{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreifs24rosqjk2lbfgtsxpyc3xahdqhjbkwedpy4zx64lkikbhtrfw4",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mf2dr4zozof2"
  },
  "path": "/t/codex-and-llms-in-general-are-a-big-fat-lie/1374390#post_7",
  "publishedAt": "2026-02-17T09:40:05.000Z",
  "site": "https://community.openai.com",
  "textContent": "Probably like anything in this world, there are people who like things and others who don’t.\nI am pretty busy in this space too, so I believe I can speak with some knowledge on this matter.\n\nWhat doesn’t work is uttering a sentence to Codex and expecting it to magically produce something out of thin air. It’s not humanly possible, so how would a machine be able to do this at the stage we are in right now (today)?\n\nWhat works is approaches that already showed their value in the real world:\n\n  * Test Driven Development\n  * Spec Driven Development\n  * Normalized Systems Theory\n  * Agile/Sliced approach to software engineering\n-…\n\n\n\nWhen you put all this in a repo and manage to get all the ambiguity out of the system before the first letter of programming (read test code) takes place, you happen to get some pretty good code out of the models. I often (7/10) get first-time-right results with this method.\n\nIdeal yet? Probably not\nQuestion: Is human software development ideal yet (after 50 years)\n\nFood for thought…",
  "title": "CODEX and LLM's in general are a big fat lie!"
}