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

> Gemini 2.5 Pro's reasoning traces (before they nerfed them) were a good example. The deep technical analysis, and then the human-friendly version in the final output. But I found their reasoning more readable than the final output!

They were also sometimes more useful: you could see whether it reasoned its way to an answer, or used faulty reasoning, or if it was just contextual recall. Huge shame they replaced them with garbage (though a bit better now).

> the language is surprisingly offputting. I don't know if it got worse

I'm pretty sure it did.



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

Search: