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

No comment on if output analysis is all that is needed, though it makes sense to me. Just wanted to note that using file size differences as an argument may simply imply transformers could be a form of (either very lossy or very efficient) compression.


You can argue any form of data is an arbitrarily lossy compression of any other form of data.

I get your point, but nobody is archiving their companies 50 years of R&D data with and LLM so they can get it down to 10GB.

They may have traits of data compression, but they are not at all in the class of data compression software.




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

Search: