SpaceXAI· @SpaceXAI · X·· 2026-09-02AI 评分35
AI 导读
LatchBio 评估了 Grok 在生物安全监测和对抗性生物任务上的表现。 他们发现，Grok 4.6 能正确检测并拒绝危险查询，包括恶意混淆的生物任务，同时也能回答有益的科研查询。 我们在博客文章中讨论了这些结果： https://x.ai/news/biosafety-at-the-frontier
正文
LatchBio evaluated Grok’s performance on biosecurity monitoring and adversarial biological tasks.
They found that Grok 4.6 correctly detects and refuses dangerous queries, including maliciously obfuscated biological tasks, while also allowing beneficial scientific queries to be answered.
We discuss these results in a blog post:
https://x.ai/news/biosafety-at-the-frontier
来源：SpaceXAI · x.com