The model has issues with recurrent visual perception.
What version of Codex CLI is running?
0.122.0
What subscription do you have?
Pro
Which model were you using?
gpt-5.4 xhigh
What platform is your computer?
CLI
What terminal emulator and version are you using (if applicable)?
_No response_
What issue are you seeing?
<img width="503" height="641" alt="Image" src="https://github.com/user-attachments/assets/c67e2125-7b10-4de4-a07c-abc8d5fdefa9" /> Here is an example of the lines next to the folders that I gave the model to create.
What i got:
<img width="390" height="748" alt="Image" src="https://github.com/user-attachments/assets/a9b7f881-e846-4357-a5ea-ecb92246fece" />
<img width="487" height="607" alt="Image" src="https://github.com/user-attachments/assets/f5b18902-1b36-4880-9fa1-29d7a084ae25" />
<img width="255" height="421" alt="Image" src="https://github.com/user-attachments/assets/5c336d26-e1a7-4f30-a376-88b6a6e13589" />
Every time I manually sent her a screenshot, she would find errors, try to fix them - doing a poor job in the process - and then, after looking at the screenshot generated by Playwright, she would somehow claim that everything was now perfect.
What steps can reproduce the bug?
Uploaded thread: 019db474-53ec-7a71-b150-28ad9dcfa204
What is the expected behavior?
_No response_
Additional information
_No response_
2 Comments
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
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 improve future models. And thanks for using the
/feedbackcommand. That additional information is useful.