{
  "type": "tweet",
  "id": "2026531440414925307",
  "url": "https://x.com/DimitrisPapail/status/2026531440414925307",
  "twitterUrl": "https://twitter.com/DimitrisPapail/status/2026531440414925307",
  "text": "https://t.co/plZjz8c3nu",
  "source": "Twitter for iPhone",
  "retweetCount": 78,
  "replyCount": 35,
  "likeCount": 900,
  "quoteCount": 36,
  "viewCount": 204488,
  "createdAt": "Wed Feb 25 05:35:21 +0000 2026",
  "lang": "zxx",
  "bookmarkCount": 956,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2026531440414925307",
  "displayTextRange": [
    0,
    23
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "DimitrisPapail",
    "url": "https://x.com/DimitrisPapail",
    "twitterUrl": "https://twitter.com/DimitrisPapail",
    "id": "573817445",
    "name": "Dimitris Papailiopoulos",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1733487310728024064/Ah_NBQlM_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/573817445/1697212820",
    "description": "",
    "location": "Madison, WI",
    "followers": 24927,
    "following": 1337,
    "status": "",
    "canDm": false,
    "canMediaTag": true,
    "createdAt": "Mon May 07 17:26:48 +0000 2012",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 12798,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 1047,
    "statusesCount": 9853,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2028669695344148946"
    ],
    "profile_bio": {
      "description": "Researcher @MSFTResearch, AI Frontiers Lab; Prof @UWMadison (on leave); reasoning in context; learning to remember; agent of agents; babas of Inez Lily.",
      "entities": {
        "description": {
          "hashtags": [],
          "symbols": [],
          "urls": [],
          "user_mentions": [
            {
              "id_str": "0",
              "indices": [
                11,
                24
              ],
              "name": "",
              "screen_name": "MSFTResearch"
            },
            {
              "id_str": "0",
              "indices": [
                49,
                59
              ],
              "name": "",
              "screen_name": "UWMadison"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "papail.io",
              "expanded_url": "http://papail.io",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/lQR1OLEMvU"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {},
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "timestamps": [],
    "urls": [
      {
        "display_url": "x.com/i/article/2026…",
        "expanded_url": "http://x.com/i/article/2026523085545857024",
        "indices": [
          0,
          23
        ],
        "url": "https://t.co/plZjz8c3nu"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "article": {
    "title": "You Don't Need to Run Every Eval",
    "preview_text": "I used Claude Code to build BenchPress a $0 benchmark prediction system, Codex to audit it for bugs, and Claude Sonnet to try to beat it for $1. Here's what I found: LLM evals are so low-rank (in fact",
    "cover_media_img_url": "https://pbs.twimg.com/media/HB-sUHUXYAA3O4X.jpg"
  }
}