{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreif7abkrxjkof4467f6pughdcvzzbrtd3lytnpbetneeq2xl7plgv4",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mjs6c2sfkix2"
  },
  "path": "/t/introducing-the-new-codex-for-almost-everything/1379125#post_15",
  "publishedAt": "2026-04-18T18:31:41.000Z",
  "site": "https://community.openai.com",
  "tags": [
    "@barker.edward",
    "write permissions."
  ],
  "textContent": "Hi @barker.edward!\n\nI also use the Pro model in ChatGPT to challenge Codex output. Besides helping to learn where the Codex models currently have limitations, that kind of feedback loop is absolutely the right approach!\n\nHave you tried using custom GPTs or ChatGPT Apps in developer mode? You can store partial model replies through actions or MCP tooling, then connect that with local Codex sessions through skills.\n\nOne thing to keep in mind: automatic extraction of ChatGPT outputs is still against the Terms of Service and could cause issues. But if you set things up so that only the code or plan review is stored externally, you can build your own solution fairly quickly.\n\nHope this helps!\n\nPs. In fact, I believe the latest version of the GitHub App for ChatGPT has write permissions. This could be the fastest way to set this up.",
  "title": "Introducing the New Codex for (almost) everything"
}