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

I'm not GP, but I don't think they are taking issue with the fact that e.g. layer numbers or architecture were arrived at without first-principles but rather empirically.

Rather that when you do come to something empirically, you need to validate your findings by e.g. ablations, hypothesis testing, case studies, etc...




Exactly, I can confirm this is what I meant.




Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

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

Search: