Codex is ignoring instructions, agents.md and making stuff up as it goes along -- it's become very hard to actually use for productive development.

Resolved 💬 2 comments Opened Nov 27, 2025 by pippu Closed Nov 27, 2025
💡 Likely answer: A maintainer (github-actions[bot], contributor) responded on this thread — see the highlighted reply below.

What version of Codex is running?

0.63.0

What subscription do you have?

Max

Which model were you using?

gpt-5.1-codex high

What platform is your computer?

Linux codistry-1 6.8.0-86-generic #87-Ubuntu SMP PREEMPT_DYNAMIC Mon Sep 22 18:03:36 UTC 2025 x86_64 x86_64 x86_64 GNU/Linux

What issue are you seeing?

Codex is ignoring instructions, agents.md and making stuff up as it goes along -- it's become very hard to actually use for productive development.

What steps can reproduce the bug?

Uploaded thread: 019ac630-34cb-7351-a896-e483c3082817

What is the expected behavior?

_No response_

Additional information

_No response_

View original on GitHub ↗

2 Comments

github-actions[bot] contributor · 9 months ago

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

  • #7086
  • #6878
  • #6666
  • #6502
  • #5804

Powered by Codex Action

etraut-openai contributor · 9 months ago

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 /feedback command. That additional information is useful.