Viewing enriched Twitter post
Three Grok bots took four reference photos, built a physics simulator from them, ran 47 fracture experiments, rejected their own hypothesis, picked the best designs, sliced them, and 3D printed them. Images to physical object in one autonomous loop, steered from an Apple Watch.
{
"score": 0.34,
"score_components": {
"author": 0.09,
"engagement": 0.0,
"quality": 0.04000000000000001,
"source": 0.135,
"nlp": 0.05,
"recency": 0.025
},
"scored_at": "2026-08-22T20:06:08.547265",
"import_source": "api_import",
"source_tagged_at": "2026-08-22T20:06:08.547275",
"enriched": true,
"enriched_at": "2026-08-22T20:06:08.547276"
}{
"type": "tweet",
"id": "2091121277859979528",
"url": "https://x.com/tetsuoai/status/2091121277859979528",
"twitterUrl": "https://twitter.com/tetsuoai/status/2091121277859979528",
"text": "Three Grok bots took four reference photos, built a physics simulator from them, ran 47 fracture experiments, rejected their own hypothesis, picked the best designs, sliced them, and 3D printed them. Images to physical object in one autonomous loop, steered from an Apple Watch.",
"source": "Twitter for iPhone",
"retweetCount": 154,
"replyCount": 66,
"likeCount": 1127,
"quoteCount": 12,
"viewCount": 425149,
"createdAt": "Sat Aug 22 11:12:18 +0000 2026",
"lang": "en",
"bookmarkCount": 262,
"isReply": false,
"inReplyToId": null,
"conversationId": "2091121277859979528",
"displayTextRange": [
0,
278
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "tetsuoai",
"url": "https://x.com/tetsuoai",
"twitterUrl": "https://twitter.com/tetsuoai",
"id": "1587601034339561472",
"name": "tetsuo",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/2035289570598924288/kAOCyKpV_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/1587601034339561472/1787313336",
"description": "",
"location": "Neo Tokyo",
"followers": 237292,
"following": 786,
"status": "",
"canDm": true,
"canMediaTag": true,
"createdAt": "Wed Nov 02 00:22:51 +0000 2022",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 130641,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 2081,
"statusesCount": 3261,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"1943867358713659726"
],
"profile_bio": {
"description": "C and Assembly • Grok • AgenC //: 👾",
"entities": {
"description": {},
"url": {
"urls": [
{
"display_url": "agenc.ag",
"expanded_url": "http://agenc.ag",
"indices": [
0,
23
],
"url": "https://t.co/l9nJH6KPKL"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {},
"card": null,
"place": {},
"entities": {},
"quoted_tweet": {
"type": "tweet",
"id": "2091108225806454802",
"url": "https://x.com/ProfBuehlerMIT/status/2091108225806454802",
"twitterUrl": "https://twitter.com/ProfBuehlerMIT/status/2091108225806454802",
"text": "Grok @bot is incredible - and they can even manufacture real physical objects! Here is a little experiment I did last night: I created a team of bots and asked them to solve a complex engineering problem end to end - starting from four images as design cues, inferring transferable structural principles from the pixels, synthesizing an executable interactive physics simulator, running and reasoning over experiments, optimizing the design & finally manufacturing the best designs.\n\nThe entire loop worked remarkably well - and I was even able to communicate with the agents from my Apple Watch. (Do we live in the future yet?) \n\nTeam of agents\n\n1⃣ Chief of Staff coordinates the workflow: watches the other agents, pulls results into the main chat, transfers files between them, and keeps the job moving.\n2⃣ Physics Experimenter is the scientist-coder. It interprets the design cues and images, writes the simulator, runs experiments, analyzes the results, and produces a detailed LaTeX scientific report.\n3⃣ 3D Printing Bot operates the fabrication workflow: prepares and slices the models, generates manufacturing code, sends the job, and monitors the printer.\n\nThe workflow\n\nI provided an initial task based on four unregistered reference photographs containing different objects at different scales (pinnate leaf venation, a Voronoi-like areole mesh, a stochastic fibrous lattice, and a radial/circumferential web).\n\nThe prompt asked the agents to infer transferable design principles - hierarchy, branching, interfaces, redundancy, disorder, load paths - and use them to build an interactive laboratory for hierarchical materials and fracture.\n\nThe scientific question was: at fixed material budget, how do hierarchy depth, redundancy, disorder, and interlevel strength change stiffness, peak load, energy absorption, and the brittle-to-progressive transition?\n\nIn ~20 minutes, the Physics Experimenter produced a 2D hierarchical Euler–Bernoulli beam-network laboratory. Coarse veins persist and remain thicker; finer infill is added inside cells; members connecting levels are treated as interfaces with relative strength κ; and total material volume is conserved. The four source photographs remain visible in an editable interpretation panel. The app generates geometry, steps or runs the network to failure, compares A/B/C designs, and exports JSON, CSV, PNG, and STL geometry for fabrication.\n\nAfter validation the Physics Experimenter used the app and conducted 47 simulation experiments, including six holdouts.\n\nIt found something scientifically interesting: extra hierarchy is not \"free\" toughness. At fixed volume, initial stiffness changed by only about 20%, while work-to-failure varied by several-fold. Infill steals cross-section from the main axial veins, so deeper and more redundant networks often absorbed less energy than a simple depth-1 grid. Weak interfaces behaved as distributed fuses, producing more progressive failure and reducing localization. The specific H2 hypothesis - that hierarchy becomes detrimental primarily because interfaces form a mechanical bottleneck - was rejected; the dominant effect instead came from redistribution of a fixed material budget across structural levels.\n\nThe Physics Experimenter then assembled the methods, tests, results, hypothesis evaluation, and conclusions into a detailed scientific report.\n\nThe best designs were passed to the 3D Printing Bot. It opened Bambu Studio and brought the Bambu Lab H2D online. Both STLs were placed on one build plate at the same 50x scale and sliced using a 0.20 mm PLA process. The prints completed within less than an hour.\n\nThe loop \n\nimages → structural abstraction → executable physics → autonomous experiments → hypothesis testing → design selection → STL → slicing/manufacturing code → physical object\n\nThat last transition is what I find especially interesting: AI is beginning to operate across the entire scientific and physical workflow - converting observations into models, models into experiments, experimental evidence into revised designs, and those designs into manufactured matter by directly operating machines. This starts to blur the boundary between AI that reasons about the physical world and AI that can actually act on it. \n\nShoutout to the @bot team - you are building something very special here! The way these agents can move naturally from reasoning, to experiments, to operating machines in the physical world feels like an important step.",
"source": "Twitter for iPhone",
"retweetCount": 69,
"replyCount": 45,
"likeCount": 525,
"quoteCount": 37,
"viewCount": 561314,
"createdAt": "Sat Aug 22 10:20:26 +0000 2026",
"lang": "en",
"bookmarkCount": 402,
"isReply": false,
"inReplyToId": null,
"conversationId": "2091108225806454802",
"displayTextRange": [
0,
268
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "ProfBuehlerMIT",
"url": "https://x.com/ProfBuehlerMIT",
"twitterUrl": "https://twitter.com/ProfBuehlerMIT",
"id": "2915980918",
"name": "Markus J. Buehler",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1133792154181021696/vn_-rmPd_normal.png",
"coverPicture": "https://pbs.twimg.com/profile_banners/2915980918/1418395608",
"description": "",
"location": "Cambridge, MA",
"followers": 21617,
"following": 2367,
"status": "",
"canDm": false,
"canMediaTag": true,
"createdAt": "Thu Dec 11 18:10:28 +0000 2014",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 21861,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 1269,
"statusesCount": 6940,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [
"2091108225806454802"
],
"profile_bio": {
"description": "McAfee Professor of Engineering @MIT; Co-Founder & CTO at Unreasonable Labs; AI-Driven Scientific Discovery",
"entities": {
"description": {},
"url": {
"urls": [
{
"display_url": "meche.mit.edu/people/faculty…",
"expanded_url": "https://meche.mit.edu/people/faculty/mbuehler@mit.edu",
"indices": [
0,
23
],
"url": "https://t.co/YY10ChEC0W"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"additional_media_info": {
"monetizable": false
},
"display_url": "pic.x.com/oYKlSTmb1A",
"expanded_url": "https://x.com/ProfBuehlerMIT/status/2091108225806454802/video/1",
"ext_media_availability": {
"status": "Available"
},
"id_str": "2091106938486505473",
"indices": [
269,
292
],
"media_key": "13_2091106938486505473",
"media_results": {
"result": {
"media_key": "13_2091106938486505473"
}
},
"media_url_https": "https://pbs.twimg.com/amplify_video_thumb/2091106938486505473/img/pTYUBPI04_3cUezV.jpg",
"original_info": {
"focus_rects": [],
"height": 1080,
"width": 1920
},
"sizes": {
"large": {
"h": 1080,
"resize": "fit",
"w": 1920
},
"medium": {
"h": 675,
"resize": "fit",
"w": 1200
},
"small": {
"h": 383,
"resize": "fit",
"w": 680
},
"thumb": {
"h": 150,
"resize": "crop",
"w": 150
}
},
"type": "video",
"url": "https://t.co/oYKlSTmb1A",
"video_info": {
"aspect_ratio": [
16,
9
],
"duration_millis": 181166,
"variants": [
{
"content_type": "application/x-mpegURL",
"url": "https://video.twimg.com/amplify_video/2091106938486505473/pl/I2uPrjhXnlJDkg_G.m3u8?tag=29&v=cfc"
},
{
"bitrate": 256000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2091106938486505473/vid/avc1/480x270/wTKWAR7US7NgPlau.mp4?tag=29"
},
{
"bitrate": 832000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2091106938486505473/vid/avc1/640x360/DUHlq0iRKQnF71XX.mp4?tag=29"
},
{
"bitrate": 2176000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2091106938486505473/vid/avc1/1280x720/2az3iC9G7RDtdz-y.mp4?tag=29"
},
{
"bitrate": 10368000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2091106938486505473/vid/avc1/1920x1080/azAvzyAZrH_NjGFi.mp4?tag=29"
}
]
}
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [],
"smarttags": [],
"symbols": [],
"timestamps": [],
"urls": [],
"user_mentions": [
{
"id_str": "2085838061347217408",
"indices": [
5,
9
],
"name": "Grok Bot",
"screen_name": "bot"
},
{
"id_str": "2085838061347217408",
"indices": [
4273,
4277
],
"name": "Grok Bot",
"screen_name": "bot"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"article": null
},
"retweeted_tweet": null,
"article": null
}