Viewing enriched Twitter post
Another interesting short study. Finds that "Llama-2-70b is almost as strong at factuality as gpt-4, and considerably better than gpt-3.5-turbo." Need to take a closer at how evaluation is done but I already starting to see strong experimental results on Llama 2 for all kinds of summarization problems. Super exciting stuff! https://t.co/LWlC4B5Gat
{
"data": [
{
"id": "",
"type": "photo",
"url": null,
"media_url": "https://pbs.twimg.com/media/F4tcHf6WEAEkOkj.png",
"media_url_https": null,
"display_url": null,
"expanded_url": null
}
],
"score": 1.0,
"scored_at": "2025-08-09T13:46:07.554804",
"import_source": "manual_curation_2023",
"media": [
{
"type": "photo",
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1696553166412689654/media_0.png?",
"filename": "media_0.png",
"original_url": "https://pbs.twimg.com/media/F4tcHf6WEAEkOkj.png"
}
],
"storage_migrated": true
}{
"user": {
"created_at": "2015-09-04T12:59:26.000Z",
"default_profile_image": false,
"description": "I share insights & advances in LLMs • Building @dair_ai • Prev: Meta AI, Galactica LLM, PapersWithCode, Elastic, PhD • Author of Prompting Guide (1.5M users)",
"fast_followers_count": 0,
"favourites_count": 23175,
"followers_count": 156961,
"friends_count": 405,
"has_custom_timelines": true,
"is_translator": false,
"listed_count": 2897,
"location": "",
"media_count": 1643,
"name": "elvis",
"normal_followers_count": 156961,
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/3448284313/1565974901",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/939313677647282181/vZjFWtAn_normal.jpg",
"screen_name": "omarsar0",
"statuses_count": 9387,
"translator_type": "regular",
"url": "https://t.co/H9w2yq9w1L",
"verified": false,
"withheld_in_countries": [],
"id_str": "3448284313"
},
"id": "1696553166412689654",
"conversation_id": "1696553166412689654",
"full_text": "Another interesting short study. \n\nFinds that \"Llama-2-70b is almost as strong at factuality as gpt-4, and considerably better than gpt-3.5-turbo.\"\n\nNeed to take a closer at how evaluation is done but I already starting to see strong experimental results on Llama 2 for all kinds of summarization problems.\n\nSuper exciting stuff!\n\nhttps://t.co/LWlC4B5Gat",
"reply_count": 20,
"retweet_count": 93,
"favorite_count": 568,
"hashtags": [],
"symbols": [],
"user_mentions": [],
"urls": [],
"media": [
{
"media_url": "https://pbs.twimg.com/media/F4tcHf6WEAEkOkj.png",
"type": "photo"
}
],
"url": "https://twitter.com/omarsar0/status/1696553166412689654",
"created_at": "2023-08-29T15:59:29.000Z",
"#sort_index": "1696553166412689654",
"view_count": 119056,
"quote_count": 4,
"is_quote_tweet": false,
"is_retweet": false,
"is_pinned": false,
"is_truncated": true,
"startUrl": "https://twitter.com/omarsar0/status/1696553166412689654"
}