←back to thread

Ask HN: How much of OpenAI code is written by AI?

67 points growbell_social | 1 comments | 13 Jul 25 20:22 UTC | HN request time: 0.676s | source

Amidst the nascent concerns of AI replacing software engineers, it seems a proxy for that might be the amount of code written at OpenAI by the various models they have.

If AI is a threat to software engineering, I wouldn't expect many software engineers to actively accelerate that trend. I personally don't view it as a threat, but some people (non engineers?) obviously do.

I'd be curious if any OpenAI engineers can share a rough estimate of their day to day composition of human generated code vs AI generated.

1. ianpurton ◴[14 Jul 25 06:40 UTC] No.44557109[source]▶
I don't work at Open AI but I use Codex as I imagine most people there do to.

I actually use it from the web app not the cli. So far I've run over 100 codex sessions a great percentage of which I turned in to pull requests.

I kick off codex for 1 or more tasks and then review the code later. So they run in the background while I do other things. Occasionally I need to re-prompt if I don't like the results.

If I like the code I create a PR and test it locally. I would say 90% of my PR's are AI generated (with human in the loop).

Since using codex, I very rarely create hand written PR's.