Viewing enriched Twitter post
A good discussion about evaluating LLMs in medicine by the head of Health AI at OpenAI, highly recommend reading. Appreciate the shoutout for Medmarks, our LLM evaluation suite developed at @SophontAI/@MedARC_AI. Glad to see even folks at frontier labs are finding it useful!
{
"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": "2026-03-13T23:45:45.814317",
"import_source": "api_import",
"source_tagged_at": "2026-03-13T23:45:45.814347",
"enriched": true,
"enriched_at": "2026-03-13T23:45:45.814350"
}{
"type": "tweet",
"id": "2032603896670285826",
"url": "https://x.com/iScienceLuvr/status/2032603896670285826",
"twitterUrl": "https://twitter.com/iScienceLuvr/status/2032603896670285826",
"text": "A good discussion about evaluating LLMs in medicine by the head of Health AI at OpenAI, highly recommend reading.\n\nAppreciate the shoutout for Medmarks, our LLM evaluation suite developed at @SophontAI/@MedARC_AI. Glad to see even folks at frontier labs are finding it useful!",
"source": "Twitter for iPhone",
"retweetCount": 0,
"replyCount": 0,
"likeCount": 0,
"quoteCount": 0,
"viewCount": 3,
"createdAt": "Fri Mar 13 23:45:07 +0000 2026",
"lang": "en",
"bookmarkCount": 1,
"isReply": false,
"inReplyToId": null,
"conversationId": "2032603896670285826",
"displayTextRange": [
0,
277
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "iScienceLuvr",
"url": "https://x.com/iScienceLuvr",
"twitterUrl": "https://twitter.com/iScienceLuvr",
"id": "441465751",
"name": "Tanishq Mathew Abraham, Ph.D.",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/2005802886622552064/4jiatr43_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/441465751/1738204246",
"description": "",
"location": "",
"followers": 86393,
"following": 1391,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Tue Dec 20 03:45:50 +0000 2011",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 118469,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 2738,
"statusesCount": 19603,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2019996902960288247"
],
"profile_bio": {
"description": "CEO @SophontAI |\nFounder @MedARC_AI |\nPhD at 19 (2023) |\nex Research Director Stability AI | \nBiomed. engineer @ 14 |\nTEDx talk➡https://t.co/xPxwKTpz0D",
"entities": {
"description": {
"hashtags": [],
"symbols": [],
"urls": [
{
"display_url": "bit.ly/3tpAuan",
"expanded_url": "https://bit.ly/3tpAuan",
"indices": [
128,
151
],
"url": "https://t.co/xPxwKTpz0D"
}
],
"user_mentions": [
{
"id_str": "0",
"indices": [
4,
14
],
"name": "",
"screen_name": "SophontAI"
},
{
"id_str": "0",
"indices": [
25,
35
],
"name": "",
"screen_name": "MedARC_AI"
}
]
},
"url": {
"urls": [
{
"display_url": "sophont.med",
"expanded_url": "https://sophont.med",
"indices": [
0,
23
],
"url": "https://t.co/MvROZZVu9I"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": [
{
"id_str": "1904091830142251008",
"indices": [
191,
201
],
"name": "Sophont",
"screen_name": "SophontAI"
},
{
"id_str": "1609864019929882625",
"indices": [
202,
212
],
"name": "MedARC",
"screen_name": "MedARC_AI"
}
]
},
"quoted_tweet": {
"type": "tweet",
"id": "2032574410692112555",
"url": "https://x.com/thekaransinghal/status/2032574410692112555",
"twitterUrl": "https://twitter.com/thekaransinghal/status/2032574410692112555",
"text": "https://t.co/sbZncI4gF9",
"source": "Twitter for iPhone",
"retweetCount": 12,
"replyCount": 4,
"likeCount": 59,
"quoteCount": 6,
"viewCount": 4684,
"createdAt": "Fri Mar 13 21:47:57 +0000 2026",
"lang": "zxx",
"bookmarkCount": 74,
"isReply": false,
"inReplyToId": null,
"conversationId": "2032574410692112555",
"displayTextRange": [
0,
23
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "thekaransinghal",
"url": "https://x.com/thekaransinghal",
"twitterUrl": "https://twitter.com/thekaransinghal",
"id": "14456589",
"name": "Karan Singhal",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1574418065642733568/lilstQIT_normal.jpg",
"coverPicture": "",
"description": "",
"location": "San Francisco, CA",
"followers": 7441,
"following": 298,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Mon Apr 21 00:31:43 +0000 2008",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 392,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 54,
"statusesCount": 211,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2010878203401843114"
],
"profile_bio": {
"description": "Health AI, AGI benefits, safety @OpenAI",
"entities": {
"description": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": [
{
"id_str": "0",
"indices": [
32,
39
],
"name": "",
"screen_name": "OpenAI"
}
]
},
"url": {
"urls": [
{
"display_url": "karansinghal.com",
"expanded_url": "https://karansinghal.com",
"indices": [
0,
23
],
"url": "https://t.co/ZCzHWQeW3N"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [
{
"display_url": "x.com/i/article/2032…",
"expanded_url": "http://x.com/i/article/2032568535038451712",
"indices": [
0,
23
],
"url": "https://t.co/sbZncI4gF9"
}
],
"user_mentions": []
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"article": {
"title": "How should AI systems be evaluated for health?",
"preview_text": "Almost every week, a new study comes out testing how LLMs perform in health scenarios. Some look at whether models can pass medical exams. Others test how they answer specific clinical questions or",
"cover_media_img_url": "https://pbs.twimg.com/media/HDUj0xNaMAIO9N9.jpg"
}
},
"retweeted_tweet": null,
"isLimitedReply": false,
"article": null
}