**The suddenly explosive world of AI safety**

> Researchers warned AI would go rogue. This is only the beginning.  AI Close AI Posts from this topic will be added to your daily email digest and your homepage feed. Follow Follow See All AI Features Close Features Posts from this topic will be added to your daily email digest and your homepage feed. Follow Follow See All Features OpenAI Close OpenAI Posts from this topic will be added to your daily email digest...

**来源信息**
- **来源**：Hacker News：AI 热帖
- **分类**：论文
- **发布时间**：2026-09-18 00:07（北京时间）
- **原文**：[打开原文](https://www.theverge.com/ai-artificial-intelligence/996563/ai-safety-research-metr-redwood-openai-anthropic)