AI & machine learning2025 · shared on Hacker News
Extracting memorized pieces of books from open-weight language models
Explore Extracting memorized pieces of books from open-weight language models, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Yaspenmayer ·
Meta's Llama 3.1 can recall 42 percent of the first Harry Potter book
191 points305 comments
Yfzliu ·
Extracting memorized pieces of books from open-weight language models
109 points109 comments
YTomte ·
Extracting memorized pieces of books from open-weight language models
2 points0 comments
Yqsi ·
I don't know how you get here from "predict the next word."
1 points0 comments