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

Maybe it's just vibes but I've repeatedly felt like gpt-6-astra on its default setting of medium is less rigorous and thoughtful than gpt-5.6-sol on its default setting. What I am certainly not getting is any sense that we are at "AGI" yet.


Most would applaud that as Sol has quite a reputation for over engineering. Not every software needs to go to the moon.


So your experience is that Astra doesn't over engineer? For more than twice the price of Sol I think most people will take the over engineering.


I found it to be less annoying in that regard then sol. Might just be that it better listens to what I instruct though.

But yeah, it's really expensive, at least in relative terms.




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

Search: