{
  "user": {
    "created_at": "2011-09-07T22:54:31.000Z",
    "default_profile_image": false,
    "description": "co-founder/CEO @llama_index\n\nCareers: https://t.co/EUnMNmbCtx\nEnterprise: https://t.co/Ht5jwxSrQB",
    "fast_followers_count": 0,
    "favourites_count": 7173,
    "followers_count": 54390,
    "friends_count": 1364,
    "has_custom_timelines": true,
    "is_translator": false,
    "listed_count": 1136,
    "location": "",
    "media_count": 1063,
    "name": "Jerry Liu",
    "normal_followers_count": 54390,
    "possibly_sensitive": false,
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/1283610285031460864/1Q4zYhtb_normal.jpg",
    "screen_name": "jerryjliu0",
    "statuses_count": 5321,
    "translator_type": "none",
    "url": "https://t.co/YiIfjVlzb6",
    "verified": true,
    "withheld_in_countries": [],
    "id_str": "369777416"
  },
  "id": "1865933308158464259",
  "conversation_id": "1865933308158464259",
  "full_text": "Agentless is a great example of how a more constrained agent is better than a general agent for specific tasks 💡 - it achieves much higher scores on SWE-Bench Lite for bug-fixing than other agent approaches 🛠️ \n\nThe whole point is to not let the agent do everything, but to do a specific set of things in sequence.\n\nI thought the points on why a general agent is worse given the current state of LLMs were interesting: \n\n1. Tool interface design is still really complicated for a general agent to learn how to use it\n2. Agents are not great at exploring a large set of tools \n3. Agent loops aren't great at self-reflection\n\nS/o @steven_xia_ for the paper \n\nRepo: https://t.co/XzJ5oE0jhz\nPaper: https://t.co/rJj9CBXeDd",
  "reply_count": 2,
  "retweet_count": 46,
  "favorite_count": 206,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [],
  "urls": [],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/GeUfh2QaUAA3emx.jpg",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/jerryjliu0/status/1865933308158464259",
  "created_at": "2024-12-09T01:35:42.000Z",
  "#sort_index": "1865933308158464259",
  "view_count": 25183,
  "quote_count": 1,
  "is_quote_tweet": true,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": true,
  "quoted_tweet": {
    "user": {
      "created_at": "2022-12-18T00:52:44.000Z",
      "default_profile_image": false,
      "description": "Build LLM agents over your data\n\nGithub: https://t.co/HC19j7vMwc\nDocs: https://t.co/QInqg2zksh\nDiscord: https://t.co/3ktq3zzYII",
      "fast_followers_count": 0,
      "favourites_count": 1261,
      "followers_count": 82614,
      "friends_count": 26,
      "has_custom_timelines": false,
      "is_translator": false,
      "listed_count": 1366,
      "location": "",
      "media_count": 1375,
      "name": "LlamaIndex 🦙",
      "normal_followers_count": 82614,
      "possibly_sensitive": false,
      "profile_banner_url": "https://pbs.twimg.com/profile_banners/1604278358296055808/1696908553",
      "profile_image_url_https": "https://pbs.twimg.com/profile_images/1623505166996742144/n-PNQGgd_normal.jpg",
      "screen_name": "llama_index",
      "statuses_count": 2997,
      "translator_type": "none",
      "url": "https://t.co/epzefqQqZx",
      "verified": true,
      "withheld_in_countries": [],
      "id_str": "1604278358296055808"
    },
    "id": "1865822785119174857",
    "conversation_id": "1865822785119174857",
    "full_text": "Today we’re featuring Agentless - an agentless approach to automatically resolving software development issues 🧑‍💻\n\nIn contrast with complex autonomous agent approaches (e.g. Devin), Agentless proposes a simple three step approach for solve issues: localization, repair, and patch validation. Importantly, it doesn’t allow LLMs to autonomously decide future actions.\n\nAs a result it achieves the highest performance with lowest cost on SWE-Bench Lite 💫\n\nIt’s a great example of how sometimes a more constrained LLM workflow can do better at domain-specific tasks. Uses @llama_index for embedding-based retrieval.\n\nBy @steven_xia_ et al. - check out paper below.\n\nRepo: https://t.co/Zb2CxE3mOZ\nPaper: https://t.co/WXiTE6Xw8s",
    "reply_count": 7,
    "retweet_count": 50,
    "favorite_count": 230,
    "hashtags": [],
    "symbols": [],
    "user_mentions": [],
    "urls": [],
    "media": [
      {
        "media_url": "https://pbs.twimg.com/media/GeS76XwbMAAnc7k.jpg",
        "type": "photo"
      }
    ],
    "url": "https://twitter.com/llama_index/status/1865822785119174857",
    "created_at": "2024-12-08T18:16:31.000Z",
    "#sort_index": "1865933308158464300",
    "view_count": 40596,
    "quote_count": 5,
    "is_quote_tweet": false,
    "is_retweet": false,
    "is_pinned": false,
    "is_truncated": true
  },
  "startUrl": "https://x.com/jerryjliu0/status/1865933308158464259"
}