Public Discussion - General Members

The AI company Anthropic has put out a set of "Constitutional Principles" that guide its chatbot, Claude.

It's a fascinating list, drawing on the Universal Declaration of Human Rights, and Apple's privacy policies.

www.anthropic.com

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?