{
  "type": "tweet",
  "id": "2026833569528644022",
  "url": "https://x.com/omarsar0/status/2026833569528644022",
  "twitterUrl": "https://twitter.com/omarsar0/status/2026833569528644022",
  "text": "At this point, \"agentic engineering\" has allowed me to build the best AI harness I could possibly get my hands on. \n\nYes, I vibe coded it. That's right. You don't need to wait around for the features you need for your AI agents. Please don't. You could just build them yourself. \n\nFocusing on agentic engineering and building my own orchestrator over the past couple of months has allowed me to build with coding agents, unlike anything I have seen or experienced in the market.\n\nClaude Cowork was built in 10 days. I totally get it. Anyone can produce that level of output these days. I truly believe that. \n\nI look at the new IDEs, TUIs, orchestrator apps, and most of the new features they are releasing these days, I had access to them in my orchestrator months ago. And for unique features, I am able to reproduce them in a few hours and give them to my orchestrator. That is absolutely crazy! \n\nIt feels like I am building an entire operating system sometimes. It's a lot of fun. \n\nAnd I am not saying this to brag or to dismiss any of the AI solutions out there. There are some great ones out there.\n\nI share this to clarify that this is the kind of leverage Karpathy is alluding to. We are building and experiencing this at different levels, but it doesn't remove the fact that you can just build the best AI agent for whatever problem you want to solve. And you should be building it.",
  "source": "Twitter for iPhone",
  "retweetCount": 15,
  "replyCount": 15,
  "likeCount": 151,
  "quoteCount": 0,
  "viewCount": 24386,
  "createdAt": "Thu Feb 26 01:35:54 +0000 2026",
  "lang": "en",
  "bookmarkCount": 124,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2026833569528644022",
  "displayTextRange": [
    0,
    278
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "omarsar0",
    "url": "https://x.com/omarsar0",
    "twitterUrl": "https://twitter.com/omarsar0",
    "id": "3448284313",
    "name": "elvis",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/939313677647282181/vZjFWtAn_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/3448284313/1565974901",
    "description": "",
    "location": "DAIR.AI Academy",
    "followers": 291571,
    "following": 776,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Fri Sep 04 12:59:26 +0000 2015",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 34909,
    "hasCustomTimelines": true,
    "isTranslator": true,
    "mediaCount": 4525,
    "statusesCount": 17379,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2028103978190590118"
    ],
    "profile_bio": {
      "description": "Building @dair_ai • Prev: Meta AI, Elastic, PhD • New AI learning portal: https://t.co/1e8RZKs4uX",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [
            {
              "display_url": "academy.dair.ai",
              "expanded_url": "https://academy.dair.ai/",
              "indices": [
                74,
                97
              ],
              "url": "https://t.co/1e8RZKs4uX"
            }
          ],
          "user_mentions": [
            {
              "id_str": "0",
              "indices": [
                9,
                17
              ],
              "name": "",
              "screen_name": "dair_ai"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "dair.ai",
              "expanded_url": "https://www.dair.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/XQto5ypSIk"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {},
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [],
    "user_mentions": []
  },
  "quoted_tweet": {
    "type": "tweet",
    "id": "2026731645169185220",
    "url": "https://x.com/karpathy/status/2026731645169185220",
    "twitterUrl": "https://twitter.com/karpathy/status/2026731645169185220",
    "text": "It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the \"progress as usual\" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December and basically work since - the models have significantly higher quality, long-term coherence and tenacity and they can power through large and long tasks, well past enough that it is extremely disruptive to the default programming workflow.\n\nJust to give an example, over the weekend I was building a local video analysis dashboard for the cameras of my home so I wrote: “Here is the local IP and username/password of my DGX Spark. Log in, set up ssh keys, set up vLLM, download and bench Qwen3-VL, set up a server endpoint to inference videos, a basic web ui dashboard, test everything, set it up with systemd, record memory notes for yourself and write up a markdown report for me”. The agent went off for ~30 minutes, ran into multiple issues, researched solutions online, resolved them one by one, wrote the code, tested it, debugged it, set up the services, and came back with the report and it was just done. I didn’t touch anything. All of this could easily have been a weekend project just 3 months ago but today it’s something you kick off and forget about for 30 minutes.\n\nAs a result, programming is becoming unrecognizable. You’re not typing computer code into an editor like the way things were since computers were invented, that era is over. You're spinning up AI agents, giving them tasks *in English* and managing and reviewing their work in parallel. The biggest prize is in figuring out how you can keep ascending the layers of abstraction to set up long-running orchestrator Claws with all of the right tools, memory and instructions that productively manage multiple parallel Code instances for you. The leverage achievable via top tier \"agentic engineering\" feels very high right now.\n\nIt’s not perfect, it needs high-level direction, judgement, taste, oversight, iteration and hints and ideas. It works a lot better in some scenarios than others (e.g. especially for tasks that are well-specified and where you can verify/test functionality). The key is to build intuition to decompose the task just right to hand off the parts that work and help out around the edges. But imo, this is nowhere near \"business as usual\" time in software.",
    "source": "Twitter for iPhone",
    "retweetCount": 4684,
    "replyCount": 1474,
    "likeCount": 36646,
    "quoteCount": 1042,
    "viewCount": 4832702,
    "createdAt": "Wed Feb 25 18:50:53 +0000 2026",
    "lang": "en",
    "bookmarkCount": 20182,
    "isReply": false,
    "inReplyToId": null,
    "conversationId": "2026731645169185220",
    "displayTextRange": [
      0,
      279
    ],
    "inReplyToUserId": null,
    "inReplyToUsername": null,
    "author": {
      "type": "user",
      "userName": "karpathy",
      "url": "https://x.com/karpathy",
      "twitterUrl": "https://twitter.com/karpathy",
      "id": "33836629",
      "name": "Andrej Karpathy",
      "isVerified": false,
      "isBlueVerified": true,
      "verifiedType": null,
      "profilePicture": "https://pbs.twimg.com/profile_images/1296667294148382721/9Pr6XrPB_normal.jpg",
      "coverPicture": "https://pbs.twimg.com/profile_banners/33836629/1407117611",
      "description": "",
      "location": "Stanford",
      "followers": 1859286,
      "following": 1055,
      "status": "",
      "canDm": true,
      "canMediaTag": true,
      "createdAt": "Tue Apr 21 06:49:15 +0000 2009",
      "entities": {
        "description": {
          "urls": []
        },
        "url": {}
      },
      "fastFollowersCount": 0,
      "favouritesCount": 22148,
      "hasCustomTimelines": true,
      "isTranslator": false,
      "mediaCount": 851,
      "statusesCount": 9983,
      "withheldInCountries": [],
      "affiliatesHighlightedLabel": {},
      "possiblySensitive": false,
      "pinnedTweetIds": [
        "1617979122625712128"
      ],
      "profile_bio": {
        "description": "I like to train large deep neural nets. Previously Director of AI @ Tesla, founding team @ OpenAI, PhD @ Stanford.",
        "entities": {
          "description": {
            "hashtags": [],
            "symbols": [],
            "urls": [],
            "user_mentions": []
          },
          "url": {
            "urls": [
              {
                "display_url": "karpathy.ai",
                "expanded_url": "https://karpathy.ai",
                "indices": [
                  0,
                  23
                ],
                "url": "https://t.co/0EcFthjJXM"
              }
            ]
          }
        }
      },
      "isAutomated": false,
      "automatedBy": null
    },
    "extendedEntities": {},
    "card": null,
    "place": {},
    "entities": {
      "hashtags": [],
      "symbols": [],
      "urls": [],
      "user_mentions": []
    },
    "quoted_tweet": null,
    "retweeted_tweet": null,
    "isLimitedReply": false,
    "article": null
  },
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}