xAI· GrokSafety or policy

xAI announces independent biosecurity evaluations of Grok 4.6 by LatchBio, showing it outperforms other frontier models in refusing hazardous tasks while maintaining routine biological work, and discusses layered safeguards and improvements over previous versions.

From the source

Today, LatchBio published an independent analysis of Grok 4.6 on their biological capability and biological red-teaming benchmark suites.

x.ai