{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreidp2iqyq5adyqphqmtw3ljjyftjalsgohmmiutu32v7nr5bsfxlua",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mo7fsbnf3xa2"
  },
  "path": "/t/why-does-codex-repeat-the-same-mistakes/1383615#post_12",
  "publishedAt": "2026-06-13T22:05:13.000Z",
  "site": "https://community.openai.com",
  "textContent": "Also, if the documents are already there -\n\nWhen you start a new session, you have to pick the documents you want the codex instance to read other wise the docs aren’t being read, and you likely don’t need it to read every doc.\n\nTypically, i’ll have an instance of Codex list all the docs in the repo, and every so often, that instance I’ll have it look for stale docs… this can get expensive if you do it generally like that because it will inspect everything the docs point at…\n\nAnd if you have a lot of docs… well, that’s a lot of looking around.\n\nSo pick your docs, ask ChatGPT how a lint will help your docs out, too, and use lints when you need them.\n\nYou’ll be able to slice through the issue you’re having bit by bit, as well as be prepared for any new failure modes that come up as you expand your coding horizons ^.^",
  "title": "Why does Codex repeat the same mistakes?"
}