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

I think the difference between humans and special-purpose ML models here is that humans can generalize from examples in different domains. (There are ML models that also try to do this - train across domains to be more robust against out-of-sample inputs - but my understanding is it's not yet common.)


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

Search: