π¦ Twitter Post Details
Viewing enriched Twitter post
π Media Metadata
{
"media": [
{
"url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2067304433843863618/media_0.jpg",
"media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2067304433843863618/media_0.jpg",
"type": "photo",
"filename": "media_0.jpg"
}
],
"processed_at": "2026-06-17T18:05:28.470936",
"pipeline_version": "2.0"
} π§ Raw API Response
{
"type": "tweet",
"id": "2067304433843863618",
"url": "https://x.com/DrJimFan/status/2067304433843863618",
"twitterUrl": "https://twitter.com/DrJimFan/status/2067304433843863618",
"text": "https://t.co/4aVgLYY50L",
"source": "Twitter for iPhone",
"retweetCount": 0,
"replyCount": 0,
"likeCount": 3,
"quoteCount": 0,
"viewCount": 1351,
"createdAt": "Wed Jun 17 17:52:40 +0000 2026",
"lang": "zxx",
"bookmarkCount": 0,
"isReply": true,
"inReplyToId": "2066921739087729043",
"conversationId": "2066921736369766762",
"displayTextRange": [
0,
23
],
"inReplyToUserId": "1007413134",
"inReplyToUsername": "DrJimFan",
"author": {
"type": "user",
"userName": "DrJimFan",
"url": "https://x.com/DrJimFan",
"twitterUrl": "https://twitter.com/DrJimFan",
"id": "1007413134",
"name": "Jim Fan",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1554922493101559808/SYSZhbcd_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1007413134/1672408318",
"description": "",
"location": "Views my own. Contact β",
"followers": 457829,
"following": 3134,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Wed Dec 12 22:11:27 +0000 2012",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 8847,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 853,
"statusesCount": 4196,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2052758642781487237"
],
"profile_bio": {
"description": "NVIDIA Director of Robotics & Distinguished Scientist. Co-Lead of GEAR lab. Solving Physical AGI, one motor at a time. Stanford Ph.D. OpenAI's 1st intern.",
"entities": {
"description": {},
"url": {
"urls": [
{
"display_url": "jimfan.me",
"expanded_url": "https://jimfan.me",
"indices": [
0,
23
],
"url": "https://t.co/H4rXo4Ei8X"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {
"urls": [
{
"display_url": "x.com/DrJimFan/statuβ¦",
"expanded_url": "https://x.com/DrJimFan/status/2067283904986517866?s=20",
"indices": [
0,
23
],
"url": "https://t.co/4aVgLYY50L"
}
]
},
"quoted_tweet": {
"type": "tweet",
"id": "2067283904986517866",
"url": "https://x.com/DrJimFan/status/2067283904986517866",
"twitterUrl": "https://twitter.com/DrJimFan/status/2067283904986517866",
"text": "I made Physical AutoResearch sound simple (conceptually), but it took a village to pull off and lots of design thinking into the robot /loopcraft. The hardest part is everything we need to setup *before* pressing Enter. Here's a behind-the-scene tour:\n\n1. Safety harness\n\nLetting 8 robots run unattended overnight means safety has to be more than a hint in the system prompt. ENPIRE hardwires it in 2 layers: (1) hard kinematic limit that trips an immediate task failure and auto-resets as soon as a robot leaves its safety envelope, and (2) a torque-limited compliant gripper so a bad contact or misaligned insertion ends in a safe stall, instead of crushing the robot or the object at hand. \n\nWe make safety more conservative than usual so humans can sleep tight. In reality, we still need a few human operators to watch over the \"robots of loving grace\". \n\n2. Definition of /done\n\nAn agent that can edit its own reward will game it for sure. ENPIRE fixes the goalposts before the fleet can move them. Here's the recipe:\n\nCollect a few minutes of success & failure demos\n-> Ask agent to write code using computer vision tools to classify success and measure against groundtruth\n-> Agent hill-climbs on classifier until reliably good\n-> This classifier becomes the real-time reward function that directly computes on sensor streams \n-> *Freeze* the reward function before AutoResearch. It's sacred, enshrined in a Gym env that no one can touch.\n\n3. System telemetry design\n\nRobot-seconds is by far the scarcest resource, followed by GPU-seconds, and finally tokens. We instrument all three and surface them to ENPIRE for live resource awareness rather than letting it hill-climb in a vacuum. \n\nWe define:\n- Mean Robot Utilization (\"MRU\"): the fraction of wall-clock time when the robot is actively executing an experiment. Otherwise the hardware is sitting idle and waiting for the next code commit.\n- Mean Token Utilization (\"MTU\"): tokens consumed per minute, our proxy for how hard the agent is actually thinking. A low MTU means the agent is stalled, waiting on a robot rollout to finish instead of doing research.\n- GPU utilization: fraction of wall-clock time when GPU is active. \n\n... and evaluate on two budget-to-outcome metrics:\n\n1. Tokens-to-Success: token budget the fleet burns to complete /goal.\n2. Time-to-Success: wall-clock time to /goal",
"source": "Twitter for iPhone",
"retweetCount": 16,
"replyCount": 12,
"likeCount": 193,
"quoteCount": 3,
"viewCount": 16280,
"createdAt": "Wed Jun 17 16:31:05 +0000 2026",
"lang": "en",
"bookmarkCount": 105,
"isReply": false,
"inReplyToId": null,
"conversationId": "2067283904986517866",
"displayTextRange": [
0,
279
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "DrJimFan",
"url": "https://x.com/DrJimFan",
"twitterUrl": "https://twitter.com/DrJimFan",
"id": "1007413134",
"name": "Jim Fan",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1554922493101559808/SYSZhbcd_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1007413134/1672408318",
"description": "",
"location": "Views my own. Contact β",
"followers": 457829,
"following": 3134,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Wed Dec 12 22:11:27 +0000 2012",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 8847,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 853,
"statusesCount": 4196,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2052758642781487237"
],
"profile_bio": {
"description": "NVIDIA Director of Robotics & Distinguished Scientist. Co-Lead of GEAR lab. Solving Physical AGI, one motor at a time. Stanford Ph.D. OpenAI's 1st intern.",
"entities": {
"description": {},
"url": {
"urls": [
{
"display_url": "jimfan.me",
"expanded_url": "https://jimfan.me",
"indices": [
0,
23
],
"url": "https://t.co/H4rXo4Ei8X"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"additional_media_info": {
"monetizable": true
},
"allow_download_status": {
"allow_download": true
},
"display_url": "pic.twitter.com/P7sfwHf7wo",
"expanded_url": "https://twitter.com/DrJimFan/status/2067283904986517866/video/1",
"ext_master_playlist_only": [],
"ext_media_availability": {
"status": "Available"
},
"ext_playlists": [],
"id_str": "2067270848499851264",
"indices": [
280,
303
],
"media_key": "13_2067270848499851264",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwABAoAARywa+JDWqAAAAA=",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAAECgABHLBr4kNaoAAAAA==",
"media_key": "13_2067270848499851264"
}
},
"media_url_https": "https://pbs.twimg.com/amplify_video_thumb/2067270848499851264/img/YbR2gWhtS9T_6Ebk.jpg",
"original_info": {
"focus_rects": [],
"height": 1080,
"width": 1920
},
"sizes": {
"large": {
"h": 1080,
"w": 1920
}
},
"type": "video",
"url": "https://t.co/P7sfwHf7wo",
"video_info": {
"aspect_ratio": [
16,
9
],
"duration_millis": 42483,
"variants": [
{
"content_type": "application/x-mpegURL",
"url": "https://video.twimg.com/amplify_video/2067270848499851264/pl/jqkJoLGODhd6pItC.m3u8?tag=28"
},
{
"bitrate": 256000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2067270848499851264/vid/avc1/480x270/u1L3tWnvS1FP74Ya.mp4?tag=28"
},
{
"bitrate": 832000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2067270848499851264/vid/avc1/640x360/tJkiQDxz9W1lAj3T.mp4?tag=28"
},
{
"bitrate": 2176000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2067270848499851264/vid/avc1/1280x720/xC7ByL-2z0EMxHrd.mp4?tag=28"
},
{
"bitrate": 10368000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2067270848499851264/vid/avc1/1920x1080/TjQcTQHBN_ugg7Yw.mp4?tag=28"
}
]
}
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": []
},
"quoted_tweet": {
"type": "tweet",
"id": "2066921736369766762",
"url": "",
"twitterUrl": "",
"text": "",
"source": "Twitter for iPhone",
"retweetCount": 0,
"replyCount": 0,
"likeCount": 0,
"quoteCount": 0,
"viewCount": 0,
"createdAt": "",
"lang": "",
"bookmarkCount": 0,
"isReply": false,
"inReplyToId": null,
"conversationId": "",
"displayTextRange": [],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
},
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
},
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
}