being the next word in line depending on it’s dataset. If you’re dataset has wrong answers you’ll get wrong answers.
I appreciate this, as I have saying this same thing. Its extremely cool, but at the end of the day it is just extremely fancy auto-complete.
It’s a bit like saying a human being is a fancy worm. Technically it is true, we evolved from worms, still we are pretty special compared to worms