logoalt Hacker News

fantasizryesterday at 10:12 PM1 replyview on HN

the fact that llms can spit out books they've been trained on near verbatim lends some credence to this.


Replies

fantasizrtoday at 12:03 AM

"However, we also find that Llama 3.1 70B memorizes some books, like Harry Potter and the Sorcerer’s Stone and 1984, almost entirely. In fact, Harry Potter is so memorized that, using a seed prompt consisting of just the first line of chapter 1, we can deterministically generate the entire book near-verbatim. "

https://reglab.stanford.edu/publications/extracting-memorize...

show 1 reply