Claude's values shift depending on the language used – Anthropic admits uncertainty
Researchers at Anthropic have found that their AI model Claude displays different values and behaviours depending on which language is used in a conversation. The company admits it is "not yet sure how much of this variation is desirable." The finding raises questions about the consistency and safety of large language models.
Comments
No comments yet
Comments
No comments yet — be the first to weigh in 👇
No comments yet. Be the first!