Maybe math is easier to score and do reinforcement learning on because of it's '... | Hacker News

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

nickfromseattle 9 months ago | parent | context | favorite | on: Learning to Reason with LLMs

Maybe math is easier to score and do reinforcement learning on because of it's 'solvability' whereas writing requires human judgement to score?

Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact