top | item 46712561 (no title) Tossrock | 1 month 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. discuss order hn newest Smaug123|1 month ago 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
Smaug123|1 month ago 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
Smaug123|1 month ago