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

This definition fails badly because it doesn't test anything outside of language. At a bear minimum have the tests involved have pictures and descriptions in them and require the AI to use the same model to synthesize information from both.


Lots of human tests involve pictures. Why does the definition fail badly?




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

Search: