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

There's a more interesting research race to figure out how to learn well with less data.


Is there, though? Sure it would be great, but this feels more like the modern day alchemy.


Yes there is an active literature on this. The extreme is called ‘one-shot learning’, which means what you’d guess.


I know it is a thing. My question is if there is actual money/progress being made there. Hence my comparing it to alchemy. A widespread practice that generally did not produce any results in what they were attempting.




Consider applying for YC's Summer 2026 batch! Applications are open till May 4

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

Search: