I'm not sure what's wrong with me, but I just wasted several hours wrestling codex to make it behave.
Here's my workflow that keeps failing:
- it writes some code. It looks good a first glance
- I push it to github
- automated tests on github show that there's a problem
- go back to codex and ask it to fix it
- it does stuff. It looks good again.
Now what do I do? If I ask it to push again to github, then it will often create a pull request that doesn't include stuff from the first pull request, but it's not a pull request that stacks on top of the previous pull request, it's a pull request that stacks on top of main.
When asked to write something that called out to gpt-4.1-mini, it used openai.ChatCompletion.create (!?!!?)
I just found myself using claude to fix codex's mistakes.
I upgraded to Pro just because of Codex and I am really not impressed. Granted, I am using rust so that may be the issue (or skill issue on my end too).
One of the things I am constantly struggling with is that the containers they use are having issues to fetch anything from the internet:
error: failed to get `anyhow` as a dependency of package `yawl-core v0.1.0 (/wor
kspace/yawl/core)`
Caused by:
download of config.json failed
Caused by:
failed to download from `https://index.crates.io/config.json`
Caused by:
[7] Could not connect to server (Failed to connect to proxy port 8080 after 30 65 ms: Could not connect to server)
Hopefully they fix this and it gets better with time, but I am not going to renew past this month otherwise.
You can specify a startup script for your environment in the Edit -> adbvaned section. The code placed there will run before they cut off the internet access. Also worth noting that it uses a proxy stored in $http_proxy.
Took me an few hours today to figure out how to install maven and have it download all the dependencies. Spent an hour trying to figure out why sudo apt-get update was failing, it was because I was was using sudo!
I have this issue with Devin. Given my limited knowledge of how these work, I believe there is simply too much context for it to take a holistic view of the task and finish accordingly.
If both OpenAI and Devin are falling into the same pattern then that’s a good indication there’s a fundamental problem to be solved here.
I think you need to run the tests locally before you push the PR. I actually think you need to (somehow?) make this part of the generation process before Codex proposes the changes.
Here's my workflow that keeps failing: - it writes some code. It looks good a first glance - I push it to github - automated tests on github show that there's a problem - go back to codex and ask it to fix it - it does stuff. It looks good again.
Now what do I do? If I ask it to push again to github, then it will often create a pull request that doesn't include stuff from the first pull request, but it's not a pull request that stacks on top of the previous pull request, it's a pull request that stacks on top of main.
When asked to write something that called out to gpt-4.1-mini, it used openai.ChatCompletion.create (!?!!?)
I just found myself using claude to fix codex's mistakes.