And we get our subscription usage cut in half tomorrow if I remember correctly? EDIT: By a third. Thx below.
Degraded performance for multiple models
11–20 of 149 posts
Re: Degraded performance for multiple models
#12ok, i am not crazy
well, I wouldn't go that far .. but in this small, narrow case ... no.
Re: Degraded performance for multiple models
#13This feels like a near daily occurrence.
Re: Degraded performance for multiple models
#14This age: we made the thing that codes faster before we made the thing that does QA faster.
Re: Degraded performance for multiple models
#15And we get our subscription usage cut in half tomorrow if I remember correctly? EDIT: By a third. Thx below.
What?!
Re: Degraded performance for multiple models
#16Our week of discontent.
Re: Degraded performance for multiple models
#17ive found degraded performance on models larger than 4.7. i assume its model damage from overly self righteous post training resulting in false/feigned balance imported into any long running complex task. wish i was joking.
I've switched off claude this week; the last week has been significantly degraded in ability, many more screw-ups.
Re: Degraded performance for multiple models
#18And we get our subscription usage cut in half tomorrow if I remember correctly? EDIT: By a third. Thx below.
by a third (it was 50% increased)
Re: Degraded performance for multiple models
#19Nooooo I'm going to have to use my brain again and write 100% of my code like a caveman from December 2024.