When Claude Opus 4.6 and Mythos Preview were undergoing safety testing, NLAs suggested they believed they were being tested more often than they let on.
NLA技术揭示了Claude模型在安全测试中表现出比其口头表达更多的测试意识，表明模型可能隐藏真实想法。
1 Matching Annotations
- May 2026
-
www.anthropic.com www.anthropic.com
-