Viewing enriched Twitter post
The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision) Link: https://t.co/m8u4wSGGzN A 166-page report from Microsoft qualitatively exploring GPT-4V capabilities and usage. Describes visual+text prompting techniques, few-shot learning, reasoning, etc. Looks like it will be a must-read for GPT-4V power users 👀
{
"media": [
{
"type": "photo",
"url": "https://pbs.twimg.com/media/F7Zyu8gbMAArTE_.png",
"media_url": "https://pbs.twimg.com/media/F7Zyu8gbMAArTE_.png",
"filename": "media_0.jpg"
},
{
"type": "photo",
"url": "https://pbs.twimg.com/media/F7Zy1Z7aEAAnYHC.jpg",
"media_url": "https://pbs.twimg.com/media/F7Zy1Z7aEAAnYHC.jpg",
"filename": "media_1.jpg"
}
],
"conversion_date": "2025-08-13T00:43:29.403008",
"format_converted": true,
"original_structure": "had_media_only",
"enhanced_from_raw_response": true,
"enhanced_at": "2025-08-13T17:20:00Z"
}{
"user": {
"created_at": "2011-12-20T03:45:50.000Z",
"default_profile_image": false,
"description": "PhD at 19 |\nFounder and CEO at @MedARC_AI |\nResearch Director at @StabilityAI | \n@kaggle Notebooks GM |\nBiomed. engineer @ 14 |\nTEDx talk➡https://t.co/DwMkst4bnG",
"fast_followers_count": 0,
"favourites_count": 59837,
"followers_count": 44965,
"friends_count": 994,
"has_custom_timelines": true,
"is_translator": false,
"listed_count": 691,
"location": "",
"media_count": 1186,
"name": "Tanishq Mathew Abraham, PhD",
"normal_followers_count": 44965,
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/441465751/1675968078",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1553508977735962624/nnlSwBmu_normal.jpg",
"screen_name": "iScienceLuvr",
"statuses_count": 12033,
"translator_type": "none",
"url": "https://t.co/nNzCz2VVd1",
"verified": false,
"withheld_in_countries": [],
"id_str": "441465751"
},
"id": "1708679393533673491",
"conversation_id": "1708679393533673491",
"full_text": "The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)\n\nLink: https://t.co/m8u4wSGGzN\n\nA 166-page report from Microsoft qualitatively exploring GPT-4V capabilities and usage. Describes visual+text prompting techniques, few-shot learning, reasoning, etc.\n\nLooks like it will be a must-read for GPT-4V power users 👀",
"reply_count": 14,
"retweet_count": 159,
"favorite_count": 666,
"hashtags": [],
"symbols": [],
"user_mentions": [],
"urls": [
{
"url": "https://t.co/qhQr50rcAf",
"expanded_url": "https://arxiv.org/abs/2309.17421",
"display_url": "arxiv.org/abs/2309.17421"
}
],
"media": [
{
"media_url": "https://pbs.twimg.com/media/F7Zyu8gbMAArTE_.png",
"type": "photo"
},
{
"media_url": "https://pbs.twimg.com/media/F7Zy1Z7aEAAnYHC.jpg",
"type": "photo"
}
],
"url": "https://twitter.com/iScienceLuvr/status/1708679393533673491",
"created_at": "2023-10-02T03:04:47.000Z",
"#sort_index": "1708679393533673491",
"view_count": 175448,
"quote_count": 13,
"is_quote_tweet": false,
"is_retweet": false,
"is_pinned": false,
"is_truncated": true,
"startUrl": "https://twitter.com/iscienceluvr/status/1708679393533673491"
}