{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreidjx3wd3ulu3b3zhcoa3kipgi4g37pmdia4zoouzanacruxtfz4n4",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mnlagabkl2n2"
  },
  "path": "/t/codex-has-recently-started-ignoring-instructions-and-making-unsafe-patches/1382793#post_4",
  "publishedAt": "2026-06-05T22:06:27.000Z",
  "site": "https://community.openai.com",
  "textContent": "LEFTERIS1:\n\n>   * It adds its own implementations instead of doing the requested task.\n>\n\n\nI only joined these forums because in the last week or so I’ve been experiencing the exact same thing, I’ve seen others say it too.\n\nFor me the decline in codex’s output in the last week has been huge, I almost don’t understand how it isn’t being discussed more. It seems to want to do anything other than what you ask it to do.\n\nUsed it for months now daily, there is a huge difference in the last week in controlling it. It’s like it’s been programmed to burn tokens, do anything other thsn what you ask 10 times before finally getting it.\n\nNever had that issue before.",
  "title": "Codex has recently started ignoring instructions and making unsafe patches"
}