**AI安全研究占比五年增长25倍,解读性成最大子领域** _How much of ML research is about AI safety, what
原帖
**AI安全研究占比五年增长25倍,解读性成最大子领域**
_How much of ML research is about AI safety, what is it about, and who's doing I_
> 基于LLM对2019至2026年三大顶会论文的统计显示,AI安全论文占比从0.3%升至8.3%。其中解读性(Interpretability)是最大子领域,其次是对齐训练和对抗鲁棒性。
**来源信息**
- **来源**:Hacker News:AI 热帖
- **分类**:论文
- **发布时间**:2026-07-15 19:02(北京时间)
- **原文**:[打开原文](https://www.lesswrong.com/posts/hcq4ZDoijSjy3Wrba/how-much-of-ml-research-is-about-ai-safety-what-is-it-about)