logoalt Hacker News

hansonkd • today at 6:21 PM • 3 replies • view on HN

I hate Opus 5.5, constant overreach and over-engineering for any project


Replies

Silagi • today at 6:24 PM

That's wild to say when comparing to the OpenAI family of models. I've never seen so many tests that validate tests that validate tests.

➕ show 1 reply
cesarvarela • today at 8:36 PM

Medium or High? Depending on the task, you might want to switch between them.

petesergeant • today at 6:36 PM

You’re holding it wrong.