🐦 Twitter Post Details

Viewing enriched Twitter post

@HamelHusain

People are misunderstanding her. It’s important to remember that a variant of semantic search is still happening 1. User writes a query 2. You send that query to a LLM with semantic understanding that knows what other tokens in latent space are similar to the query 3. LLM decides to rewrite query as traditional search, Grep, regex and expand the hell out of keywords based on semantica It’s all about tradeoffs: the order of operations very much depends on the goal and sometimes a different path is optimal 1. Sometimes (Often) you want to do hybrid search 2. Sometimes you want to to show a model interleaved results and have it do multiple rounds of search if it’s truly exploratory 3. Some domains need semantic search way more than others But don’t read into blanket statements on Twitter that X is dead. When you see this it just means “We aren’t using X in our specific situation because of out tradeoffs”

📊 Media Metadata

{
  "score": 0.42,
  "score_components": {
    "author": 0.09,
    "engagement": 0.0,
    "quality": 0.12,
    "source": 0.135,
    "nlp": 0.05,
    "recency": 0.025
  },
  "scored_at": "2026-03-06T07:19:08.392255",
  "import_source": "api_import",
  "source_tagged_at": "2026-03-06T07:19:08.392269",
  "enriched": true,
  "enriched_at": "2026-03-06T07:19:08.392273"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2029713829882646848",
  "url": "https://x.com/HamelHusain/status/2029713829882646848",
  "twitterUrl": "https://twitter.com/HamelHusain/status/2029713829882646848",
  "text": "People are misunderstanding her. \n\nIt’s important to remember that a variant of semantic search is still happening \n\n1. User writes a query \n2. You send that query to a LLM with semantic understanding that knows what other tokens in latent space are similar to the query \n3. LLM decides to rewrite query as traditional search, Grep, regex and expand the hell out of keywords based on semantica\n\nIt’s all about tradeoffs: the order of  operations very much depends on the goal and sometimes a different path is optimal\n\n1. Sometimes (Often) you want to do hybrid search \n2. Sometimes you want to to show a model interleaved results and have it do multiple rounds of search if it’s truly exploratory \n3. Some domains need semantic search way more than others \n\nBut don’t read into blanket statements on Twitter that X is dead.  When you see this it just means \n\n“We aren’t using X in our specific situation because of out tradeoffs”",
  "source": "Twitter for iPhone",
  "retweetCount": 3,
  "replyCount": 9,
  "likeCount": 87,
  "quoteCount": 1,
  "viewCount": 13087,
  "createdAt": "Fri Mar 06 00:21:01 +0000 2026",
  "lang": "en",
  "bookmarkCount": 77,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2029713829882646848",
  "displayTextRange": [
    0,
    278
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "HamelHusain",
    "url": "https://x.com/HamelHusain",
    "twitterUrl": "https://twitter.com/HamelHusain",
    "id": "825766640",
    "name": "Hamel Husain",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1287206199088173057/ixE4fKy1_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/825766640/1758993452",
    "description": "",
    "location": "Looking at the data",
    "followers": 43910,
    "following": 2433,
    "status": "",
    "canDm": true,
    "canMediaTag": false,
    "createdAt": "Sat Sep 15 18:45:02 +0000 2012",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 17276,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 1530,
    "statusesCount": 16111,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "1998452926935695649"
    ],
    "profile_bio": {
      "description": "Bringing data science back to AI -  https://t.co/Zrmp6LRd9c\n\nAbout Me: https://t.co/P6WyeKkyTa",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [
            {
              "display_url": "evals.info",
              "expanded_url": "http://evals.info",
              "indices": [
                36,
                59
              ],
              "url": "https://t.co/Zrmp6LRd9c"
            },
            {
              "display_url": "hamel.dev",
              "expanded_url": "https://hamel.dev",
              "indices": [
                71,
                94
              ],
              "url": "https://t.co/P6WyeKkyTa"
            }
          ],
          "user_mentions": []
        },
        "url": {
          "urls": [
            {
              "display_url": "evals.info",
              "expanded_url": "http://evals.info",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/Zrmp6LRd9c"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {},
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [],
    "user_mentions": []
  },
  "quoted_tweet": {
    "type": "tweet",
    "id": "2029319888003842117",
    "url": "https://x.com/hahnbeelee/status/2029319888003842117",
    "twitterUrl": "https://twitter.com/hahnbeelee/status/2029319888003842117",
    "text": "semantic search is dead. file-based context retrieval is far better.\n\nlet us know what you think and if there's more you want to see from our AI assistant",
    "source": "Twitter for iPhone",
    "retweetCount": 3,
    "replyCount": 23,
    "likeCount": 171,
    "quoteCount": 4,
    "viewCount": 65427,
    "createdAt": "Wed Mar 04 22:15:38 +0000 2026",
    "lang": "en",
    "bookmarkCount": 140,
    "isReply": false,
    "inReplyToId": null,
    "conversationId": "2029319888003842117",
    "displayTextRange": [
      0,
      154
    ],
    "inReplyToUserId": null,
    "inReplyToUsername": null,
    "author": {
      "type": "user",
      "userName": "hahnbeelee",
      "url": "https://x.com/hahnbeelee",
      "twitterUrl": "https://twitter.com/hahnbeelee",
      "id": "1347828010850910208",
      "name": "Hahnbee Lee",
      "isVerified": false,
      "isBlueVerified": true,
      "verifiedType": null,
      "profilePicture": "https://pbs.twimg.com/profile_images/1962278056581877760/GO5FqXcM_normal.jpg",
      "coverPicture": "https://pbs.twimg.com/profile_banners/1347828010850910208/1610328002",
      "description": "",
      "location": "San Francisco, CA",
      "followers": 7425,
      "following": 921,
      "status": "",
      "canDm": true,
      "canMediaTag": true,
      "createdAt": "Sat Jan 09 08:50:22 +0000 2021",
      "entities": {
        "description": {
          "urls": []
        },
        "url": {}
      },
      "fastFollowersCount": 0,
      "favouritesCount": 22783,
      "hasCustomTimelines": true,
      "isTranslator": false,
      "mediaCount": 291,
      "statusesCount": 1889,
      "withheldInCountries": [],
      "affiliatesHighlightedLabel": {},
      "possiblySensitive": false,
      "pinnedTweetIds": [
        "2029319888003842117"
      ],
      "profile_bio": {
        "description": "co-founder @mintlify",
        "entities": {
          "description": {
            "hashtags": [],
            "symbols": [],
            "urls": [],
            "user_mentions": [
              {
                "id_str": "0",
                "indices": [
                  11,
                  20
                ],
                "name": "",
                "screen_name": "mintlify"
              }
            ]
          },
          "url": {
            "urls": [
              {
                "display_url": "mintlify.com/careers",
                "expanded_url": "http://mintlify.com/careers",
                "indices": [
                  0,
                  23
                ],
                "url": "https://t.co/dKuDSfw1dT"
              }
            ]
          }
        }
      },
      "isAutomated": false,
      "automatedBy": null
    },
    "extendedEntities": {},
    "card": null,
    "place": {},
    "entities": {
      "hashtags": [],
      "symbols": [],
      "timestamps": [],
      "urls": [],
      "user_mentions": []
    },
    "quoted_tweet": {
      "type": "tweet",
      "id": "2029316990746411376",
      "url": "",
      "twitterUrl": "",
      "text": "",
      "source": "Twitter for iPhone",
      "retweetCount": 0,
      "replyCount": 0,
      "likeCount": 0,
      "quoteCount": 0,
      "viewCount": 0,
      "createdAt": "",
      "lang": "",
      "bookmarkCount": 0,
      "isReply": false,
      "inReplyToId": null,
      "conversationId": "",
      "displayTextRange": [],
      "inReplyToUserId": null,
      "inReplyToUsername": null,
      "author": {},
      "extendedEntities": {},
      "card": null,
      "place": {},
      "entities": {},
      "quoted_tweet": null,
      "retweeted_tweet": null,
      "isLimitedReply": false,
      "article": null
    },
    "retweeted_tweet": null,
    "isLimitedReply": false,
    "article": null
  },
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}