@yawnxyz
this is a great read for those working on "really hard to eval" stuff like science
Viewing enriched Twitter post
this is a great read for those working on "really hard to eval" stuff like science
{
"score": 0.3,
"score_components": {
"author": 0.09,
"engagement": 0.0,
"quality": 0.0,
"source": 0.135,
"nlp": 0.05,
"recency": 0.025
},
"scored_at": "2026-07-01T21:02:24.482218",
"import_source": "api_import",
"source_tagged_at": "2026-07-01T21:02:24.482229",
"enriched": true,
"enriched_at": "2026-07-01T21:02:24.482231"
} {
"type": "tweet",
"id": "2072423345866580233",
"url": "https://x.com/yawnxyz/status/2072423345866580233",
"twitterUrl": "https://twitter.com/yawnxyz/status/2072423345866580233",
"text": "this is a great read for those working on \"really hard to eval\" stuff like science",
"source": "Twitter for iPhone",
"retweetCount": 1,
"replyCount": 1,
"likeCount": 1,
"quoteCount": 0,
"viewCount": 165,
"createdAt": "Wed Jul 01 20:53:24 +0000 2026",
"lang": "en",
"bookmarkCount": 1,
"isReply": false,
"inReplyToId": null,
"conversationId": "2072423345866580233",
"displayTextRange": [
0,
82
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "yawnxyz",
"url": "https://x.com/yawnxyz",
"twitterUrl": "https://twitter.com/yawnxyz",
"id": "1022157402014195712",
"name": "Jan",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1768502415496732672/0lg2qmv8_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1022157402014195712/1719901783",
"description": "",
"location": "agent land",
"followers": 3214,
"following": 4921,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Wed Jul 25 16:31:30 +0000 2018",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 26382,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 425,
"statusesCount": 6957,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1817249422360842691"
],
"profile_bio": {
"description": "ai insecurity researcher @nvidia digital bio • ex @WestmeadInst @phagedirectory @groqinc @carnegiemellon • designed in sweden, made in china • opinions = own",
"entities": {
"description": {
"user_mentions": [
{
"id_str": "",
"indices": [
25,
32
],
"name": "",
"screen_name": "nvidia"
},
{
"id_str": "",
"indices": [
50,
63
],
"name": "",
"screen_name": "WestmeadInst"
},
{
"id_str": "",
"indices": [
64,
79
],
"name": "",
"screen_name": "phagedirectory"
},
{
"id_str": "",
"indices": [
80,
88
],
"name": "",
"screen_name": "groqinc"
},
{
"id_str": "",
"indices": [
89,
104
],
"name": "",
"screen_name": "carnegiemellon"
}
]
},
"url": {
"urls": [
{
"display_url": "janzheng.com",
"expanded_url": "https://janzheng.com",
"indices": [
0,
23
],
"url": "https://t.co/wGZnbRHU6X"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {},
"quoted_tweet": {
"type": "tweet",
"id": "2071710766663979322",
"url": "https://x.com/HamelHusain/status/2071710766663979322",
"twitterUrl": "https://twitter.com/HamelHusain/status/2071710766663979322",
"text": "New blog post: “It’s Hard to Eval” Is a Product Smell\n\nIf you find it hard to verify AI output, chances are that your users will too! In other words, I often find that product design is the bottleneck\n\nIn the post I embed three **interactive before/after examples** based on products I've helped with:\n\n1. an AI data agent that answers business questions\n2. a PE lesson‑plan generator for K‑12 teachers\n3. a workers’ comp tool that drafts 50‑page medical reports\n\nI believe this is a significant issue in AI Engineering and upstream of evals! \n\nLink to post: https://t.co/ErA9dp4ZPw\n\nNote: I'm not a designer so the design sketches are far from perfect, but I felt it was important enough to spend a significant amount of time on this. \n\nThanks to @sh_reya and @isaac_flath for feedback.",
"source": "Twitter for iPhone",
"retweetCount": 22,
"replyCount": 14,
"likeCount": 179,
"quoteCount": 6,
"viewCount": 31190,
"createdAt": "Mon Jun 29 21:41:51 +0000 2026",
"lang": "en",
"bookmarkCount": 223,
"isReply": false,
"inReplyToId": null,
"conversationId": "2071710766663979322",
"displayTextRange": [
0,
277
],
"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": 49863,
"following": 2569,
"status": "",
"canDm": true,
"canMediaTag": false,
"createdAt": "Sat Sep 15 18:45:02 +0000 2012",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 18130,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 1574,
"statusesCount": 16721,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2071710766663979322"
],
"profile_bio": {
"description": "Evals Evals Evals - https://t.co/Zrmp6LRd9c\n\nAbout Me: https://t.co/P6WyeKkyTa",
"entities": {
"description": {
"urls": [
{
"display_url": "evals.info",
"expanded_url": "http://evals.info",
"indices": [
21,
44
],
"url": "https://t.co/Zrmp6LRd9c"
},
{
"display_url": "hamel.dev",
"expanded_url": "https://hamel.dev",
"indices": [
56,
79
],
"url": "https://t.co/P6WyeKkyTa"
}
]
},
"url": {
"urls": [
{
"display_url": "evals.info",
"expanded_url": "http://evals.info",
"indices": [
0,
23
],
"url": "https://t.co/Zrmp6LRd9c"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"display_url": "pic.twitter.com/qxzZtPIYQz",
"expanded_url": "https://twitter.com/HamelHusain/status/2071710766663979322/photo/1",
"ext_master_playlist_only": [],
"ext_media_availability": {
"status": "Available"
},
"ext_playlists": [],
"features": {
"large": {
"faces": [
{
"h": 263,
"w": 263,
"x": 138,
"y": 278
}
]
},
"orig": {
"faces": [
{
"h": 263,
"w": 263,
"x": 138,
"y": 278
}
]
}
},
"id_str": "2071708926467534848",
"indices": [
278,
301
],
"media_key": "3_2071708926467534848",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARzAMErQGnAACgACHMAx90Rb0ToAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAABCgABHMAwStAacAAKAAIcwDH3RFvROgAA",
"media_key": "3_2071708926467534848"
}
},
"media_url_https": "https://pbs.twimg.com/media/HMAwStAacAAVCqh.jpg",
"original_info": {
"focus_rects": [
{
"h": 630,
"w": 1125,
"x": 38,
"y": 0
},
{
"h": 630,
"w": 630,
"x": 285,
"y": 0
},
{
"h": 630,
"w": 553,
"x": 324,
"y": 0
},
{
"h": 630,
"w": 315,
"x": 443,
"y": 0
},
{
"h": 630,
"w": 1200,
"x": 0,
"y": 0
}
],
"height": 630,
"width": 1200
},
"sizes": {
"large": {
"h": 630,
"w": 1200
}
},
"type": "photo",
"url": "https://t.co/qxzZtPIYQz"
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"urls": [
{
"display_url": "hamel.dev/blog/posts/eva…",
"expanded_url": "https://hamel.dev/blog/posts/eval-smell/",
"indices": [
564,
587
],
"url": "https://t.co/ErA9dp4ZPw"
}
],
"user_mentions": [
{
"id_str": "2286218053",
"indices": [
753,
761
],
"name": "Shreya Shankar",
"screen_name": "sh_reya"
},
{
"id_str": "1297324065611489285",
"indices": [
766,
778
],
"name": "Isaac Flath",
"screen_name": "isaac_flath"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
},
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
}