🐦 Twitter Post Details

Viewing enriched Twitter post

@slimcat0101

Double down on this. šŸ’Æ Take OCR and document parsing for instance. Running a giant monster model is pure overkill. 1/ Data > Model Size: A lightweight, fine-tuned VLM (or custom parsing model) fed with high-quality document data easily beats frontier giant LLMs in pixel-perfect structural extraction. 2/ The ROI Problem: Invoices, financial reports, and endless PDFs need high throughput. Good luck processing them at scale with hyper-expensive API bills or massive GPU clusters. 3/ Local & Edge: Edge deployment (even via llamacpp/ONNX) with zero data leak risks is what enterprises actually need.

šŸ“Š Media Metadata

{
  "score": 0.4,
  "score_components": {
    "author": 0.09,
    "engagement": 0.0,
    "quality": 0.1,
    "source": 0.135,
    "nlp": 0.05,
    "recency": 0.025
  },
  "scored_at": "2026-07-02T21:02:24.247416",
  "import_source": "api_import",
  "source_tagged_at": "2026-07-02T21:02:24.247427",
  "enriched": true,
  "enriched_at": "2026-07-02T21:02:24.247429"
}

šŸ”§ Raw API Response

{
  "type": "tweet",
  "id": "2072681862363832552",
  "url": "https://x.com/slimcat0101/status/2072681862363832552",
  "twitterUrl": "https://twitter.com/slimcat0101/status/2072681862363832552",
  "text": "Double down on this. šŸ’Æ\n\nTake OCR and document parsing for instance. Running a giant monster model is pure overkill.\n\n1/ Data > Model Size: A lightweight, fine-tuned VLM (or custom parsing model) fed with high-quality document data easily beats frontier giant LLMs in pixel-perfect structural extraction.\n\n2/ The ROI Problem: Invoices, financial reports, and endless PDFs need high throughput. Good luck processing them at scale with hyper-expensive API bills or massive GPU clusters.\n\n3/ Local & Edge: Edge deployment (even via llamacpp/ONNX) with zero data leak risks is what enterprises actually need.",
  "source": "Twitter for iPhone",
  "retweetCount": 3,
  "replyCount": 2,
  "likeCount": 8,
  "quoteCount": 0,
  "viewCount": 2833,
  "createdAt": "Thu Jul 02 14:00:39 +0000 2026",
  "lang": "en",
  "bookmarkCount": 5,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2072681862363832552",
  "displayTextRange": [
    0,
    269
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "slimcat0101",
    "url": "https://x.com/slimcat0101",
    "twitterUrl": "https://twitter.com/slimcat0101",
    "id": "1929934810887438336",
    "name": "Cheng Cui",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/2067191968795697152/3JgfpZYO_normal.jpg",
    "coverPicture": "",
    "description": "",
    "location": "Beijing, China",
    "followers": 179,
    "following": 56,
    "status": "",
    "canDm": false,
    "canMediaTag": true,
    "createdAt": "Tue Jun 03 16:15:03 +0000 2025",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 101,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 9,
    "statusesCount": 70,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [],
    "profile_bio": {
      "description": "Tech Lead @ PaddleOCR | Document AI & VLM Researcher.\n\nšŸ’” Making AI practical and scalable.",
      "entities": {
        "description": {}
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {},
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [],
    "user_mentions": []
  },
  "quoted_tweet": {
    "type": "tweet",
    "id": "2071951499660292496",
    "url": "https://x.com/ClementDelangue/status/2071951499660292496",
    "twitterUrl": "https://twitter.com/ClementDelangue/status/2071951499660292496",
    "text": "A study from @Stanford showed that 71.3% of chatgpt queries could be accurately answered by a local model. I suspect a major part of enterprise AI workloads could be run locally too for free (compared to the massive costs of frontier API cost). \n\nAlso, it reduces the risk of these workloads being taken away from you because you own the models instead of renting them - which sounds like a good idea these days haha.\n\nThat's why we're introducing the ability for everyone to filter AI models on @huggingface based on your local hardware. \n\nFor me, there are 800k+ public models that fit on my M5 24GB and that I can use easily thanks to llamacpp.\n\nLet's go local AI!",
    "source": "Twitter for iPhone",
    "retweetCount": 263,
    "replyCount": 183,
    "likeCount": 2009,
    "quoteCount": 82,
    "viewCount": 194363,
    "createdAt": "Tue Jun 30 13:38:27 +0000 2026",
    "lang": "en",
    "bookmarkCount": 767,
    "isReply": false,
    "inReplyToId": null,
    "conversationId": "2071951499660292496",
    "displayTextRange": [
      0,
      275
    ],
    "inReplyToUserId": null,
    "inReplyToUsername": null,
    "author": {
      "type": "user",
      "userName": "ClementDelangue",
      "url": "https://x.com/ClementDelangue",
      "twitterUrl": "https://twitter.com/ClementDelangue",
      "id": "186420551",
      "name": "clem šŸ¤—",
      "isVerified": false,
      "isBlueVerified": true,
      "verifiedType": null,
      "profilePicture": "https://pbs.twimg.com/profile_images/1100512198139498497/utHSJ4st_normal.png",
      "coverPicture": "https://pbs.twimg.com/profile_banners/186420551/1731168567",
      "description": "",
      "location": "Miami / New York / Paris",
      "followers": 430578,
      "following": 4881,
      "status": "",
      "canDm": true,
      "canMediaTag": true,
      "createdAt": "Fri Sep 03 12:25:12 +0000 2010",
      "entities": {
        "description": {
          "urls": []
        },
        "url": {}
      },
      "fastFollowersCount": 0,
      "favouritesCount": 8842,
      "hasCustomTimelines": true,
      "isTranslator": false,
      "mediaCount": 2947,
      "statusesCount": 30578,
      "withheldInCountries": [],
      "affiliatesHighlightedLabel": {},
      "possiblySensitive": false,
      "pinnedTweetIds": [
        "2039695447506210905"
      ],
      "profile_bio": {
        "description": "Co-founder & CEO @HuggingFace šŸ¤—, the open and collaborative platform for AI builders",
        "entities": {
          "description": {
            "user_mentions": [
              {
                "id_str": "",
                "indices": [
                  17,
                  29
                ],
                "name": "",
                "screen_name": "HuggingFace"
              }
            ]
          },
          "url": {
            "urls": [
              {
                "display_url": "huggingface.co/clem",
                "expanded_url": "http://huggingface.co/clem",
                "indices": [
                  0,
                  23
                ],
                "url": "https://t.co/7OMlqfI2Rh"
              }
            ]
          }
        }
      },
      "isAutomated": false,
      "automatedBy": null
    },
    "extendedEntities": {
      "media": [
        {
          "display_url": "pic.twitter.com/V7cv7lWXFV",
          "expanded_url": "https://twitter.com/ClementDelangue/status/2071951499660292496/photo/1",
          "ext_master_playlist_only": [],
          "ext_media_availability": {
            "status": "Available"
          },
          "ext_playlists": [],
          "features": {
            "large": {
              "faces": [
                {
                  "h": 47,
                  "w": 47,
                  "x": 987,
                  "y": 347
                }
              ]
            },
            "orig": {
              "faces": [
                {
                  "h": 47,
                  "w": 47,
                  "x": 987,
                  "y": 347
                }
              ]
            }
          },
          "id_str": "2071950848242970624",
          "indices": [
            276,
            299
          ],
          "media_key": "3_2071950848242970624",
          "media_results": {
            "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARzBDFGdl3AACgACHMEM6UkW8ZAAAA==",
            "result": {
              "__typename": "ApiMedia",
              "id": "QXBpTWVkaWE6DAABCgABHMEMUZ2XcAAKAAIcwQzpSRbxkAAA",
              "media_key": "3_2071950848242970624"
            }
          },
          "media_url_https": "https://pbs.twimg.com/media/HMEMUZ2XcAA__bS.jpg",
          "original_info": {
            "focus_rects": [
              {
                "h": 683,
                "w": 1220,
                "x": 0,
                "y": 457
              },
              {
                "h": 1140,
                "w": 1140,
                "x": 0,
                "y": 0
              },
              {
                "h": 1140,
                "w": 1000,
                "x": 0,
                "y": 0
              },
              {
                "h": 1140,
                "w": 570,
                "x": 0,
                "y": 0
              },
              {
                "h": 1140,
                "w": 1220,
                "x": 0,
                "y": 0
              }
            ],
            "height": 1140,
            "width": 1220
          },
          "sizes": {
            "large": {
              "h": 1140,
              "w": 1220
            }
          },
          "type": "photo",
          "url": "https://t.co/V7cv7lWXFV"
        }
      ]
    },
    "card": null,
    "place": {},
    "entities": {
      "hashtags": [],
      "symbols": [],
      "urls": [],
      "user_mentions": [
        {
          "id_str": "18036441",
          "indices": [
            13,
            22
          ],
          "name": "Stanford University",
          "screen_name": "Stanford"
        },
        {
          "id_str": "778764142412984320",
          "indices": [
            496,
            508
          ],
          "name": "Hugging Face",
          "screen_name": "huggingface"
        }
      ]
    },
    "quoted_tweet": null,
    "retweeted_tweet": null,
    "isLimitedReply": false,
    "communityInfo": null,
    "article": null
  },
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}