Ideas & society2024 · shared on Hacker News
Representation noising effectively prevents harmful fine-tuning on LLMs
Explore Representation noising effectively prevents harmful fine-tuning on LLMs, 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.
Yjph00 ·
What policy makers need to know about AI
81 points35 comments
Ydarosati ·
Representation noising effectively prevents harmful fine-tuning on LLMs
1 points0 comments