xAI Shares LatchBio Evaluation of Grok 4.6 Safeguards
Evaluation shows model blocks malicious bio queries while permitting useful research.
TLDR
xAI posted that LatchBio tested Grok 4.6 on biosecurity monitoring and adversarial biological tasks. The company states the model detects and refuses dangerous queries, including obfuscated ones, more reliably than other frontier systems. At the same time it continues to answer beneficial scientific queries. xAI linked to LatchBio’s blog post that presents the benchmark results and analysis of the safeguards.
Combined views
136K
2 Sources, first seen 29d ago