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

So your sample size is 1 task and 1 LLM? I would recommend trying o3, opus 4 (API) with web search enabled.



Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

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

Search: