🐦 Twitter Post Details

Viewing enriched Twitter post

@omarsar0

Where the field is headed (agentic workflows with advanced tool/computer use) open-source code LLMs are going to be a big deal! Great to see this new effort, OpenCode, a fully open-source LLM specialized for code generation and understanding. Main factors for building high-performing code LLMs: - effective data cleaning with code-optimized heuristic rules for deduplication, - recall of relevant text corpus related to code - high-quality synthetic in both annealing and supervised fine-tuning stages OpenCoder surpasses previous fully open models at the 6B+ parameter scale and releases not just the model weights but also the complete training pipeline, datasets, and protocols to enable reproducible research.

Media 1
View on Twitter

📊 Media Metadata

{
  "data": [
    {
      "media_url": "https://pbs.twimg.com/media/Gcc3FmAXwAAgaOR.png",
      "type": "photo"
    }
  ],
  "score": 1.0,
  "scored_at": "2025-08-09T13:46:07.553471",
  "import_source": "network_archive_import",
  "media": [
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1857515355595526450/media_0.png?",
      "filename": "media_0.png"
    }
  ],
  "reprocessed_at": "2025-08-12T15:26:21.741079",
  "reprocessed_reason": "missing_media_array"
}

🔧 Raw API Response

{
  "user": {
    "created_at": "2015-09-04T12:59:26.000Z",
    "default_profile_image": false,
    "description": "Building with AI Agents @dair_ai • Prev: Meta AI, Elastic, Galactica LLM, PhD • I also teach how to build with LLMs, RAG & AI Agents ⬇️",
    "fast_followers_count": 0,
    "favourites_count": 27933,
    "followers_count": 216713,
    "friends_count": 532,
    "has_custom_timelines": true,
    "is_translator": false,
    "listed_count": 3688,
    "location": "",
    "media_count": 2656,
    "name": "elvis",
    "normal_followers_count": 216713,
    "possibly_sensitive": false,
    "profile_banner_url": "https://pbs.twimg.com/profile_banners/3448284313/1565974901",
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/939313677647282181/vZjFWtAn_normal.jpg",
    "screen_name": "omarsar0",
    "statuses_count": 12439,
    "translator_type": "regular",
    "url": "https://t.co/JBU5beHQNs",
    "verified": true,
    "withheld_in_countries": [],
    "id_str": "3448284313"
  },
  "id": "1857515355595526450",
  "conversation_id": "1857515355595526450",
  "full_text": "Where the field is headed (agentic workflows with advanced tool/computer use) open-source code LLMs are going to be a big deal!\n\nGreat to see this new effort, OpenCode, a fully open-source LLM specialized for code generation and understanding.\n\nMain factors for building high-performing code LLMs: \n\n- effective data cleaning with code-optimized heuristic rules for deduplication,\n- recall of relevant text corpus related to code\n- high-quality synthetic in both annealing and supervised fine-tuning stages\n\nOpenCoder surpasses previous fully open models at the 6B+ parameter scale and releases not just the model weights but also the complete training pipeline, datasets, and protocols to enable reproducible research.",
  "reply_count": 4,
  "retweet_count": 66,
  "favorite_count": 321,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [],
  "urls": [],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/Gcc3FmAXwAAgaOR.png",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/omarsar0/status/1857515355595526450",
  "created_at": "2024-11-15T20:05:46.000Z",
  "#sort_index": "1857515355595526450",
  "view_count": 23217,
  "quote_count": 0,
  "is_quote_tweet": false,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": true,
  "startUrl": "https://x.com/omarsar0/status/1857515355595526450"
}