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

I’d be curious to know if someone could get a more “valiant effort” version of those first two questions with some prompt engineering. E.g. if it was asked to roleplay a conversation with the proper disclaimers to override its objection to not knowing what they actually think.


Bard just dives right in and role-plays it. It honestly feels kind of barbaric compared to the more sophisticated GPT4 answers.




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

Search: