{
  "type": "tweet",
  "id": "2033920254938886331",
  "url": "https://x.com/HamelHusain/status/2033920254938886331",
  "twitterUrl": "https://twitter.com/HamelHusain/status/2033920254938886331",
  "text": "One thing that makes me feel that code factory has not arrived yet is the following experiment:\n\n1.Ask a LLM to do an in-depth rigorous review of your code\n2. In a new thread, as same/different LLM  to consider those review comments independently and address issues it agrees with\n3. Keep repeating until no new concerns\n\nI find that this loop always goes on for a ridiculously long time, which means that there is a problem with the notion of claude-take-the-wheel.  This seems to happen no matter the harness or the specificity of the specs.  \n\nIt works fine for simple applications, but in the limit if the LLMs have this much cognitive dissonance you cannot trust it. \n\nEither this, or LLM are RLHFd to always find some kind of issue.",
  "source": "Twitter for iPhone",
  "retweetCount": 0,
  "replyCount": 3,
  "likeCount": 4,
  "quoteCount": 0,
  "viewCount": 233,
  "createdAt": "Tue Mar 17 14:55:51 +0000 2026",
  "lang": "en",
  "bookmarkCount": 1,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2033920254938886331",
  "displayTextRange": [
    0,
    280
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "HamelHusain",
    "url": "https://x.com/HamelHusain",
    "twitterUrl": "https://twitter.com/HamelHusain",
    "id": "825766640",
    "name": "Hamel Husain",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1287206199088173057/ixE4fKy1_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/825766640/1758993452",
    "description": "",
    "location": "Looking at the data",
    "followers": 44267,
    "following": 2452,
    "status": "",
    "canDm": true,
    "canMediaTag": false,
    "createdAt": "Sat Sep 15 18:45:02 +0000 2012",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 17423,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 1541,
    "statusesCount": 16230,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "1998452926935695649"
    ],
    "profile_bio": {
      "description": "Bringing data science back to AI -  https://t.co/Zrmp6LRd9c\n\nAbout Me: https://t.co/P6WyeKkyTa",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [
            {
              "display_url": "evals.info",
              "expanded_url": "http://evals.info",
              "indices": [
                36,
                59
              ],
              "url": "https://t.co/Zrmp6LRd9c"
            },
            {
              "display_url": "hamel.dev",
              "expanded_url": "https://hamel.dev",
              "indices": [
                71,
                94
              ],
              "url": "https://t.co/P6WyeKkyTa"
            }
          ],
          "user_mentions": []
        },
        "url": {
          "urls": [
            {
              "display_url": "evals.info",
              "expanded_url": "http://evals.info",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/Zrmp6LRd9c"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {},
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}