Ideas & society2025 · shared on Hacker News
Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
Explore Weird Generalization and Inductive Backdoors: New Ways to Corrupt 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.
YMrAlex94 ·
No AI* Here – A Response to Mozilla's Next Chapter
564 points328 comments
Ysurprisetalk ·
Our position on open-weights models
191 points174 comments
Yadmp ·
TimeCapsuleLLM: LLM trained only on data from 1800-1875
87 points45 comments
Yjoegibbs ·
Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
7 points2 comments
Ybediger4000 ·
Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
7 points1 comments
Y_tk_ ·
Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
3 points0 comments
Ybearseascape ·
Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
1 points0 comments
YAnon84 ·
Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
1 points0 comments
YPaulHoule ·
Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
1 points0 comments