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

If that was the case they wouldn't have so much stuff in their system card desperately trying to stop it from behaving like this: https://docs.anthropic.com/en/release-notes/system-prompts

> 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.



These are the guys who made Golden Gate Claude. I'm surprised they haven't just abliterated the praise away.


The problem there is that by doing so, you may just end up with a model that is always critical, gloomy and depressed.




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

Search: