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

Yikes! Sounds to me like reliable longer form translation is very much not something you can trust to these models. Thanks for sharing.


Right. Training data might not encompass runs of translations exceeding this amount of characters so wouldn't be apparent for anything resembling existing training data.




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

Search: