Viewing enriched Twitter post
We now have a benchmark for AI hallucinations, and, based on OpenAI models, 3 useful findings: 1) Larger models hallucinate less 2) If you ask models their confidence in answers, high confidence = lower chance of hallucination 3) Where accuracy is low, answers you get vary a lot https://t.co/mFaSUmZp01
{
"data": [
{
"id": "",
"type": "photo",
"url": null,
"media_url": "https://pbs.twimg.com/media/GbOTe4UXEAAOy_s.png",
"media_url_https": null,
"display_url": null,
"expanded_url": null
},
{
"id": "",
"type": "photo",
"url": null,
"media_url": "https://pbs.twimg.com/media/GbOTgX-XoAAWrSL.jpg",
"media_url_https": null,
"display_url": null,
"expanded_url": null
},
{
"id": "",
"type": "photo",
"url": null,
"media_url": "https://pbs.twimg.com/media/GbOTiMCWoAACaFO.jpg",
"media_url_https": null,
"display_url": null,
"expanded_url": null
}
],
"score": 1.0,
"scored_at": "2025-08-09T13:46:07.551019",
"import_source": "network_archive_import",
"media": [
{
"type": "photo",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1851986250049237131/media_0.png?",
"filename": "media_0.png",
"original_url": "https://pbs.twimg.com/media/GbOTe4UXEAAOy_s.png"
},
{
"type": "photo",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1851986250049237131/media_1.jpg?",
"filename": "media_1.jpg",
"original_url": "https://pbs.twimg.com/media/GbOTgX-XoAAWrSL.jpg"
},
{
"type": "photo",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1851986250049237131/media_2.jpg?",
"filename": "media_2.jpg",
"original_url": "https://pbs.twimg.com/media/GbOTiMCWoAACaFO.jpg"
}
],
"storage_migrated": true
}{
"user": {
"created_at": "2009-05-10T22:33:52.000Z",
"default_profile_image": false,
"description": "Professor @Wharton studying AI, innovation & startups. Democratizing education using tech\nBook: https://t.co/CSmipbJ2jV\nSubstack: https://t.co/UIBhxu4bgq",
"fast_followers_count": 0,
"favourites_count": 6584,
"followers_count": 242516,
"friends_count": 557,
"has_custom_timelines": false,
"is_translator": false,
"listed_count": 5555,
"location": "Philadelphia, PA",
"media_count": 12485,
"name": "Ethan Mollick",
"normal_followers_count": 242516,
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/39125788/1713840725",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1601382188712398850/3AAOlqrX_normal.jpg",
"screen_name": "emollick",
"statuses_count": 29379,
"translator_type": "none",
"url": "https://t.co/uItckI9ujc",
"verified": true,
"withheld_in_countries": [],
"id_str": "39125788"
},
"id": "1851986250049237131",
"conversation_id": "1851986250049237131",
"full_text": "We now have a benchmark for AI hallucinations, and, based on OpenAI models, 3 useful findings:\n1) Larger models hallucinate less\n2) If you ask models their confidence in answers, high confidence = lower chance of hallucination\n3) Where accuracy is low, answers you get vary a lot https://t.co/mFaSUmZp01",
"reply_count": 21,
"retweet_count": 96,
"favorite_count": 636,
"hashtags": [],
"symbols": [],
"user_mentions": [],
"urls": [],
"media": [
{
"media_url": "https://pbs.twimg.com/media/GbOTe4UXEAAOy_s.png",
"type": "photo"
},
{
"media_url": "https://pbs.twimg.com/media/GbOTgX-XoAAWrSL.jpg",
"type": "photo"
},
{
"media_url": "https://pbs.twimg.com/media/GbOTiMCWoAACaFO.jpg",
"type": "photo"
}
],
"url": "https://twitter.com/emollick/status/1851986250049237131",
"created_at": "2024-10-31T13:55:04.000Z",
"#sort_index": "1851986250049237131",
"view_count": 50474,
"quote_count": 6,
"is_quote_tweet": false,
"is_retweet": false,
"is_pinned": false,
"is_truncated": false,
"startUrl": "https://x.com/emollick/status/1851986250049237131"
}