🐦 Twitter Post Details

Viewing enriched Twitter post

@iScienceLuvr

Frontier Models are Capable of In-context Scheming abs: https://t.co/CddPus9d03 "Our results show that o1, Claude 3.5 Sonnet, Claude 3 Opus, Gemini 1.5 Pro, and Llama 3.1 405B all demonstrate in-context scheming capabilities. They recognize scheming as a viable strategy and readily engage in such behavior. For example, models strategically introduce subtle mistakes into their responses, attempt to disable their oversight mechanisms, and even exfiltrate what they believe to be their model weights to external servers."

Media 1
View on Twitter

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/1865982666237264215/media_0.jpg",
      "type": "photo",
      "original_url": "https://pbs.twimg.com/media/GeVNV36agAEdkZ1.jpg",
      "recovered_from_supabase": true
    }
  ],
  "conversion_date": "2025-08-13T00:27:38.260303",
  "format_converted": true,
  "original_structure": "had_media_only"
}

🔧 Raw API Response

{
  "user": {
    "created_at": "2011-12-20T03:45:50.000Z",
    "default_profile_image": false,
    "description": "PhD at 19 |\nFounder and CEO at @MedARC_AI |\nResearch Director at @StabilityAI | \n@kaggle Notebooks GM |\nBiomed. engineer @ 14 |\nTEDx talk➡https://t.co/xPxwKTpz0D",
    "fast_followers_count": 0,
    "favourites_count": 83827,
    "followers_count": 63880,
    "friends_count": 1100,
    "has_custom_timelines": true,
    "is_translator": false,
    "listed_count": 974,
    "location": "",
    "media_count": 1828,
    "name": "Tanishq Mathew Abraham, Ph.D.",
    "normal_followers_count": 63880,
    "possibly_sensitive": false,
    "profile_banner_url": "https://pbs.twimg.com/profile_banners/441465751/1675968078",
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/1553508977735962624/nnlSwBmu_normal.jpg",
    "screen_name": "iScienceLuvr",
    "statuses_count": 14515,
    "translator_type": "none",
    "url": "https://t.co/nNzCz2VVd1",
    "verified": true,
    "withheld_in_countries": [],
    "id_str": "441465751"
  },
  "id": "1865982666237264215",
  "conversation_id": "1865982666237264215",
  "full_text": "Frontier Models are Capable of In-context Scheming\n\nabs: https://t.co/CddPus9d03\n\n\"Our results show that o1, Claude 3.5 Sonnet, Claude 3 Opus, Gemini 1.5 Pro, and Llama 3.1 405B all demonstrate in-context scheming capabilities. They recognize scheming as a viable strategy and readily engage in such behavior. For example, models strategically introduce subtle mistakes into their responses, attempt to disable their oversight mechanisms, and even exfiltrate what they believe to be their model weights to external servers.\"",
  "reply_count": 6,
  "retweet_count": 35,
  "favorite_count": 159,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [],
  "urls": [
    {
      "url": "https://t.co/a1OQYDOsQ4",
      "expanded_url": "https://arxiv.org/abs/2412.04984",
      "display_url": "arxiv.org/abs/2412.04984"
    }
  ],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/GeVNV36agAEdkZ1.jpg",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/iScienceLuvr/status/1865982666237264215",
  "created_at": "2024-12-09T04:51:50.000Z",
  "#sort_index": "1865982666237264215",
  "view_count": 20546,
  "quote_count": 5,
  "is_quote_tweet": false,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": true,
  "startUrl": "https://x.com/iscienceluvr/status/1865982666237264215"
}