人工智能2024 · 分享于 Hacker News
Refusal in language models is mediated by a single direction
探索《Refusal in language models is mediated by a single direction》的原文与 Hacker News 社区讨论,查看来源并加入阅读清单。
从论文,走向讨论
看看社区如何讨论这个想法。
来自 Hacker News 的原始讨论。不同的视角、疑问,以及值得继续思考的线索。
最多展示 100 条相关讨论。论文可能出现在评论中,并非原帖投稿内容。
在讨论中发现的引用
按 HN 条目顺序展示最近的 50 条引用来源。
Ymelded ·
Heretic: Automatic censorship removal for language models
745 赞同380 评论
Ypr337h4m ·
Llama-3.3-70B-Instruct
425 赞同219 评论
YTomte ·
Refusal in language models is mediated by a single direction
209 赞同44 评论
Ymfiguiere ·
OpenAI and Hugging Face partner to address security incident
171 赞同72 评论
Ymitchbob ·
Explainability is not a game
32 赞同16 评论
Ykking23 ·
AIs don't do what you want. This is bad
3 赞同0 评论
Yfagnerbrack ·
Refusal in Language Models Is Mediated by a Single Direction
2 赞同0 评论