🐦 Twitter Post Details

Viewing enriched Twitter post

@_wenlixiao

Autoresearch just left the sandbox and entered the embodied world. We are excited to introduce π„πππˆπ‘π„: a system that drops frontier coding agents onto a fleet of real robots and hands them the entire loop: reset the environment β†’ search the literature β†’ implement ideas and build the infra β†’ train and deploy β†’ self-verify β†’ analyze the logs and rewrite the code β†’ repeat, until the policy is reliable in the real world. No human in the loop. Guided only by the robot's self-proposed, heuristic-based success signal, the agents hill-climb to 99% on dexterous real-world tasks: organizing pins into a box, seating GPUs, tying zip-ties. We envision the bottleneck in robotics shifting β€” from building smarter algorithms to building the closed physical feedback loops an agent can finally turn on its own. πŸ”— https://t.co/3tL2ArGo3v From @NVIDIA @CMU_Robotics @Berkeley_AI 🧡

View on Twitter

πŸ“Š Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2066913044652015727/media_0.mp4",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2066913044652015727/media_0.mp4",
      "type": "video",
      "filename": "media_0.mp4"
    }
  ],
  "processed_at": "2026-06-16T16:35:16.031250",
  "pipeline_version": "2.0"
}

πŸ”§ Raw API Response

{
  "type": "tweet",
  "id": "2066913044652015727",
  "url": "https://x.com/_wenlixiao/status/2066913044652015727",
  "twitterUrl": "https://twitter.com/_wenlixiao/status/2066913044652015727",
  "text": "Autoresearch just left the sandbox and entered the embodied world.\n\nWe are excited to introduce π„πππˆπ‘π„: a system that drops frontier coding agents onto a fleet of real robots and hands them the entire loop:\n\nreset the environment β†’ search the literature β†’ implement ideas and build the infra β†’ train and deploy β†’ self-verify β†’ analyze the logs and rewrite the code β†’ repeat, until the policy is reliable in the real world. No human in the loop.\n\nGuided only by the robot's self-proposed, heuristic-based success signal, the agents hill-climb to 99% on dexterous real-world tasks: organizing pins into a box, seating GPUs, tying zip-ties.\n\nWe envision the bottleneck in robotics shifting β€” from building smarter algorithms to building the closed physical feedback loops an agent can finally turn on its own.\n\nπŸ”— https://t.co/3tL2ArGo3v\nFrom @NVIDIA @CMU_Robotics @Berkeley_AI\n🧡",
  "source": "Twitter for iPhone",
  "retweetCount": 5,
  "replyCount": 1,
  "likeCount": 19,
  "quoteCount": 7,
  "viewCount": 1531,
  "createdAt": "Tue Jun 16 15:57:25 +0000 2026",
  "lang": "en",
  "bookmarkCount": 6,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2066913044652015727",
  "displayTextRange": [
    0,
    271
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "_wenlixiao",
    "url": "https://x.com/_wenlixiao",
    "twitterUrl": "https://twitter.com/_wenlixiao",
    "id": "1160530286297305093",
    "name": "Wenli Xiao",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1935026078462132224/MTe2btEp_normal.jpg",
    "coverPicture": "",
    "description": "",
    "location": "Santa Clara, CA",
    "followers": 2162,
    "following": 661,
    "status": "",
    "canDm": false,
    "canMediaTag": true,
    "createdAt": "Sun Aug 11 12:35:56 +0000 2019",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 885,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 38,
    "statusesCount": 222,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "2066913044652015727"
    ],
    "profile_bio": {
      "description": "PhD Student at @CMU_Robotics | GEAR Lab @NvidiaAI | Physical AI & Robotics",
      "entities": {
        "description": {
          "user_mentions": [
            {
              "id_str": "",
              "indices": [
                15,
                28
              ],
              "name": "",
              "screen_name": "CMU_Robotics"
            },
            {
              "id_str": "",
              "indices": [
                40,
                49
              ],
              "name": "",
              "screen_name": "NvidiaAI"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "wenlixiao.com",
              "expanded_url": "https://www.wenlixiao.com",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/ktW81clqWT"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "additional_media_info": {
          "monetizable": true
        },
        "display_url": "pic.twitter.com/E3HgsguYXC",
        "expanded_url": "https://twitter.com/_wenlixiao/status/2066913044652015727/video/1",
        "ext_master_playlist_only": [],
        "ext_media_availability": {
          "status": "Available"
        },
        "ext_playlists": [],
        "id_str": "2066912976117059585",
        "indices": [
          272,
          295
        ],
        "media_key": "13_2066912976117059585",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwABAoAARyvJmabGlABAAA=",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAAECgABHK8mZpsaUAEAAA==",
            "media_key": "13_2066912976117059585"
          }
        },
        "media_url_https": "https://pbs.twimg.com/amplify_video_thumb/2066912976117059585/img/LMSWip5hYlp3UvXl.jpg",
        "original_info": {
          "focus_rects": [],
          "height": 1080,
          "width": 1920
        },
        "sizes": {
          "large": {
            "h": 1080,
            "w": 1920
          }
        },
        "type": "video",
        "url": "https://t.co/E3HgsguYXC",
        "video_info": {
          "aspect_ratio": [
            16,
            9
          ],
          "duration_millis": 75732,
          "variants": [
            {
              "content_type": "application/x-mpegURL",
              "url": "https://video.twimg.com/amplify_video/2066912976117059585/pl/srGpnCNbgzSQUUe7.m3u8?tag=14"
            },
            {
              "bitrate": 288000,
              "content_type": "video/mp4",
              "url": "https://video.twimg.com/amplify_video/2066912976117059585/vid/avc1/480x270/5-1bjnRNJbpsUl9R.mp4?tag=14"
            },
            {
              "bitrate": 832000,
              "content_type": "video/mp4",
              "url": "https://video.twimg.com/amplify_video/2066912976117059585/vid/avc1/640x360/4DbjfdUzfW3XFEiS.mp4?tag=14"
            },
            {
              "bitrate": 2176000,
              "content_type": "video/mp4",
              "url": "https://video.twimg.com/amplify_video/2066912976117059585/vid/avc1/1280x720/rb47KQwX3WvPac8z.mp4?tag=14"
            }
          ]
        }
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "timestamps": [],
    "urls": [
      {
        "display_url": "research.nvidia.com/labs/gear/enpi…",
        "expanded_url": "https://research.nvidia.com/labs/gear/enpire/",
        "indices": [
          810,
          833
        ],
        "url": "https://t.co/3tL2ArGo3v"
      }
    ],
    "user_mentions": [
      {
        "id_str": "61559439",
        "indices": [
          839,
          846
        ],
        "name": "NVIDIA",
        "screen_name": "NVIDIA"
      },
      {
        "id_str": "1137228224",
        "indices": [
          847,
          860
        ],
        "name": "CMU Robotics Institute",
        "screen_name": "CMU_Robotics"
      },
      {
        "id_str": "891077171673931776",
        "indices": [
          861,
          873
        ],
        "name": "Berkeley AI Research",
        "screen_name": "Berkeley_AI"
      }
    ]
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}