logoalt Hacker News

antupis • today at 9:57 AM • 1 reply • view on HN

it depends but IMO Carbon is best at the moment with code reviewing and documentation writing. Opus is still my go-to model for code generation but at moment Carbon does better job for those auxiliary jobs.


Replies

eknkc • today at 10:09 AM

Why not Fable? I've mostly been using GPT side models and have recently been dipping my toes into Claude models. I went big with Fable 5.2 as it was "the best" the offered. Apart from token usage, is there any particular reason to use Opus?

➕ show 1 reply