{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreicwvo5dzdg4sxf7hwqeznigpai2sizzizbm5vrvr5pcgowd2au5aa",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mnmpgueiwky2"
  },
  "path": "/t/using-chatgpt-for-planning-vs-codex/1382876#post_1",
  "publishedAt": "2026-06-06T12:55:16.000Z",
  "site": "https://community.openai.com",
  "textContent": "Good day.\n\nFirst, I’d like to say that Codex has become such an incredible, powerful tool. I hardly write code anymore - what a paradigm shift! It’s remarkable to look back and recall how _seamlessly_ we have transitioned.\n\nNaturally, cost and power intertwine. We spend moar, and/or strategize to reduce cost.\n\nAs a result, I have been using ChatGPT w/ GitHub connector to plan and debug, while using Codex to execute, and have been wondering if anyone else has done so?\n\n## Advantages\n\n  * Doesn’t cost Codex credits\n  * Is much easier for back-and-forth\n  * Can be used in any typical conversation\n\n\n\n## Disadvantages\n\n  * I imagine the model isn’t as _suitable_ as Codex, and more likely to make bad decisions? However, I haven’t really been able to notice any difference\n\n\n\nWonder if anyone else has adopted this strategy, and what they’ve seen.\n\nI imagine this would be effective for many use-cases - not strictly coding.",
  "title": "Using ChatGPT for Planning vs Codex?"
}