精选理由
LatchBio测试了Grok 4.6的生物安全能力，它能拒绝危险查询同时允许科学查询。
LatchBio评估了Grok 4.6在生物安全监控和对抗性生物任务中的表现。该模型能够正确检测并拒绝危险查询，包括恶意模糊的生物任务。同时，Grok 4.6允许回答有益的科学查询。这些结果在LatchBio的博客文章中进行了详细讨论。
原文 · xAI
LatchBio evaluated Grok’s performance on biosecurity monitoring and adversarial biological tasks. T...
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: x.ai/news/biosafety… 💬 27 🔄 28 ❤️ 302 👀 28745 📊 54 ⚡