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

They’re the same thing:

A type theory has a corresponding geometric interpretation, per topos theory. And this is bidirectional, since there’s an equivalence.

A geometric model of language will correspond to some effective type theory encoded in that language.

So LLMs are essentially learning an implicit “internal language” they’re reasoning in — based on their training data of our language and ways of reasoning.




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: