🐦 Twitter Post Details

Viewing enriched Twitter post

@omarsar0

Regarding autoresearch agents, this question has attracted a lot of attention. Do research agents have taste? This has attracted massive interest because autoresearch agents could unlock major discoveries. This study gave six frontier models seven recent NLP papers, then ran every experiment they proposed, including the ones they ranked last. Of 415 experiments, 194 were judged sound, valuable, and new. Only 73 were also beyond the seed paper and non-obvious. The rankings added little. First choices beat a random pick, but they were not shown to beat the experiment written first. Forecasts beat a base rate, but they were not measurably better than a fresh instance of the same model that read only the paper and registrations. They tested with teams of agents, which cost more, with no clear improvement in proposal quality. https://t.co/wF4ajNDptV Chat with Paper: https://t.co/uokhb72MyB

Media 1

📊 Media Metadata

{
  "media": [
    {
      "type": "photo",
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2116204488562528713/media_0.jpg",
      "filename": "media_0.jpg"
    }
  ],
  "processed_at": "2026-10-30T17:02:57.611798",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2116204488562528713",
  "url": "https://x.com/omarsar0/status/2116204488562528713",
  "twitterUrl": "https://twitter.com/omarsar0/status/2116204488562528713",
  "text": "Regarding autoresearch agents, this question has attracted a lot of attention.\n\nDo research agents have taste?\n\nThis has attracted massive interest because autoresearch agents could unlock major discoveries.\n\nThis study gave six frontier models seven recent NLP papers, then ran every experiment they proposed, including the ones they ranked last.\n\nOf 415 experiments, 194 were judged sound, valuable, and new. Only 73 were also beyond the seed paper and non-obvious.\n\nThe rankings added little. First choices beat a random pick, but they were not shown to beat the experiment written first.\n\nForecasts beat a base rate, but they were not measurably better than a fresh instance of the same model that read only the paper and registrations.\n\nThey tested with teams of agents, which cost more, with no clear improvement in proposal quality.\n\nhttps://t.co/wF4ajNDptV\n\nChat with Paper: https://t.co/uokhb72MyB",
  "source": "",
  "retweetCount": 4,
  "replyCount": 14,
  "likeCount": 26,
  "quoteCount": 0,
  "viewCount": 2448,
  "createdAt": "Fri Oct 30 16:24:01 +0000 2026",
  "lang": "en",
  "bookmarkCount": 10,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2116204488562528713",
  "displayTextRange": [
    0,
    278
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "omarsar0",
    "url": "https://x.com/omarsar0",
    "twitterUrl": "https://twitter.com/omarsar0",
    "id": "3448284313",
    "name": "elvis",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/939313677647282181/vZjFWtAn_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/3448284313/1565974901",
    "description": "",
    "location": "DAIR.AI Academy",
    "followers": 326900,
    "following": 1359,
    "status": "",
    "canDm": true,
    "canMediaTag": true,
    "createdAt": "Fri Sep 04 12:59:26 +0000 2015",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 42133,
    "hasCustomTimelines": true,
    "isTranslator": true,
    "mediaCount": 5221,
    "statusesCount": 21056,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2115980498975551690"
    ],
    "profile_bio": {
      "description": "Building the frontier @dair_ai • Prev: Meta AI | Galactica LLM | Papers with Code | Elastic | PhD",
      "entities": {
        "description": {
          "user_mentions": [
            {
              "id_str": "",
              "indices": [
                22,
                30
              ],
              "name": "",
              "screen_name": "dair_ai"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "academy.dair.ai",
              "expanded_url": "https://www.academy.dair.ai/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/R5bOTNbyJW"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null,
    "protected": false
  },
  "extendedEntities": {
    "media": [
      {
        "display_url": "pic.x.com/aKxPOlYYA3",
        "expanded_url": "https://x.com/omarsar0/status/2116204488562528713/photo/1",
        "ext_master_playlist_only": [],
        "ext_media_availability": {
          "status": "Available"
        },
        "ext_playlists": [],
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2116204484477190146",
        "indices": [
          279,
          302
        ],
        "media_key": "3_2116204484477190146",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAAR1eRMQ5WgACCgACHV5ExSzbUckAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHV5ExDlaAAIKAAIdXkTFLNtRyQAA",
            "media_key": "3_2116204484477190146"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HV5ExDlaAAIMErD.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 909,
              "w": 1624,
              "x": 0,
              "y": 0
            },
            {
              "h": 1624,
              "w": 1624,
              "x": 0,
              "y": 0
            },
            {
              "h": 1851,
              "w": 1624,
              "x": 0,
              "y": 0
            },
            {
              "h": 1900,
              "w": 950,
              "x": 337,
              "y": 0
            },
            {
              "h": 1900,
              "w": 1624,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1900,
          "width": 1624
        },
        "sizes": {
          "large": {
            "h": 1900,
            "w": 1624
          }
        },
        "type": "photo",
        "url": "https://t.co/aKxPOlYYA3"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "arxiv.org/abs/2610.40488",
        "expanded_url": "https://arxiv.org/abs/2610.40488",
        "indices": [
          841,
          864
        ],
        "url": "https://t.co/wF4ajNDptV"
      },
      {
        "display_url": "academy.dair.ai/papers/rtaste-…",
        "expanded_url": "https://academy.dair.ai/papers/rtaste-do-research-agents-have-taste-evaluating-early-stage-research-judgment-2610.40488",
        "indices": [
          883,
          906
        ],
        "url": "https://t.co/uokhb72MyB"
      }
    ],
    "user_mentions": []
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}