🐦 Twitter Post Details

Viewing enriched Twitter post

@ValerioCapraro

Here's the longer version of our Nature piece. Our argument is simple: statistical approximation is not the same thing as intelligence. Strong benchmark scores often say very little about how LLMs behave under novelty, uncertainty, or shifting goals. Even more importantly, similar behaviors can arise from fundamentally different processes. In another paper, we identified seven epistemological fault lines between humans and LLMs. For example, LLMs have no internal representation of what is true. They often generate confident contradictions, especially in longer interactions, because they do not track what is actually true. Another example. Yes, LLMs have solved some open mathematical problems, but these cases typically involve applying known methods to well-defined problems. LLMs cannot invent anything that is truly new and true at the same time, because they lack the epistemic machinery to determine what is true. None of this means LLMs are useless. Quite the opposite: they are extraordinarily useful. But we should be careful about what they are and what they are not. Producing plausible text is not the same as understanding. Statistical prediction is not the same as intelligence. So despite the hype from the usual suspects, AGI has not been achieved. * paper in the first reply Joint with @Walter4C and @GaryMarcus

Media 1
View on Twitter

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2032441725516411009/media_0.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2032441725516411009/media_0.jpg",
      "type": "photo",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2026-03-13T16:22:05.379841",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2032441725516411009",
  "url": "https://x.com/ValerioCapraro/status/2032441725516411009",
  "twitterUrl": "https://twitter.com/ValerioCapraro/status/2032441725516411009",
  "text": "Here's the longer version of our Nature piece.\n\nOur argument is simple: statistical approximation is not the same thing as intelligence.\n\nStrong benchmark scores often say very little about how LLMs behave under novelty, uncertainty, or shifting goals.\n\nEven more importantly, similar behaviors can arise from fundamentally different processes. In another paper, we identified seven epistemological fault lines between humans and LLMs.\n\nFor example, LLMs have no internal representation of what is true. They often generate confident contradictions, especially in longer interactions, because they do not track what is actually true.\n\nAnother example. Yes, LLMs have solved some open mathematical problems, but these cases typically involve applying known methods to well-defined problems. LLMs cannot invent anything that is truly new and true at the same time, because they lack the epistemic machinery to determine what is true.\n\nNone of this means LLMs are useless. Quite the opposite: they are extraordinarily useful.\n\nBut we should be careful about what they are and what they are not.\n\nProducing plausible text is not the same as understanding.\nStatistical prediction is not the same as intelligence.\n\nSo despite the hype from the usual suspects, AGI has not been achieved.\n\n*\npaper in the first reply\n\nJoint with @Walter4C and @GaryMarcus",
  "source": "Twitter for iPhone",
  "retweetCount": 19,
  "replyCount": 14,
  "likeCount": 53,
  "quoteCount": 2,
  "viewCount": 3857,
  "createdAt": "Fri Mar 13 13:00:42 +0000 2026",
  "lang": "en",
  "bookmarkCount": 32,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2032441725516411009",
  "displayTextRange": [
    0,
    276
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "ValerioCapraro",
    "url": "https://x.com/ValerioCapraro",
    "twitterUrl": "https://twitter.com/ValerioCapraro",
    "id": "1856509825",
    "name": "Valerio Capraro",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1987826440117551104/Nm8PaM6g_normal.jpg",
    "coverPicture": "",
    "description": "",
    "location": "Milano, Lombardia",
    "followers": 12449,
    "following": 229,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Thu Sep 12 06:24:52 +0000 2013",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 4858,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 443,
    "statusesCount": 1447,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "1800528441546031494"
    ],
    "profile_bio": {
      "description": "Associate Professor at Uni Milan-Bicocca. I write about social behaviour and AI.",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [],
          "user_mentions": []
        },
        "url": {
          "urls": [
            {
              "display_url": "caprarovalerio.com",
              "expanded_url": "http://caprarovalerio.com",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/zuMx6bmZwL"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.twitter.com/nsCNNyE2LE",
        "expanded_url": "https://twitter.com/ValerioCapraro/status/2032441725516411009/photo/1",
        "ext_media_availability": {
          "status": "Available"
        },
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2032441721099821057",
        "indices": [
          277,
          300
        ],
        "media_key": "3_2032441721099821057",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARw0rvoc1qABCgACHDSu+yQWcIEAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHDSu+hzWoAEKAAIcNK77JBZwgQAA",
            "media_key": "3_2032441721099821057"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HDSu-hzWoAEO85Z.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 655,
              "w": 1169,
              "x": 0,
              "y": 0
            },
            {
              "h": 852,
              "w": 852,
              "x": 246,
              "y": 0
            },
            {
              "h": 852,
              "w": 747,
              "x": 299,
              "y": 0
            },
            {
              "h": 852,
              "w": 426,
              "x": 459,
              "y": 0
            },
            {
              "h": 852,
              "w": 1169,
              "x": 0,
              "y": 0
            }
          ],
          "height": 852,
          "width": 1169
        },
        "sizes": {
          "large": {
            "h": 852,
            "w": 1169
          }
        },
        "type": "photo",
        "url": "https://t.co/nsCNNyE2LE"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "timestamps": [],
    "urls": [],
    "user_mentions": [
      {
        "id_str": "468764094",
        "indices": [
          1321,
          1330
        ],
        "name": "W. Quattrociocchi",
        "screen_name": "Walter4C"
      },
      {
        "id_str": "232294292",
        "indices": [
          1335,
          1346
        ],
        "name": "Gary Marcus",
        "screen_name": "GaryMarcus"
      }
    ]
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": null
}