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

Slow is good thought, that's when you know it'll get it right.


Correctness does not necessitate slowness.

And why would I want a slower mode that gets it right when the faster model already got it right before?

If it can’t even do basic stuff anymore I’m not gonna use it for advanced tasks either.




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

Search: