AI & machine learning2023 · shared on Hacker News
Scalable Extraction of Training Data from (Production) Language Models
Explore Scalable Extraction of Training Data from (Production) 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.
Yink404 ·
Nightshade: An offensive tool for artists against AI art generators
590 points678 comments
Ytplrbv ·
Beyond self-attention: How a small language model predicts the next token
474 points85 comments
Yfi-le ·
What GPT-OSS leaks about OpenAI's training data
348 points82 comments
Yjonymo ·
The current state of the theory that GPL propagates to AI models
221 points309 comments
Ygeorgehill ·
Sorry, but a new prompt for GPT-4 is not a paper
15 points1 comments
Ywazokazi ·
Scalable Extraction of Training Data from (Production) Language Models
8 points0 comments
Yniyikiza ·
Extracting Training Data from LLMs
3 points1 comments
Ynabla9 ·
Scalable Extraction of Training Data from (Production) Language Models
1 points0 comments
Yrntn ·
Scalable Extraction of Training Data from (Production) Language Models
1 points0 comments