Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

you can see why in claude's system prompt :)

> 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...



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.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: