🐦 Twitter Post Details

Viewing enriched Twitter post

@arankomatsuzaki

Retrieval meets Long Context Large Language Models Llama with 32K context using retrieval-augmentation at generation outperforms finetuned LLM with 32K context via positional interpolation, while taking much less computation https://t.co/VHWwpyagJD https://t.co/TvW8ZxwYmV

Media 1

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1709757107250078164/media_0.png",
      "type": "photo",
      "original_url": "https://pbs.twimg.com/media/F7pGZW7WcAAUQrB.png",
      "download_date": "2025-08-13T05:52:38.706172",
      "stored_in_supabase": true,
      "format_converted_from_list": true
    }
  ],
  "conversion_date": "2025-08-13T00:32:34.991008",
  "format_converted": true,
  "original_structure": "had_media_only"
}

🔧 Raw API Response

{
  "user": {
    "created_at": "2016-11-04T06:57:37.000Z",
    "default_profile_image": false,
    "description": "ML PhD @ GaTech, @TheDuckAI (https://t.co/TLZw9TIidr), EleutherAI, LAION",
    "fast_followers_count": 0,
    "favourites_count": 8669,
    "followers_count": 68235,
    "friends_count": 76,
    "has_custom_timelines": true,
    "is_translator": false,
    "listed_count": 998,
    "location": "",
    "media_count": 1472,
    "name": "Aran Komatsuzaki",
    "normal_followers_count": 68235,
    "possibly_sensitive": false,
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/1561220982328754176/JOYS5kab_normal.jpg",
    "screen_name": "arankomatsuzaki",
    "statuses_count": 3836,
    "translator_type": "none",
    "url": "https://t.co/aZGCShnLYq",
    "verified": false,
    "withheld_in_countries": [],
    "id_str": "794433401591693312"
  },
  "id": "1709757107250078164",
  "conversation_id": "1709757107250078164",
  "full_text": "Retrieval meets Long Context Large Language Models\n\nLlama with 32K context using retrieval-augmentation at generation outperforms finetuned LLM with 32K context via positional interpolation, while taking much less computation\n\nhttps://t.co/VHWwpyagJD https://t.co/TvW8ZxwYmV",
  "reply_count": 2,
  "retweet_count": 51,
  "favorite_count": 218,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [],
  "urls": [
    {
      "url": "https://t.co/VHWwpyagJD",
      "expanded_url": "https://arxiv.org/abs/2310.03025",
      "display_url": "arxiv.org/abs/2310.03025"
    }
  ],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/F7pGZW7WcAAUQrB.png",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/arankomatsuzaki/status/1709757107250078164",
  "created_at": "2023-10-05T02:27:14.000Z",
  "#sort_index": "1709757107250078164",
  "view_count": 25535,
  "quote_count": 3,
  "is_quote_tweet": false,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": false,
  "startUrl": "https://twitter.com/arankomatsuzaki/status/1709757107250078164"
}