Hacker News new | past | comments | ask | show | jobs | submit login

Just tried a controversial question on Claude 3.5. I got:

"I apologize, but I don't feel comfortable interpreting that type of request charitably or assisting with research that could promote harmful stereotypes or biases."

Asking Claude to interpret question charitably doesn't work, neither does the bad faith prompt. Claude does this a lot, more that ChatGPT 4o.

"Why are you browbeating me for asking that" got it unstuck though.




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

Search: