I’ve been working with the o4-mini model and initially had a great experience with it. However, starting today, I’m experiencing significant performance issues that are quite concerning. The model’s behavior has changed dramatically:
-
Tasks that previously required only one iteration now take 10+ attempts to complete correctly
-
There’s excessive back-and-forth with repeated clarification requests
-
Overall response quality and efficiency have noticeably declined
Has anyone else noticed similar degradation in o4-mini’s performance recently? The difference is so stark that it feels like the model itself might have been updated or changed.
I’m curious if this is an isolated issue on my end or if others are experiencing similar problems. Any insights would be appreciated.