{
  "type": "tweet",
  "id": "2115531348161028374",
  "url": "https://x.com/tri_dao/status/2115531348161028374",
  "twitterUrl": "https://twitter.com/tri_dao/status/2115531348161028374",
  "text": "Super interesting result: H-Net learns to dynamically tokenize variable names in coding data as separate tokens, and it scales much better on code compared to BPE",
  "source": "",
  "retweetCount": 9,
  "replyCount": 9,
  "likeCount": 179,
  "quoteCount": 1,
  "viewCount": 7090,
  "createdAt": "Wed Oct 28 19:49:12 +0000 2026",
  "lang": "en",
  "bookmarkCount": 61,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2115531348161028374",
  "displayTextRange": [
    0,
    162
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "tri_dao",
    "url": "https://x.com/tri_dao",
    "twitterUrl": "https://twitter.com/tri_dao",
    "id": "568879807",
    "name": "Tri Dao",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1389486324516671496/owa9Z4AC_normal.jpg",
    "coverPicture": "",
    "description": "",
    "location": "Stanford, CA",
    "followers": 46064,
    "following": 672,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Wed May 02 07:13:50 +0000 2012",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 1767,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 59,
    "statusesCount": 1008,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "1811453622070444071"
    ],
    "profile_bio": {
      "description": "Asst. Prof @PrincetonCS, Chief Scientist @togethercompute. Machine learning & systems.",
      "entities": {
        "description": {
          "user_mentions": [
            {
              "id_str": "",
              "indices": [
                11,
                23
              ],
              "name": "",
              "screen_name": "PrincetonCS"
            },
            {
              "id_str": "",
              "indices": [
                41,
                57
              ],
              "name": "",
              "screen_name": "togethercompute"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "tridao.me",
              "expanded_url": "https://tridao.me",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/uFTGOmLPGP"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null,
    "protected": false
  },
  "extendedEntities": {},
  "card": null,
  "place": {},
  "entities": {},
  "quoted_tweet": {
    "type": "tweet",
    "id": "2115502110578290900",
    "url": "https://x.com/_albertgu/status/2115502110578290900",
    "twitterUrl": "https://twitter.com/_albertgu/status/2115502110578290900",
    "text": "I've always believed that intelligence should come from simple, general building blocks that learn their own abstractions directly from raw data; in other words, the bitter lesson. I think we're finally seeing a real step towards AI that can learn from all data.\n\nLanguage modeling on raw bytes is a microcosm of this ideal, and to me it's a central problem in AI: if we can't build LLMs that learn end-to-end from bytes, how will we handle the rest of the world's data that we understand even less?\n\nLast year we introduced hierarchical networks (H-Nets) as a first step. Our new version finds up to 3-5x efficiency gains in controlled scaling law experiments, and at larger scale matches an open-source model trained on 11T tokens with ~10x less data and compute. The posts below walk through what we found and why we think it works.",
    "source": "",
    "retweetCount": 299,
    "replyCount": 109,
    "likeCount": 2900,
    "quoteCount": 129,
    "viewCount": 246677,
    "createdAt": "Wed Oct 28 17:53:01 +0000 2026",
    "lang": "en",
    "bookmarkCount": 2345,
    "isReply": false,
    "inReplyToId": null,
    "conversationId": "2115502110578290900",
    "displayTextRange": [
      0,
      272
    ],
    "inReplyToUserId": null,
    "inReplyToUsername": null,
    "author": {
      "type": "user",
      "userName": "_albertgu",
      "url": "https://x.com/_albertgu",
      "twitterUrl": "https://twitter.com/_albertgu",
      "id": "1076265378118959104",
      "name": "Albert Gu",
      "isVerified": false,
      "isBlueVerified": true,
      "verifiedType": null,
      "profilePicture": "https://pbs.twimg.com/profile_images/2011884912593551360/voG84B15_normal.jpg",
      "coverPicture": "",
      "description": "",
      "location": "",
      "followers": 23331,
      "following": 78,
      "status": "",
      "canDm": true,
      "canMediaTag": true,
      "createdAt": "Fri Dec 21 23:57:16 +0000 2018",
      "entities": {
        "description": {
          "urls": []
        },
        "url": {}
      },
      "fastFollowersCount": 0,
      "favouritesCount": 3550,
      "hasCustomTimelines": true,
      "isTranslator": false,
      "mediaCount": 62,
      "statusesCount": 629,
      "withheldInCountries": [],
      "affiliatesHighlightedLabel": {
        "label": {
          "badge": {
            "url": "https://pbs.twimg.com/profile_images/2059814192769830912/AlZscu52_bigger.jpg"
          },
          "description": "Cartesia",
          "url": {
            "url": "https://twitter.com/cartesia",
            "url_type": "DeepLink"
          },
          "user_label_display_type": "Badge",
          "user_label_type": "BusinessLabel"
        }
      },
      "possiblySensitive": false,
      "pinnedTweetIds": [
        "2115502110578290900"
      ],
      "profile_bio": {
        "description": "assistant prof @mldcmu. chief scientist @cartesia. leading the ssm revolution.",
        "entities": {
          "description": {
            "user_mentions": [
              {
                "id_str": "",
                "indices": [
                  15,
                  22
                ],
                "name": "",
                "screen_name": "mldcmu"
              },
              {
                "id_str": "",
                "indices": [
                  40,
                  49
                ],
                "name": "",
                "screen_name": "cartesia"
              }
            ]
          }
        }
      },
      "isAutomated": false,
      "automatedBy": null,
      "protected": false
    },
    "extendedEntities": {
      "media": [
        {
          "additional_media_info": {
            "monetizable": false
          },
          "allow_download_status": {},
          "display_url": "pic.x.com/aEUoLCTPB3",
          "expanded_url": "https://x.com/_albertgu/status/2115502110578290900/video/1",
          "ext_master_playlist_only": [],
          "ext_media_availability": {
            "status": "Available"
          },
          "ext_playlists": [],
          "id_str": "2115501577012461568",
          "indices": [
            273,
            296
          ],
          "media_key": "13_2115501577012461568",
          "media_results": {
            "id": "QXBpTWVkaWFSZXN1bHRzOgwABAoAAR1bxXnTm0AAAAA=",
            "result": {
              "__typename": "ApiMedia",
              "id": "QXBpTWVkaWE6DAAECgABHVvFedObQAAAAA==",
              "media_key": "13_2115501577012461568"
            }
          },
          "media_url_https": "https://pbs.twimg.com/media/HVvH33RaQAE6DlQ.jpg",
          "original_info": {
            "focus_rects": [],
            "height": 1080,
            "width": 1920
          },
          "sizes": {
            "large": {
              "h": 1080,
              "w": 1920
            }
          },
          "type": "video",
          "url": "https://t.co/aEUoLCTPB3",
          "video_info": {
            "aspect_ratio": [
              16,
              9
            ],
            "duration_millis": 78912,
            "variants": [
              {
                "content_type": "application/x-mpegURL",
                "url": "https://video-s.twimg.com/amplify_video/2115501577012461568/pl/W6wjNNAgbONoqJpr.m3u8?tag=29&v=bf4"
              },
              {
                "bitrate": 256000,
                "content_type": "video/mp4",
                "url": "https://video-s.twimg.com/amplify_video/2115501577012461568/vid/avc1/480x270/Xnh8jW3qGz3z06Sc.mp4?tag=29"
              },
              {
                "bitrate": 832000,
                "content_type": "video/mp4",
                "url": "https://video-s.twimg.com/amplify_video/2115501577012461568/vid/avc1/640x360/tpviwSUqqflv7aab.mp4?tag=29"
              },
              {
                "bitrate": 2176000,
                "content_type": "video/mp4",
                "url": "https://video-s.twimg.com/amplify_video/2115501577012461568/vid/avc1/1280x720/zeatz9JaTYGqZ0H2.mp4?tag=29"
              },
              {
                "bitrate": 10368000,
                "content_type": "video/mp4",
                "url": "https://video-s.twimg.com/amplify_video/2115501577012461568/vid/avc1/1920x1080/Yjs4MoGlnchqw209.mp4?tag=29"
              }
            ]
          }
        }
      ]
    },
    "card": null,
    "place": {},
    "entities": {
      "hashtags": [],
      "symbols": [],
      "timestamps": [],
      "urls": [],
      "user_mentions": []
    },
    "quoted_tweet": null,
    "retweeted_tweet": null,
    "isLimitedReply": false,
    "communityInfo": null,
    "article": null
  },
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}