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

I wonder how someone will integrate symbolic reasoning with LLMs, or if it will be possible.


This is what we're doing. I think it's not only possible, but also necessary for applications beyond trial-and-error generation.


Ditto, this seems to have some parallels to the neurosymbolic ideas being explored by Lab V2 at ASU


LEAN




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

Search: