Quality/regression issue

What issue are you seeing?

I’m using Codex Desktop with the Sol model on a $200 subscription. The same tasks that previously produced correct results now consistently produce much worse results. This appears to be a model regression, not a prompt issue. Please compare this session with my previous results and verify the model quality.

What steps can reproduce the bug?

usage

What is the expected behavior?

_No response_

Additional information

_No response_