🐦 Twitter Post Details

Viewing enriched Twitter post

@omarsar0

ChatGPT o1 is the most "intelligent" AI model and it's not even close! Full o1 generates thinking steps ~50 faster than preview. It's more accurate, reliable, and got better on harder tasks that require advanced reasoning and knowledge. I ran a few tests on it already. Here are my observations: Full video with examples & explanations: https://t.co/oVcBdyZDxB Strengths - impressive at math, code, and knowledge-intensive tasks. Weakness - it only failed on a cross-word puzzle but I think it might be solvable when a web search becomes available. In the end, while very efficient with complex knowledge use, it's still constrained by data it's trained on. Speed - the thinking steps are generated a lot faster! Not a fair comparison with the open alternatives but I think this improves the overall user experience. "Knowledgeable and highly intelligent" - as mentioned in the demo by OpenAI researchers, o1 is great at dealing with ambiguity and filling in knowledge gaps. I was impressed by how it implemented an agentic solution (with lots of details) from a basic diagram of architecture (with minimal details). Check out the sample video. Better Task Coverage - Due to the speed and the ability to make sense of instructions and intent (i.e., know when to response fast and when to "think" deeply) much better, it feels like it might be more useful for a broader range of tasks. Image understanding - the image understanding capability is mysterious (often leads to faster responses but no thinking) but impressive. More experiments and notes soon. Stay tuned!

View on Twitter

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1864787459445326277/media_0.jpg",
      "type": "video",
      "original_url": "https://pbs.twimg.com/ext_tw_video_thumb/1864786648107544576/pu/img/ds6_hdWEDhKALdUd.jpg",
      "download_date": "2025-08-13T05:53:27.645838",
      "stored_in_supabase": true
    }
  ],
  "conversion_date": "2025-08-13T00:39:16.318505",
  "format_converted": true,
  "original_structure": "had_media_only"
}

🔧 Raw API Response

{
  "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": 27931,
    "followers_count": 216714,
    "friends_count": 532,
    "has_custom_timelines": true,
    "is_translator": false,
    "listed_count": 3688,
    "location": "",
    "media_count": 2656,
    "name": "elvis",
    "normal_followers_count": 216714,
    "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": "1864787459445326277",
  "conversation_id": "1864787459445326277",
  "full_text": "ChatGPT o1 is the most \"intelligent\" AI model and it's not even close!\n\nFull o1 generates thinking steps ~50 faster than preview.\n\nIt's more accurate, reliable, and got better on harder tasks that require advanced reasoning and knowledge.\n\nI ran a few tests on it already. Here are my observations:\n\nFull video with examples & explanations: https://t.co/oVcBdyZDxB\n\nStrengths - impressive at math, code, and knowledge-intensive tasks. \n\nWeakness - it only failed on a cross-word puzzle but I think it might be solvable when a web search becomes available. In the end, while very efficient with complex knowledge use, it's still constrained by data it's trained on. \n\nSpeed - the thinking steps are generated a lot faster! Not a fair comparison with the open alternatives but I think this improves the overall user experience.\n\n\"Knowledgeable and highly intelligent\" - as mentioned in the demo by OpenAI researchers, o1 is great at dealing with ambiguity and filling in knowledge gaps. I was impressed by how it implemented an agentic solution (with lots of details) from a basic diagram of architecture (with minimal details). Check out the sample video. \n\nBetter Task Coverage - Due to the speed and the ability to make sense of instructions and intent (i.e., know when to response fast and when to \"think\" deeply) much better, it feels like it might be more useful for a broader range of tasks. \n\nImage understanding - the image understanding capability is mysterious (often leads to faster responses but no thinking) but impressive.\n\nMore experiments and notes soon. Stay tuned!",
  "reply_count": 13,
  "retweet_count": 43,
  "favorite_count": 285,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [],
  "urls": [],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/ext_tw_video_thumb/1864786648107544576/pu/img/ds6_hdWEDhKALdUd.jpg",
      "type": "video",
      "video_url": "https://video.twimg.com/ext_tw_video/1864786648107544576/pu/vid/avc1/1280x720/hLhqfmaO-nrL7n6x.mp4?tag=12"
    }
  ],
  "url": "https://twitter.com/omarsar0/status/1864787459445326277",
  "created_at": "2024-12-05T21:42:31.000Z",
  "#sort_index": "1864787459445326277",
  "view_count": 100324,
  "quote_count": 10,
  "is_quote_tweet": false,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": true,
  "startUrl": "https://x.com/omarsar0/status/1864787459445326277"
}