思想与社会2025 · 分享于 Hacker News
Query Agnostic Adversarial Triggers for Reasoning Models
探索《Query Agnostic Adversarial Triggers for Reasoning Models》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。
Ysohzm ·
My open source project was relicensed by a YC company [license updated]
947 赞同506 评论
Ysxv ·
Irrelevant facts about cats added to math problems increase LLM errors by 300%
492 赞同257 评论
YCynddl ·
Training language models to be warm and empathetic makes them less reliable
358 赞同375 评论
Ylayer8 ·
Query Agnostic Adversarial Triggers for Reasoning Models
5 赞同0 评论
Yipnon ·
Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning
4 赞同0 评论
Yfzliu ·
Query Agnostic Adversarial Triggers for Reasoning Models
3 赞同0 评论
Yfelineflock ·
Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning
2 赞同0 评论
Ytfpgh ·
Cats Confuse Reasoning LLM – Adversarial Triggers for Reasoning Models
1 赞同0 评论
YDyslexicAtheist ·
Cats Confuse LLM: Query Agnostic Adversarial Triggers for Reasoning Models
1 赞同0 评论