🐦 Twitter Post Details

Viewing enriched Twitter post

@RaiaHadsell

It's been about 20 years since I first started working on embeddings with Yann LeCun (siamese networks!), and I've been fascinated ever since. Gemini Embeddings 2 approaches the platonic ideal: native embedding of text, image, video, audio, and docs to a single space.

📊 Media Metadata

{
  "score": 0.38,
  "score_components": {
    "author": 0.09,
    "engagement": 0.0,
    "quality": 0.08000000000000002,
    "source": 0.135,
    "nlp": 0.05,
    "recency": 0.025
  },
  "scored_at": "2026-03-16T20:22:48.993503",
  "import_source": "api_import",
  "source_tagged_at": "2026-03-16T20:22:48.993515",
  "enriched": true,
  "enriched_at": "2026-03-16T20:22:48.993518"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2033599015556989392",
  "url": "https://x.com/RaiaHadsell/status/2033599015556989392",
  "twitterUrl": "https://twitter.com/RaiaHadsell/status/2033599015556989392",
  "text": "It's been about 20 years since I first started working on embeddings with Yann LeCun (siamese networks!), and I've been fascinated ever since. Gemini Embeddings 2 approaches the platonic ideal: native embedding of text, image, video, audio, and docs to a single space.",
  "source": "Twitter for iPhone",
  "retweetCount": 24,
  "replyCount": 6,
  "likeCount": 277,
  "quoteCount": 2,
  "viewCount": 25597,
  "createdAt": "Mon Mar 16 17:39:22 +0000 2026",
  "lang": "en",
  "bookmarkCount": 158,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2033599015556989392",
  "displayTextRange": [
    0,
    268
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "RaiaHadsell",
    "url": "https://x.com/RaiaHadsell",
    "twitterUrl": "https://twitter.com/RaiaHadsell",
    "id": "844953243931291648",
    "name": "raia hadsell",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/864431541652307968/GG8YPLzr_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/844953243931291648/1494926531",
    "description": "",
    "location": "London, England",
    "followers": 9935,
    "following": 259,
    "status": "",
    "canDm": false,
    "canMediaTag": true,
    "createdAt": "Thu Mar 23 16:45:26 +0000 2017",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 564,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 7,
    "statusesCount": 242,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "1899238174259372365"
    ],
    "profile_bio": {
      "description": "VP of Research @googledeepmind.",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [],
          "user_mentions": [
            {
              "id_str": "0",
              "indices": [
                15,
                30
              ],
              "name": "",
              "screen_name": "googledeepmind"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "raiahadsell.com",
              "expanded_url": "http://www.raiahadsell.com",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/6nnE0g9dpA"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {},
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "timestamps": [],
    "urls": [],
    "user_mentions": []
  },
  "quoted_tweet": {
    "type": "tweet",
    "id": "2031421162123870239",
    "url": "https://x.com/GoogleAIStudio/status/2031421162123870239",
    "twitterUrl": "https://twitter.com/GoogleAIStudio/status/2031421162123870239",
    "text": "https://t.co/mIXzM657cR",
    "source": "Twitter for iPhone",
    "retweetCount": 1302,
    "replyCount": 262,
    "likeCount": 11289,
    "quoteCount": 553,
    "viewCount": 4239567,
    "createdAt": "Tue Mar 10 17:25:21 +0000 2026",
    "lang": "zxx",
    "bookmarkCount": 9430,
    "isReply": false,
    "inReplyToId": null,
    "conversationId": "2031421162123870239",
    "displayTextRange": [
      0,
      23
    ],
    "inReplyToUserId": null,
    "inReplyToUsername": null,
    "author": {
      "type": "user",
      "userName": "GoogleAIStudio",
      "url": "https://x.com/GoogleAIStudio",
      "twitterUrl": "https://twitter.com/GoogleAIStudio",
      "id": "1742923424056713217",
      "name": "Google AI Studio",
      "isVerified": false,
      "isBlueVerified": false,
      "verifiedType": "Business",
      "profilePicture": "https://pbs.twimg.com/profile_images/1957558782067896323/6jXpPKD4_normal.png",
      "coverPicture": "https://pbs.twimg.com/profile_banners/1742923424056713217/1773068211",
      "description": "",
      "location": "It's time to build",
      "followers": 129860,
      "following": 2,
      "status": "",
      "canDm": true,
      "canMediaTag": true,
      "createdAt": "Thu Jan 04 14:58:26 +0000 2024",
      "entities": {
        "description": {
          "urls": []
        },
        "url": {}
      },
      "fastFollowersCount": 0,
      "favouritesCount": 155,
      "hasCustomTimelines": true,
      "isTranslator": false,
      "mediaCount": 42,
      "statusesCount": 96,
      "withheldInCountries": [],
      "affiliatesHighlightedLabel": {},
      "possiblySensitive": false,
      "pinnedTweetIds": [],
      "profile_bio": {
        "description": "The fastest path from prompt to prototype to production with Gemini",
        "entities": {
          "description": {
            "hashtags": [],
            "symbols": [],
            "urls": [],
            "user_mentions": []
          },
          "url": {
            "urls": [
              {
                "display_url": "ai.studio/build",
                "expanded_url": "https://ai.studio/build",
                "indices": [
                  0,
                  23
                ],
                "url": "https://t.co/dp8FrcqyIA"
              }
            ]
          }
        }
      },
      "isAutomated": false,
      "automatedBy": null
    },
    "extendedEntities": {},
    "card": null,
    "place": {},
    "entities": {
      "hashtags": [],
      "symbols": [],
      "timestamps": [],
      "urls": [
        {
          "display_url": "x.com/i/article/2031…",
          "expanded_url": "http://x.com/i/article/2031415977049731077",
          "indices": [
            0,
            23
          ],
          "url": "https://t.co/mIXzM657cR"
        }
      ],
      "user_mentions": []
    },
    "quoted_tweet": null,
    "retweeted_tweet": null,
    "isLimitedReply": false,
    "article": {
      "title": "Gemini Embedding 2: Our first natively multimodal embedding model",
      "preview_text": "Gemini Embedding 2 is our first natively multimodal embedding model that maps text, images, video, audio and documents into a single embedding space, enabling multimodal retrieval and classification",
      "cover_media_img_url": "https://pbs.twimg.com/media/HDEOl73a0AAqw4G.jpg"
    }
  },
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}