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

Well ya once each project, e.g. “grad level math”, “k—12 math”, “undergrad math”, “k-12 chemistry”, etc is sufficient they are all fed into a larger more powerful model.

Maybe my RLHF work does make it harder for me to dream, but I teach models math which means a lot of prompt writing, and yet I have not found a way to have the model teach me math I don’t know yet (and there’s a lot I don’t know). It’s fun to play around with, but I still gravitate toward the isolated texts, not the aggregation as too much is lost or averaged in my opinion/experience. But hey maybe I’m overtrained on the traditional learning methods.



Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10

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

Search: