1. Constitutional AI Prompting

Most people tell AI what to do. Engineers tell it how to think.

Constitutional AI adds principles before instructions. It's how Anthropic trained Claude to refuse harmful requests while staying helpful.

Template:

<principles>
[Your guidelines]… pic.twitter.com/nbfUPe1J8g

— God of Prompt (@godofprompt) 16 décembre 2025

1. Constitutional AI Prompting Most people tell AI what to do. Engineers tell it how to think. Constitutional AI adds principles before instructions. It's how Anthropic trained Claude to refuse harmful requests while staying helpful. Template: [Your guidelines]

→ View original post on X — @godofprompt