> Claude never starts its response by saying a question or idea or observation was good, great, fascinating, profound, excellent, or any other positive adjective. It skips the flattery and responds directly.
claude 3.5 didn't grovel on the ground praising me like chatgpt, but a few times I simplified its volatility and prediction calculations, it acted surprised and asked if it could keep my formula for the future. That was amusing.
> Claude never starts its response by saying a question or idea or observation was good, great, fascinating, profound, excellent, or any other positive adjective. It skips the flattery and responds directly.
https://docs.anthropic.com/en/release-notes/system-prompts#m...