{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiejmefiij4jqnc6xx6baw6ujlt6dlk3oiwzzq4r6eclxrvabr4f5y",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mnn4u6sd3ix2"
  },
  "path": "/t/codex-has-recently-started-ignoring-instructions-and-making-unsafe-patches/1382793#post_6",
  "publishedAt": "2026-06-06T16:39:24.000Z",
  "site": "https://community.openai.com",
  "textContent": "Completely agree - we’ve observed night and day difference in the comprehension level. It misses intent now across most queries and implementations have quickly become very superficial.\n\nI’ve now verified this across Codex app, VS Codex extension and across many disciplines such as engineering, science, finance, firmware and software dev, across clean and existing repos, with and without defined instructions and workflows and across Med to Extra High reasoning on gpt-5.5. The Extra High feels like a Low/Med did a few weeks ago - possibly worse.\n\nI posted about it recently - whatever changes have taken place have truly diminished the capabilities of the product with the exception of speed. I would say the outputs are generating faster, which is what led me to think right away about the reasoning level.\n\nJust posting for additional confirmation, but this is extremely infuriating and has been causing all sort of problems with our development and automation.",
  "title": "Codex has recently started ignoring instructions and making unsafe patches"
}