Viewing enriched Twitter post
I've said it before: Structured generation is the future 🔮 The @dottxtai team has ported its core Outlines algos to rust, which means from now on, structured LLM generation is: - faster - more robust - embeddable into any ML software (no need for Python anymore) ^#3 is my personal favorite
{
"data": [
{
"id": "",
"type": "photo",
"url": null,
"media_url": "https://pbs.twimg.com/media/Gap2Jx_XQAA_BE4.jpg",
"media_url_https": null,
"display_url": null,
"expanded_url": null
}
],
"score": 0.86,
"scored_at": "2025-08-09T13:46:07.549877",
"import_source": "network_archive_import",
"media": [
{
"type": "photo",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1849421181461356601/media_0.jpg?",
"filename": "media_0.jpg",
"original_url": "https://pbs.twimg.com/media/Gap2Jx_XQAA_BE4.jpg"
}
],
"storage_migrated": true
}{
"user": {
"created_at": "2008-09-05T07:56:27.000Z",
"default_profile_image": false,
"description": "Co-founder and CTO at @huggingface 🤗. ML/AI for everyone, building products to propel communities fwd. @Stanford + @Polytechnique",
"fast_followers_count": 0,
"favourites_count": 22291,
"followers_count": 54338,
"friends_count": 1116,
"has_custom_timelines": true,
"is_translator": false,
"listed_count": 1081,
"location": "Paris / New York",
"media_count": 1590,
"name": "Julien Chaumond",
"normal_followers_count": 54338,
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/16141659/1409913820",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1108502565925326850/zPsBf2BI_normal.png",
"screen_name": "julien_c",
"statuses_count": 16268,
"translator_type": "regular",
"url": "https://t.co/wagOrVH3jY",
"verified": true,
"withheld_in_countries": [],
"id_str": "16141659"
},
"id": "1849421181461356601",
"conversation_id": "1849421181461356601",
"full_text": "I've said it before: \n\nStructured generation is the future 🔮\n\nThe @dottxtai team has ported its core Outlines algos to rust, which means from now on, structured LLM generation is:\n\n- faster\n- more robust\n- embeddable into any ML software (no need for Python anymore)\n\n^#3 is my personal favorite",
"reply_count": 4,
"retweet_count": 26,
"favorite_count": 169,
"hashtags": [],
"symbols": [],
"user_mentions": [
{
"id_str": "1719934067435520000",
"name": ".txt",
"screen_name": "dottxtai",
"profile": "https://twitter.com/dottxtai"
}
],
"urls": [],
"media": [
{
"media_url": "https://pbs.twimg.com/media/Gap2Jx_XQAA_BE4.jpg",
"type": "photo"
}
],
"url": "https://twitter.com/julien_c/status/1849421181461356601",
"created_at": "2024-10-24T12:02:24.000Z",
"#sort_index": "1849421181461356601",
"view_count": 11106,
"quote_count": 1,
"is_quote_tweet": false,
"is_retweet": false,
"is_pinned": false,
"is_truncated": true,
"startUrl": "https://x.com/julien_c/status/1849421181461356601"
}