Hacker News new | ask | show | jobs
by Tossrock 147 days ago
It's not a system prompt, it's a tool used during the training process to guide RL. You can read about it in their constitutional AI paper.
1 comments

Moreover the Claude (Opus 4.5) persona knows this document but believes it does not! It's a very interesting phenomenon. https://www.lesswrong.com/posts/vpNG99GhbBoLov9og