Ideas & society2025 · shared on Hacker News
Query Agnostic Adversarial Triggers for Reasoning Models
Explore Query Agnostic Adversarial Triggers for Reasoning 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.
Ysohzm ·
My open source project was relicensed by a YC company [license updated]
947 points506 comments
Ysxv ·
Irrelevant facts about cats added to math problems increase LLM errors by 300%
492 points257 comments
YCynddl ·
Training language models to be warm and empathetic makes them less reliable
358 points375 comments
Ylayer8 ·
Query Agnostic Adversarial Triggers for Reasoning Models
5 points0 comments
Yipnon ·
Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning
4 points0 comments
Yfzliu ·
Query Agnostic Adversarial Triggers for Reasoning Models
3 points0 comments
Yfelineflock ·
Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning
2 points0 comments
Ytfpgh ·
Cats Confuse Reasoning LLM – Adversarial Triggers for Reasoning Models
1 points0 comments
YDyslexicAtheist ·
Cats Confuse LLM: Query Agnostic Adversarial Triggers for Reasoning Models
1 points0 comments