Viewing enriched Twitter post
Curious: asking GPT 3.5/4T to estimate the length of a piece of text shows ~OK accuracy on short sequences but weird results >1k words. Any theories? 1024 context length during training? A dearth of longer essays with word counts? Something else? https://t.co/aRk6tCr8r0
{
"score": 0.84,
"scored_at": "2025-08-09T13:47:19.518903",
"import_source": "manual_curation_2024",
"links_checked": true,
"checked_at": "2025-08-10T10:33:13.421680",
"media": [
{
"type": "photo",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1760094827147079897/media_0.jpg?",
"filename": "media_0.jpg"
},
{
"type": "photo",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1760094827147079897/media_1.jpg?",
"filename": "media_1.jpg"
},
{
"id": "",
"type": "photo",
"url": null,
"media_url": "https://pbs.twimg.com/media/GG0c2QMawAAcclq.jpg",
"media_url_https": null,
"display_url": null,
"expanded_url": null
},
{
"id": "",
"type": "photo",
"url": null,
"media_url": "https://pbs.twimg.com/media/GG0cLgNbYAEnVoa.jpg",
"media_url_https": null,
"display_url": null,
"expanded_url": null
}
],
"reprocessed_at": "2025-08-12T15:28:08.210203",
"reprocessed_reason": "missing_media_array",
"original_structure": "had_both"
}{
"user": {
"created_at": "2015-10-20T20:07:48.000Z",
"default_profile_image": false,
"description": "Data scientist and AI researcher. R&D at https://t.co/9xrxRrGfEE.",
"fast_followers_count": 0,
"favourites_count": 11980,
"followers_count": 6320,
"friends_count": 914,
"has_custom_timelines": true,
"is_translator": false,
"listed_count": 153,
"location": "Portland, Oregon",
"media_count": 506,
"name": "Jonathan Whitaker",
"normal_followers_count": 6320,
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/4004364327/1649394299",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1734357687796748288/RWKKnzbT_normal.jpg",
"screen_name": "johnowhitaker",
"statuses_count": 1762,
"translator_type": "none",
"url": "https://t.co/GWPJDPerHO",
"verified": false,
"withheld_in_countries": [],
"id_str": "4004364327"
},
"id": "1760094827147079897",
"conversation_id": "1760094827147079897",
"full_text": "Curious: asking GPT 3.5/4T to estimate the length of a piece of text shows ~OK accuracy on short sequences but weird results >1k words. \nAny theories? 1024 context length during training? A dearth of longer essays with word counts? Something else? https://t.co/aRk6tCr8r0",
"reply_count": 7,
"retweet_count": 4,
"favorite_count": 22,
"hashtags": [],
"symbols": [],
"user_mentions": [],
"urls": [],
"media": [
{
"media_url": "https://pbs.twimg.com/media/GG0c2QMawAAcclq.jpg",
"type": "photo"
},
{
"media_url": "https://pbs.twimg.com/media/GG0cLgNbYAEnVoa.jpg",
"type": "photo"
}
],
"url": "https://twitter.com/johnowhitaker/status/1760094827147079897",
"created_at": "2024-02-21T00:11:22.000Z",
"#sort_index": "1760094827147079897",
"view_count": 23511,
"quote_count": 1,
"is_quote_tweet": false,
"is_retweet": false,
"is_pinned": false,
"is_truncated": false,
"startUrl": "https://twitter.com/johnowhitaker/status/1760094827147079897"
}