Viewing enriched Twitter post
I tried Codex 5.3 (web) for porting VidEoMT, a simple and elegant ViT-based video segmentation model, to @huggingface Transformers Sadly, it missed the global picture, mistakenly assuming the model uses DINOv3 as its backbone, whereas it actually uses DINOv2. It got stuck. Opus 4.6 fixed it after I told it The job of ML Engineer is still safe - humans stay in the driver's seat PR: https://t.co/5ahL0GqtZN
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2026751735893549164/media_0.jpg?",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2026751735893549164/media_0.jpg?",
"type": "photo",
"filename": "media_0.jpg"
},
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2026751735893549164/media_1.jpg?",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2026751735893549164/media_1.jpg?",
"type": "photo",
"filename": "media_1.jpg"
}
],
"processed_at": "2026-03-01T19:34:56.691850",
"pipeline_version": "2.0"
}{
"type": "tweet",
"id": "2026751735893549164",
"url": "https://x.com/NielsRogge/status/2026751735893549164",
"twitterUrl": "https://twitter.com/NielsRogge/status/2026751735893549164",
"text": "I tried Codex 5.3 (web) for porting VidEoMT, a simple and elegant ViT-based video segmentation model, to @huggingface Transformers \n\nSadly, it missed the global picture, mistakenly assuming the model uses DINOv3 as its backbone, whereas it actually uses DINOv2. It got stuck. Opus 4.6 fixed it after I told it\n\nThe job of ML Engineer is still safe - humans stay in the driver's seat \n\nPR: https://t.co/5ahL0GqtZN",
"source": "Twitter for iPhone",
"retweetCount": 18,
"replyCount": 13,
"likeCount": 234,
"quoteCount": 3,
"viewCount": 43769,
"createdAt": "Wed Feb 25 20:10:43 +0000 2026",
"lang": "en",
"bookmarkCount": 156,
"isReply": false,
"inReplyToId": null,
"conversationId": "2026751735893549164",
"displayTextRange": [
0,
276
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "NielsRogge",
"url": "https://x.com/NielsRogge",
"twitterUrl": "https://twitter.com/NielsRogge",
"id": "133818617",
"name": "Niels Rogge",
"isVerified": false,
"isBlueVerified": false,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1828883496066060288/n0OUAXhz_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/133818617/1636026056",
"description": "",
"location": "Belgium",
"followers": 18701,
"following": 722,
"status": "",
"canDm": true,
"canMediaTag": false,
"createdAt": "Fri Apr 16 18:18:57 +0000 2010",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 1746,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 666,
"statusesCount": 2904,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1575416431793119232"
],
"profile_bio": {
"description": "ML Engineer @ML6team @huggingface. @KU_Leuven grad. General interest in machine learning, deep learning. Making AI more accessible for everyone!",
"entities": {
"description": {
"hashtags": [],
"symbols": [],
"urls": [],
"user_mentions": [
{
"id_str": "0",
"indices": [
12,
20
],
"name": "",
"screen_name": "ML6team"
},
{
"id_str": "0",
"indices": [
21,
33
],
"name": "",
"screen_name": "huggingface"
},
{
"id_str": "0",
"indices": [
35,
45
],
"name": "",
"screen_name": "KU_Leuven"
}
]
},
"url": {
"urls": [
{
"display_url": "nielsrogge.github.io",
"expanded_url": "http://nielsrogge.github.io",
"indices": [
0,
23
],
"url": "https://t.co/5ZROAxgOnO"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"display_url": "pic.twitter.com/ld6TBFo0nu",
"expanded_url": "https://twitter.com/NielsRogge/status/2026751735893549164/photo/1",
"ext_media_availability": {
"status": "Available"
},
"id_str": "2026751242072903680",
"indices": [
277,
300
],
"media_key": "16_2026751242072903680",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwAAgoAARwgd4Q31lAACgACHCB39zHXYGwAAA==",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAACCgABHCB3hDfWUAAKAAIcIHf3MddgbAAA",
"media_key": "16_2026751242072903680"
}
},
"media_url_https": "https://pbs.twimg.com/tweet_video_thumb/HCB3hDfWUAA5c9M.jpg",
"original_info": {
"focus_rects": [],
"height": 720,
"width": 1280
},
"sizes": {
"large": {
"h": 720,
"w": 1280
}
},
"type": "animated_gif",
"url": "https://t.co/ld6TBFo0nu",
"video_info": {
"aspect_ratio": [
16,
9
],
"variants": [
{
"bitrate": 0,
"content_type": "video/mp4",
"url": "https://video.twimg.com/tweet_video/HCB3hDfWUAA5c9M.mp4"
}
]
}
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"urls": [
{
"display_url": "github.com/huggingface/tr…",
"expanded_url": "https://github.com/huggingface/transformers/pull/44285",
"indices": [
391,
414
],
"url": "https://t.co/5ahL0GqtZN"
}
],
"user_mentions": [
{
"id_str": "778764142412984320",
"indices": [
105,
117
],
"name": "Hugging Face",
"screen_name": "huggingface"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"article": null
}