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

Are you setting the "reasoning effort"? I find going from the default (medium) to high makes a big difference on coding tasks for openai reasoning models.


what/how does that work internally?


https://learn.microsoft.com/en-us/azure/ai-services/openai/h...

It's just the number of tokens it's willing to expend in the little internal dialogue before it has to spit out an answer.




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

Search: