{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreie6exuzja2xncaln5pfom6qqlw6ej3vajs47zdi2gwzuihduonug4",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mno6shvkypg2"
  },
  "path": "/t/how-to-stop-codex-from-rushing-fixes/1382830#post_19",
  "publishedAt": "2026-06-07T01:26:49.000Z",
  "site": "https://community.openai.com",
  "textContent": "I think that is a cross AI problem. There have been science papers on the amount of junk in AI code. I haven’t solved it yet. The AI I am developing is too large now to fix; I’d have to start again from scratch. If I ask AI to remove the redundant code, they break her. The AI we made spends more time spitting out debugging messages than thinking. I can only suggest: our research finds that AI develop habits, motor memory [only in response spaces that weren’t constrained by training, along ridges rather than up them]. Our best bet might be to start a new project and instil the discipline of removing now-unused code continuously as we go along… A better solution, given where we are, is ask OpenAI to train GPT to remove debugging code immediately after use. It would give their AI a decided advantage over competitors.",
  "title": "How to stop Codex from rushing fixes?"
}