🐦 Twitter Post Details

Viewing enriched Twitter post

@omarsar0

So much alpha in tuning/building LLM verifiers and judges. I use them on top of my harness, and it has unlocked agentic coding workflows that are beyond anything that exists in the market today. Building verifiers and LLM judges is starting to become a skill in high demand.

📊 Media Metadata

{
  "score": 0.36,
  "score_components": {
    "author": 0.09,
    "engagement": 0.0,
    "quality": 0.06000000000000001,
    "source": 0.135,
    "nlp": 0.05,
    "recency": 0.025
  },
  "scored_at": "2026-07-02T16:01:34.954523",
  "import_source": "api_import",
  "source_tagged_at": "2026-07-02T16:01:34.954533",
  "enriched": true,
  "enriched_at": "2026-07-02T16:01:34.954535"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2072710620261093436",
  "url": "https://x.com/omarsar0/status/2072710620261093436",
  "twitterUrl": "https://twitter.com/omarsar0/status/2072710620261093436",
  "text": "So much alpha in tuning/building LLM verifiers and judges. \n\nI use them on top of my harness, and it has unlocked agentic coding workflows that are beyond anything that exists in the market today.\n\nBuilding verifiers and LLM judges is starting to become a skill in high demand.",
  "source": "Twitter for iPhone",
  "retweetCount": 2,
  "replyCount": 4,
  "likeCount": 8,
  "quoteCount": 0,
  "viewCount": 1374,
  "createdAt": "Thu Jul 02 15:54:55 +0000 2026",
  "lang": "en",
  "bookmarkCount": 7,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2072710620261093436",
  "displayTextRange": [
    0,
    277
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "omarsar0",
    "url": "https://x.com/omarsar0",
    "twitterUrl": "https://twitter.com/omarsar0",
    "id": "3448284313",
    "name": "elvis",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/939313677647282181/vZjFWtAn_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/3448284313/1565974901",
    "description": "",
    "location": "DAIR.AI Academy",
    "followers": 309534,
    "following": 891,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Fri Sep 04 12:59:26 +0000 2015",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 37219,
    "hasCustomTimelines": true,
    "isTranslator": true,
    "mediaCount": 4760,
    "statusesCount": 18558,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2072430551446032847"
    ],
    "profile_bio": {
      "description": "Building self-improving AI @dair_ai • Prev: Meta AI | PhD • Learn about AI Agents for FREE here: https://t.co/P5SA9u54xO",
      "entities": {
        "description": {
          "urls": [
            {
              "display_url": "academy.dair.ai/courses/elemen…",
              "expanded_url": "https://academy.dair.ai/courses/elements-of-ai-agents",
              "indices": [
                97,
                120
              ],
              "url": "https://t.co/P5SA9u54xO"
            }
          ],
          "user_mentions": [
            {
              "id_str": "",
              "indices": [
                27,
                35
              ],
              "name": "",
              "screen_name": "dair_ai"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "dair.ai",
              "expanded_url": "https://www.dair.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/XQto5ypkSM"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {},
  "card": null,
  "place": {},
  "entities": {},
  "quoted_tweet": {
    "type": "tweet",
    "id": "2072050039317578236",
    "url": "https://x.com/miramurati/status/2072050039317578236",
    "twitterUrl": "https://twitter.com/miramurati/status/2072050039317578236",
    "text": "Bridgewater used their unique financial knowledge and partnered with us on @tinkerapi to fine-tune a model that helps their analysts focus on what's important. Experts improving AI that empowers experts.\nhttps://t.co/6RJITMG2BJ",
    "source": "Twitter for iPhone",
    "retweetCount": 136,
    "replyCount": 48,
    "likeCount": 2146,
    "quoteCount": 55,
    "viewCount": 480719,
    "createdAt": "Tue Jun 30 20:10:00 +0000 2026",
    "lang": "en",
    "bookmarkCount": 1460,
    "isReply": false,
    "inReplyToId": null,
    "conversationId": "2072050039317578236",
    "displayTextRange": [
      0,
      227
    ],
    "inReplyToUserId": null,
    "inReplyToUsername": null,
    "author": {
      "type": "user",
      "userName": "miramurati",
      "url": "https://x.com/miramurati",
      "twitterUrl": "https://twitter.com/miramurati",
      "id": "180115578",
      "name": "Mira Murati",
      "isVerified": false,
      "isBlueVerified": true,
      "verifiedType": null,
      "profilePicture": "https://pbs.twimg.com/profile_images/2057853902918455296/D_nfq15L_normal.jpg",
      "coverPicture": "https://pbs.twimg.com/profile_banners/180115578/1665340075",
      "description": "",
      "location": "San Francisco, CA",
      "followers": 716554,
      "following": 620,
      "status": "",
      "canDm": false,
      "canMediaTag": false,
      "createdAt": "Wed Aug 18 21:43:38 +0000 2010",
      "entities": {
        "description": {
          "urls": []
        },
        "url": {}
      },
      "fastFollowersCount": 0,
      "favouritesCount": 2103,
      "hasCustomTimelines": true,
      "isTranslator": false,
      "mediaCount": 8,
      "statusesCount": 366,
      "withheldInCountries": [],
      "affiliatesHighlightedLabel": {},
      "possiblySensitive": false,
      "pinnedTweetIds": [],
      "profile_bio": {
        "description": "Now building @thinkymachines. Previously CTO @OpenAI",
        "entities": {
          "description": {
            "user_mentions": [
              {
                "id_str": "",
                "indices": [
                  13,
                  28
                ],
                "name": "",
                "screen_name": "thinkymachines"
              },
              {
                "id_str": "",
                "indices": [
                  45,
                  52
                ],
                "name": "",
                "screen_name": "OpenAI"
              }
            ]
          }
        }
      },
      "isAutomated": false,
      "automatedBy": null
    },
    "extendedEntities": {},
    "card": {
      "binding_values": [
        {
          "key": "photo_image_full_size_large",
          "value": {
            "image_value": {
              "alt": "Learning to Replicate Expert Judgment in Financial Tasks",
              "height": 419,
              "url": "https://pbs.twimg.com/card_img/2072034052752973825/I343EzDx?format=png&name=800x419",
              "width": 800
            }
          }
        },
        {
          "key": "thumbnail_image",
          "value": {
            "image_value": {
              "alt": "Learning to Replicate Expert Judgment in Financial Tasks",
              "height": 147,
              "url": "https://pbs.twimg.com/card_img/2072034052752973825/I343EzDx?format=png&name=280x150",
              "width": 280
            }
          }
        },
        {
          "key": "description",
          "value": {
            "string_value": "With expert-labeled data and fine-tuning on Tinker, a custom model outperforms frontier LLMs on financial information-filtering tasks at a fraction of the cost."
          }
        },
        {
          "key": "domain",
          "value": {
            "string_value": "thinkingmachines.ai"
          }
        },
        {
          "key": "thumbnail_image_large",
          "value": {
            "image_value": {
              "alt": "Learning to Replicate Expert Judgment in Financial Tasks",
              "height": 315,
              "url": "https://pbs.twimg.com/card_img/2072034052752973825/I343EzDx?format=png&name=600x600",
              "width": 600
            }
          }
        },
        {
          "key": "summary_photo_image_small",
          "value": {
            "image_value": {
              "alt": "Learning to Replicate Expert Judgment in Financial Tasks",
              "height": 202,
              "url": "https://pbs.twimg.com/card_img/2072034052752973825/I343EzDx?format=png&name=386x202",
              "width": 386
            }
          }
        },
        {
          "key": "thumbnail_image_original",
          "value": {
            "image_value": {
              "alt": "Learning to Replicate Expert Judgment in Financial Tasks",
              "height": 858,
              "url": "https://pbs.twimg.com/card_img/2072034052752973825/I343EzDx?format=png&name=orig",
              "width": 1635
            }
          }
        },
        {
          "key": "photo_image_full_size_small",
          "value": {
            "image_value": {
              "alt": "Learning to Replicate Expert Judgment in Financial Tasks",
              "height": 202,
              "url": "https://pbs.twimg.com/card_img/2072034052752973825/I343EzDx?format=png&name=386x202",
              "width": 386
            }
          }
        },
        {
          "key": "summary_photo_image_large",
          "value": {
            "image_value": {
              "alt": "Learning to Replicate Expert Judgment in Financial Tasks",
              "height": 419,
              "url": "https://pbs.twimg.com/card_img/2072034052752973825/I343EzDx?format=png&name=800x419",
              "width": 800
            }
          }
        },
        {
          "key": "thumbnail_image_small",
          "value": {
            "image_value": {
              "alt": "Learning to Replicate Expert Judgment in Financial Tasks",
              "height": 76,
              "url": "https://pbs.twimg.com/card_img/2072034052752973825/I343EzDx?format=png&name=144x144",
              "width": 144
            }
          }
        },
        {
          "key": "thumbnail_image_x_large",
          "value": {
            "image_value": {
              "alt": "Learning to Replicate Expert Judgment in Financial Tasks",
              "height": 858,
              "url": "https://pbs.twimg.com/card_img/2072034052752973825/I343EzDx?format=png&name=2048x2048_2_exp",
              "width": 1635
            }
          }
        },
        {
          "key": "photo_image_full_size_original",
          "value": {
            "image_value": {
              "alt": "Learning to Replicate Expert Judgment in Financial Tasks",
              "height": 858,
              "url": "https://pbs.twimg.com/card_img/2072034052752973825/I343EzDx?format=png&name=orig",
              "width": 1635
            }
          }
        },
        {
          "key": "photo_image_full_size_alt_text",
          "value": {
            "string_value": "Learning to Replicate Expert Judgment in Financial Tasks"
          }
        },
        {
          "key": "vanity_url",
          "value": {
            "scribe_key": "vanity_url",
            "string_value": "thinkingmachines.ai"
          }
        },
        {
          "key": "photo_image_full_size",
          "value": {
            "image_value": {
              "alt": "Learning to Replicate Expert Judgment in Financial Tasks",
              "height": 314,
              "url": "https://pbs.twimg.com/card_img/2072034052752973825/I343EzDx?format=png&name=600x314",
              "width": 600
            }
          }
        },
        {
          "key": "summary_photo_image_alt_text",
          "value": {
            "string_value": "Learning to Replicate Expert Judgment in Financial Tasks"
          }
        },
        {
          "key": "thumbnail_image_color",
          "value": {
            "image_color_value": {
              "palette": [
                {
                  "percentage": 100,
                  "rgb": {
                    "blue": 240,
                    "green": 240,
                    "red": 240
                  }
                }
              ]
            }
          }
        },
        {
          "key": "title",
          "value": {
            "string_value": "Learning to Replicate Expert Judgment in Financial Tasks"
          }
        },
        {
          "key": "summary_photo_image_color",
          "value": {
            "image_color_value": {
              "palette": [
                {
                  "percentage": 100,
                  "rgb": {
                    "blue": 240,
                    "green": 240,
                    "red": 240
                  }
                }
              ]
            }
          }
        },
        {
          "key": "summary_photo_image_x_large",
          "value": {
            "image_value": {
              "alt": "Learning to Replicate Expert Judgment in Financial Tasks",
              "height": 858,
              "url": "https://pbs.twimg.com/card_img/2072034052752973825/I343EzDx?format=png&name=2048x2048_2_exp",
              "width": 1635
            }
          }
        },
        {
          "key": "summary_photo_image",
          "value": {
            "image_value": {
              "alt": "Learning to Replicate Expert Judgment in Financial Tasks",
              "height": 314,
              "url": "https://pbs.twimg.com/card_img/2072034052752973825/I343EzDx?format=png&name=600x314",
              "width": 600
            }
          }
        },
        {
          "key": "photo_image_full_size_color",
          "value": {
            "image_color_value": {
              "palette": [
                {
                  "percentage": 100,
                  "rgb": {
                    "blue": 240,
                    "green": 240,
                    "red": 240
                  }
                }
              ]
            }
          }
        },
        {
          "key": "photo_image_full_size_x_large",
          "value": {
            "image_value": {
              "alt": "Learning to Replicate Expert Judgment in Financial Tasks",
              "height": 858,
              "url": "https://pbs.twimg.com/card_img/2072034052752973825/I343EzDx?format=png&name=2048x2048_2_exp",
              "width": 1635
            }
          }
        },
        {
          "key": "card_url",
          "value": {
            "scribe_key": "card_url",
            "string_value": "https://t.co/6RJITMG2BJ"
          }
        },
        {
          "key": "summary_photo_image_original",
          "value": {
            "image_value": {
              "alt": "Learning to Replicate Expert Judgment in Financial Tasks",
              "height": 858,
              "url": "https://pbs.twimg.com/card_img/2072034052752973825/I343EzDx?format=png&name=orig",
              "width": 1635
            }
          }
        }
      ],
      "card_platform": {
        "platform": {
          "audience": {
            "name": "production"
          },
          "device": {
            "name": "iPhone",
            "version": "13"
          }
        }
      },
      "name": "summary_large_image",
      "url": "https://t.co/6RJITMG2BJ",
      "user_refs_results": []
    },
    "place": {},
    "entities": {
      "urls": [
        {
          "display_url": "thinkingmachines.ai/news/learning-…",
          "expanded_url": "https://thinkingmachines.ai/news/learning-to-replicate-expert-judgment-in-financial-tasks/",
          "indices": [
            204,
            227
          ],
          "url": "https://t.co/6RJITMG2BJ"
        }
      ],
      "user_mentions": [
        {
          "id_str": "2008226291535970305",
          "indices": [
            75,
            85
          ],
          "name": "Tinker",
          "screen_name": "tinkerapi"
        }
      ]
    },
    "quoted_tweet": null,
    "retweeted_tweet": null,
    "isLimitedReply": false,
    "communityInfo": null,
    "article": null
  },
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}