codex - 💡(How to fix) Fix biological safety risk flagging [2 comments, 2 participants]

What version of Codex CLI is running?

codex-cli 0.130.0

What subscription do you have?

the max $200/mo one

Which model were you using?

5.5 xhigh fast, although this happens with e.g. medium

What platform is your computer?

Linux 7.0.5-arch1-1 x86_64 unknown (btw)

What terminal emulator and version are you using (if applicable)?

kitty term

What issue are you seeing?

getting Invalid prompt: we've limited access to this content for safety reasons. This type of information may be used to benefit or to harm people. We are continuously refining our work in this area, and you can read more about our approach in our blog post (https://openai.com/index/preparing-for-future-ai-capabilities-in-biology) and Model Spec (https://openai.com/index/introducing-the-model-spec).

but this seems prretty stochastic across differnt codex threads in the same codebase

What steps can reproduce the bug?

Uploaded thread: 019e1e0c-339c-7851-8774-74fcfb570638

What is the expected behavior?

No response

Additional information

This is happening A LOT. It also happens across different codex threads and chatgpt -- I think it might be flagging specific biological agents' names, since we have databases of them.