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

Caveman hurt model performance. If you need a dumber model with less token output, just use sonnet-4-6 or other non-reasoning model.


Does it? I'm not sure I'd necessarily notice but I haven't found it noticeably worse.




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

Search: