🐦 Twitter Post Details

Viewing enriched Twitter post

@dair_ai

When does combining LLMs help? Great analysis on combining language models, measured across 67 models from 21 providers. Any policy that routes, votes, cascades, or runs a mixture of agents and then returns one model's answer is bounded above by 1 minus beta, where beta is the fraction of queries every candidate model gets wrong. The common justification for ensembling is diversity, usually measured as low pairwise error correlation. The paper proves that correlation cannot identify beta, so decorrelation does not establish that headroom exists. And across the 67 models, real co-failures are far more concentrated than independence-style assumptions predict. Before assuming a router or MoA setup will help, measure beta. Co-failures cluster on the answer format rather than the subject. Paper: https://t.co/PGO9YAoBzH Learn to build effective AI agents in our academy: https://t.co/LRnpZN7L4c

Media 1

📊 Media Metadata

{
  "media": [
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2070984020155158636/media_0.png",
      "filename": "media_0.png"
    }
  ],
  "processed_at": "2026-06-29T15:02:34.792012",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2070984020155158636",
  "url": "https://x.com/dair_ai/status/2070984020155158636",
  "twitterUrl": "https://twitter.com/dair_ai/status/2070984020155158636",
  "text": "When does combining LLMs help?\n\nGreat analysis on combining language models, measured across 67 models from 21 providers.\n\nAny policy that routes, votes, cascades, or runs a mixture of agents and then returns one model's answer is bounded above by 1 minus beta, where beta is the fraction of queries every candidate model gets wrong.\n\nThe common justification for ensembling is diversity, usually measured as low pairwise error correlation. The paper proves that correlation cannot identify beta, so decorrelation does not establish that headroom exists. And across the 67 models, real co-failures are far more concentrated than independence-style assumptions predict.\n\nBefore assuming a router or MoA setup will help, measure beta. Co-failures cluster on the answer format rather than the subject.\n\nPaper: https://t.co/PGO9YAoBzH\n\nLearn to build effective AI agents in our academy: https://t.co/LRnpZN7L4c",
  "source": "Twitter for iPhone",
  "retweetCount": 25,
  "replyCount": 14,
  "likeCount": 127,
  "quoteCount": 5,
  "viewCount": 16539,
  "createdAt": "Sat Jun 27 21:34:02 +0000 2026",
  "lang": "en",
  "bookmarkCount": 111,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2070984020155158636",
  "displayTextRange": [
    0,
    279
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "dair_ai",
    "url": "https://x.com/dair_ai",
    "twitterUrl": "https://twitter.com/dair_ai",
    "id": "889050642903293953",
    "name": "DAIR.AI",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1643277398522187778/31dedbLo_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/889050642903293953/1773242460",
    "description": "",
    "location": "",
    "followers": 127062,
    "following": 1,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Sun Jul 23 09:12:45 +0000 2017",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 4678,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 260,
    "statusesCount": 3380,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2071260533383135531"
    ],
    "profile_bio": {
      "description": "Democratizing AI research, education, and technologies. Learn about AI Agents for FREE at https://t.co/HHXg8rryu4",
      "entities": {
        "description": {
          "urls": [
            {
              "display_url": "academy.dair.ai/courses/elemen…",
              "expanded_url": "https://academy.dair.ai/courses/elements-of-ai-agents",
              "indices": [
                90,
                113
              ],
              "url": "https://t.co/HHXg8rryu4"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "dair.ai",
              "expanded_url": "https://www.dair.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/lkqPZtMU5s"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/P5Letzaz6R",
        "expanded_url": "https://twitter.com/dair_ai/status/2070984020155158636/photo/1",
        "ext_master_playlist_only": [],
        "ext_media_availability": {
          "status": "Available"
        },
        "ext_playlists": [],
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2070984016329916416",
        "indices": [
          280,
          303
        ],
        "media_key": "3_2070984016329916416",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARy9nP2E20AACgACHL2c/mjb0GwAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHL2c/YTbQAAKAAIcvZz+aNvQbAAA",
            "media_key": "3_2070984016329916416"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HL2c_YTbQAAV48K.png",
        "original_info": {
          "focus_rects": [
            {
              "h": 991,
              "w": 1770,
              "x": 0,
              "y": 0
            },
            {
              "h": 1770,
              "w": 1770,
              "x": 0,
              "y": 0
            },
            {
              "h": 1886,
              "w": 1654,
              "x": 68,
              "y": 0
            },
            {
              "h": 1886,
              "w": 943,
              "x": 424,
              "y": 0
            },
            {
              "h": 1886,
              "w": 1770,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1886,
          "width": 1770
        },
        "sizes": {
          "large": {
            "h": 1886,
            "w": 1770
          }
        },
        "type": "photo",
        "url": "https://t.co/P5Letzaz6R"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "arxiv.org/abs/2606.27288",
        "expanded_url": "https://arxiv.org/abs/2606.27288",
        "indices": [
          807,
          830
        ],
        "url": "https://t.co/PGO9YAoBzH"
      },
      {
        "display_url": "academy.dair.ai",
        "expanded_url": "https://academy.dair.ai/",
        "indices": [
          883,
          906
        ],
        "url": "https://t.co/LRnpZN7L4c"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}