codex cli gpt 5.1 max getting flakey like gpt 4 again
Resolved 💬 2 comments Opened Dec 4, 2025 by spacemeadow Closed Dec 4, 2025
💡 Likely answer: A maintainer (etraut-openai, contributor)
responded on this thread — see the highlighted reply below.
What version of Codex is running?
codex-cli 0.63.0
What subscription do you have?
plus
Which model were you using?
gpt-5.1-codex-max - high
What platform is your computer?
MacOS
What issue are you seeing?
The model is making errors again in the flaky way that ChatGPT four was making errors. For complicated coding, it is impossible to use an AI that makes errors like this.
What steps can reproduce the bug?
Uploaded thread: 019ae46c-1771-7370-8343-05bbc0b7a58c
What is the expected behavior?
It's code checks and communication have to make sense.
Additional information
_No response_
2 Comments
+1
Yes, I've noticed, that it is super lazy today.
that is only a few of the things from working with it today. at first I thought I'm using a different model and reasoning effort, but no:
gpt-5.1-codex-maxwith reasoningxhigh.edit: using codex-cli 0.64.0
Thanks for the bug report. We'll share the feedback with the team responsible for training our codex models. We're tracking this feedback and similar reports so we can make future models more robust and efficient. And thanks for using the
/feedbackcommand. That additional information is useful.