X：SpaceXAI (@SpaceXAI)· @SpaceXAI·· 2026-09-02AI 评分
LatchBio 评估 Grok 4.6 生物安全监测与对抗性生物任务表现
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
LatchBio 评估了 Grok 4.6 在生物安全监测与对抗性生物任务上的表现，发现它能正确识别并拒绝危险查询，包括经过恶意混淆的生物任务，同时仍能回答有益的科研问题。xAI 称 Grok 4.6 拒绝危险查询的可靠性高于其他前沿模型，相关结果已发布在博客文章中。
来源：X：SpaceXAI (@SpaceXAI) · x.lingyaoai.com