In my limited experimentation, 5.4 thinking is markedly worse than 5.2 at mathem... | Hacker News

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

scuppernong 5 months ago | parent | context | favorite | on: GPT-5.4

In my limited experimentation, 5.4 thinking is markedly worse than 5.2 at mathematical reasoning.

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