{
  "user": {
    "created_at": "2015-09-04T12:59:26.000Z",
    "default_profile_image": false,
    "description": "Building with AI Agents @dair_ai • Prev: Meta AI, Elastic, Galactica LLM, PhD • I also teach how to build with LLMs, RAG & AI Agents ⬇️",
    "fast_followers_count": 0,
    "favourites_count": 27933,
    "followers_count": 216711,
    "friends_count": 532,
    "has_custom_timelines": true,
    "is_translator": false,
    "listed_count": 3690,
    "location": "",
    "media_count": 2656,
    "name": "elvis",
    "normal_followers_count": 216711,
    "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": 12439,
    "translator_type": "regular",
    "url": "https://t.co/JBU5beHQNs",
    "verified": true,
    "withheld_in_countries": [],
    "id_str": "3448284313"
  },
  "id": "1848782378631892997",
  "conversation_id": "1848782378631892997",
  "full_text": "Reasoning Patterns of OpenAI's o1-preview Model\n\nWhen compared with other test-time compute methods, o1 achieved the best performance across most datasets.\n\nThe authors observe that the most commonly used reasoning patterns in o1 are divide and conquer and self-refinement.\n\no1 uses different reasoning patterns for different tasks. For commonsense reasoning tasks, o1 tends to use context identification and emphasize constraints. For math and coding tasks, o1 mainly relies on method reuse and divide and conquer.\n\n\"We also explore the number of reasoning tokens of o1 across different tasks, and observe that the number of reasoning tokens varies a lot across different tasks.\"\n\nModels like o1-preview are hard to use in that it's not so clear how to further optimize their performance. Understanding these \"reasoning\" patterns is a good first step but there is a lot more research to be done on these patterns and what and when to add additional context.",
  "reply_count": 4,
  "retweet_count": 47,
  "favorite_count": 271,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [],
  "urls": [],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/GagxxiTbEAoggo5.png",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/omarsar0/status/1848782378631892997",
  "created_at": "2024-10-22T17:44:02.000Z",
  "#sort_index": "1848782378631892997",
  "view_count": 24639,
  "quote_count": 5,
  "is_quote_tweet": false,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": true,
  "startUrl": "https://x.com/omarsar0/status/1848782378631892997"
}