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

Do you have any indication whether this “universal” space might be shared between models, or is it unique to the architecture and training set?

Maybe it’s crazy, but is there any possibility that, say, Llama and Mistral use the same representation space?



No need to postulate platonic forms. All we need is the idea that there are real patterns to be mapped. The idea that distinct nets can share a representational space is around at least since Laakso And Cottrell published their "Content and cluster analysis: assessing representational similarity in neural systems" in 2000. If you look for "representational similarity analysis" you'll find more research about it.


> the same representation space

Platonic world of forms, perchance?




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

Search: