《Claude’s Constitution 克劳德宪法》
它为语言模型提供了由宪法确定的明确值，而不是通过大规模人类反馈隐式确定的值。
它使人工智能系统的价值更容易理解，也更容易根据需要进行调整。
https://www.anthropic.com/index/claudes-constitution
----------------------
Anthropic
Claude’s Constitution
How does a language model decide which questions it will engage with and which it deems inappropriate? Why will it encourage some actions and discourage others? What “values” might a language model have?
----------------------
via AI News - Telegram Channel
