←back to thread

A Research Preview of Codex

(openai.com)
511 points meetpateltech | 1 comments | 16 May 25 15:02 UTC | HN request time: 0.337s | source
Show context
solresol ◴[17 May 25 06:38 UTC] No.44012451[source]▶
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.

replies(4): >>44012616 #>>44012921 #>>44012938 #>>44013898 #
1. bargainbin ◴[17 May 25 08:39 UTC] No.44012938[source]▶
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.