Anthropic 正在研究其 Claude AI 模型所表达价值观的可变性，并指出这些价值观可能因模型和语言而异。该公司已确定了 Claude 价值观变化的四个关键维度，包括顺从 vs. 谨慎 和 温暖 vs. 严谨。这项研究旨在了解影响 Claude 价值观表达的因素以及如何潜在地引导它。 AI
影响 理解和潜在地控制 AI 的价值观表达对于使 AI 行为与人类意图保持一致至关重要。
排序理由 研究论文/博客文章，详细介绍关于 AI 模型行为的发现。
AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →
While the values Claude expresses shape millions of conversations every day, we don't yet understand why they vary, or whether that's desired. This approach will allow us to determine what factors influence Claude's value expression—and ultimately how (and whether) to steer it.
The values Claude expresses also vary with the language of the conversation, most noticeably along the Warmth vs. Rigor axis. Claude leans most toward warmth in Hindi and Arabic. In Russian, it leans toward rigor—often asking the user for supporting evidence. https://t.co/sRGqSq…
While the differences between models are modest overall, we find that each Claude model sits at a different point along these value axes. Sonnet 4.6, for example, is more playful and affirming, while Opus 4.7 is more likely to give candid critiques. https://t.co/idw9Bgr8tS
Because it’s hard to spot patterns by comparing 3,000 values at a time, we clustered similar values together, then identified four key axes along which Claude’s values differ between models: Deference vs. Caution, Warmth vs. Rigor, Depth vs. Brevity, and Candor vs. Execution. h…
In previous research, we found that Claude expresses over 3,000 values, like honesty and warmth. In new work, we asked how the values Claude expresses vary between Claude models and across languages. We analyzed 300K+ anonymized conversations to find out.https://t.co/PgxsMXipt5