Viewing enriched Twitter post
Google presents Inference Scaling for Long-Context Retrieval Augmented Generation - Finds that increasing inference computation leads to nearly linear gains in RAG perf when optimally allocated -Scaling inference compute on long-context LLMs achieves up to 58.9% gains on benchmark https://t.co/dpulK3a20k
{
"user": {
"created_at": "2016-11-04T06:57:37.000Z",
"default_profile_image": false,
"description": "",
"fast_followers_count": 0,
"favourites_count": 12031,
"followers_count": 113759,
"friends_count": 83,
"has_custom_timelines": true,
"is_translator": false,
"listed_count": 1410,
"location": "",
"media_count": 2259,
"name": "Aran Komatsuzaki",
"normal_followers_count": 113759,
"possibly_sensitive": false,
"profile_image_url_https": "https://pbs.twimg.com/profile_images/1561220982328754176/JOYS5kab_normal.jpg",
"screen_name": "arankomatsuzaki",
"statuses_count": 5395,
"translator_type": "none",
"url": "https://t.co/aZGCShnLYq",
"verified": true,
"withheld_in_countries": [],
"id_str": "794433401591693312"
},
"id": "1846730425370309089",
"conversation_id": "1846730425370309089",
"full_text": "Google presents Inference Scaling for Long-Context Retrieval Augmented Generation\n\n- Finds that increasing inference computation leads to nearly linear gains in RAG perf when optimally allocated\n-Scaling inference compute on long-context LLMs achieves up to 58.9% gains on benchmark\n\nhttps://t.co/dpulK3a20k",
"reply_count": 6,
"retweet_count": 84,
"favorite_count": 366,
"hashtags": [],
"symbols": [],
"user_mentions": [],
"urls": [],
"media": [
{
"media_url": "https://pbs.twimg.com/media/GaDnAy2bIAA89vK.png",
"type": "photo"
}
],
"url": "https://twitter.com/arankomatsuzaki/status/1846730425370309089",
"created_at": "2024-10-17T01:50:18.000Z",
"#sort_index": "1846730425370309089",
"view_count": 85102,
"quote_count": 3,
"is_quote_tweet": false,
"is_retweet": false,
"is_pinned": false,
"is_truncated": true,
"startUrl": "https://x.com/arankomatsuzaki/status/1846730425370309089"
}