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

I feel like GPT-4o would ace that. If you look at the questions in this benchmark they are stuff that 99% of people won't know, although at least they would know that they don't know the answer.


We'll find out -- I just submitted a form to HN to collect some QA pairs to try it out.




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

Search: