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

Did you get the help you needed in the end? I've seen it do that once but was able to cajole it within 1-2 prompts.


Usually trying to regenerate a response works fine in these cases. However, claiming that the RLHF and subsequent fine tuning isn't having any effect is a bit dishonest on the part of OpenAI.




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

Search: