Viewing enriched Twitter post
Frontier models all have at least 100k context length, Gemini 1.5 has even 1m context. What about research and open source? Introducing Long Context Data Engineering, a data driven method achieving the first 128k context open source model matching GPT4-level Needle in a Haystack
{
"media": [
{
"id": "",
"type": "photo",
"url": null,
"media_url": "https://pbs.twimg.com/media/GGy6BD2XEAAr6lb.jpg",
"media_url_https": null,
"display_url": null,
"expanded_url": null
}
],
"nlp": {
"sentiment": "positive",
"processed_at": "2025-08-06T12:53:26.982537"
},
"score": 1.0,
"scored_at": "2025-08-09T13:46:07.546138",
"import_source": "manual_curation_2024",
"score_components": {
"author": 0.09,
"engagement": 0.139654580008829,
"quality": 0.13999999999999999,
"source": 0.15,
"nlp": 0.1,
"recency": 0.010000000000000002
},
"source_tagged_at": "2025-08-09T13:43:08.477283",
"enriched": true,
"enriched_at": "2025-08-09T13:43:08.477287",
"original_structure": "had_media_only"
}{
"user": {
"created_at": "2016-06-10T16:57:03.000Z",
"default_profile_image": false,
"description": "PhD @EdinburghNLP on LLMs and Machine Reasoning. Ex. @Columbia @PKU1898 @MITIBMLab @allen_ai AGI has yet to come, so keep running",
"fast_followers_count": 0,
"favourites_count": 2140,
"followers_count": 12234,
"friends_count": 1658,
"has_custom_timelines": false,
"is_translator": false,
"listed_count": 255,
"location": "",
"media_count": 41,
"name": "Yao Fu",
"normal_followers_count": 12234,
"possibly_sensitive": false,
"profile_banner_url": "https://pbs.twimg.com/profile_banners/741313237287768064/1650890183",
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1672654817297088512/CrHTKYgD_normal.jpg",
"screen_name": "Francis_YAO_",
"statuses_count": 688,
"translator_type": "none",
"url": "https://t.co/6K2Rtdvze3",
"verified": true,
"withheld_in_countries": [],
"id_str": "741313237287768064"
},
"id": "1759986097365627054",
"conversation_id": "1759986097365627054",
"full_text": "Frontier models all have at least 100k context length, Gemini 1.5 has even 1m context. What about research and open source? \n\nIntroducing Long Context Data Engineering, a data driven method achieving the first 128k context open source model matching GPT4-level Needle in a Haystack",
"reply_count": 8,
"retweet_count": 72,
"favorite_count": 476,
"hashtags": [],
"symbols": [],
"user_mentions": [],
"urls": [],
"media": [
{
"media_url": "https://pbs.twimg.com/media/GGy6BD2XEAAr6lb.jpg",
"type": "photo"
}
],
"url": "https://twitter.com/Francis_YAO_/status/1759986097365627054",
"created_at": "2024-02-20T16:59:19.000Z",
"#sort_index": "1759986097365627054",
"view_count": 80544,
"quote_count": 6,
"is_quote_tweet": false,
"is_retweet": false,
"is_pinned": false,
"is_truncated": true,
"startUrl": "https://twitter.com/francis_yao_/status/1759986097365627054"
}