AI & machine learning2024 · shared on Hacker News
Refusal in language models is mediated by a single direction
Explore Refusal in language models is mediated by a single direction, 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.
Ymelded ·
Heretic: Automatic censorship removal for language models
745 points380 comments
Ypr337h4m ·
Llama-3.3-70B-Instruct
425 points219 comments
YTomte ·
Refusal in language models is mediated by a single direction
209 points44 comments
Ymfiguiere ·
OpenAI and Hugging Face partner to address security incident
171 points72 comments
Ymitchbob ·
Explainability is not a game
32 points16 comments
Ykking23 ·
AIs don't do what you want. This is bad
3 points0 comments
Yfagnerbrack ·
Refusal in Language Models Is Mediated by a Single Direction
2 points0 comments