{ "meta": { "built": "2026-08-31T07:06:17.259Z", "as_of": "2026-08-31", "ti": 172.1, "counts": { "problems": 7, "categories": 14, "components": 44, "indicators": 159, "sources": 248 }, "method": "Every reading is the weight-weighted roll-up of what sits below it. See spec 07 §1." }, "problems": [ { "id": "materials", "pres": "hero", "pal": "materials", "name": "MATERIALS", "mission": "Establishing what a body has to be made of.", "reading": 35.8, "scale": 600, "state": "INDEPENDENT", "moved": "4 WEEKS AGO", "rec": "warm", "kicker": "MATERIALS", "big": "35.8", "bigLabel": "FAMILY READING", "plate": "PLATE 02", "worstComponent": { "id": "self-healing-materials", "name": "Self-healing materials", "factor": 10000000 }, "componentCount": 9, "weight": 58, "kids": [ { "id": "cat-chassis-and-materials", "pres": "card", "name": "Chassis & materials", "meta": "3 COMPONENTS", "reading": 61.6, "scale": 600, "state": "MORE EFFORTS", "moved": "4 WEEKS AGO", "rec": "warm", "blurb": "A skeleton that survives what kills the flesh. Taking sustained gunfire and continuing to walk.", "factLeft": "3 COMPONENTS", "factMid": "9 INDICATORS", "factRight": "WEIGHT 19 OF 313", "footMeta": "3 COMPONENTS · 9 INDICATORS\nWEIGHT 19 OF 313", "weight": 19, "progress": 0.06157894736842105, "kids": [ { "id": "hyperalloy-combat-chassis", "pres": "leaf", "name": "Hyperalloy combat chassis", "reading": 0.093, "scale": 1, "state": "MORE EFFORTS", "moved": "7 MONTHS AGO", "rec": "mid", "factor": 943.3962264150944, "short": "943× short", "canon": "A bipedal, fully armoured, human-scale structural skeleton machined from an unspecified 'hyperalloy', carrying every actuator, the power cell and the processor, and supporting a living-tissue envelope. It must remain fully operational - walking, aiming, gripping - after total loss of that envelope to fire. Canon defines the material entirely by what fails to destroy it; its composition is never given.", "real": "The alloys exist; the machine does not. Nobody has built a humanoid frame designed to survive fire, blast or impact, because there is no market for one. More fundamentally, a frame that survives 1,500 C is useless when the neodymium-iron-boron magnets, bearing lubricants, wire insulation, elastomer seals and silicon it carries all fail between roughly 150 C and 400 C.", "realVal": "40 degC", "canonVal": "1500 degC", "footMeta": "TRL 7 · WEIGHT 8 OF 10\nREVIEWED EVERY 30 DAYS\n3 INDICATORS · 4 SOURCES", "indicators": [ { "metric": "Rated maximum ambient operating temperature, best production humanoid", "unit": "degC", "value": 40, "canon_target": 1500, "as_of": "2026-01-05", "source": "https://bostondynamics.com/blog/boston-dynamics-unveils-new-atlas-robot-to-revolutionize-industry/" }, { "metric": "Yield strength of best refractory high-entropy alloy at 1600 degC", "unit": "MPa", "value": 571, "canon_target": 571, "as_of": "2022-10-17", "source": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9586648/" }, { "metric": "Longest continuous walking distance by a humanoid without power-down", "unit": "km", "value": 106, "canon_target": 100000, "as_of": "2025-11-24", "source": "https://www.upi.com/Odd_News/2025/11/24/AgiBot-A2-Guinness-World-Records-robot-walk/3681764010764" } ], "sources": [ { "date": "2026-01-24", "org": "HUMANOIDS DAILY", "text": "Production Atlas specifications reported as 1.9 m, 90 kg, IP67, 50 kg instantaneous and 30 kg sustained payload, approximately 4 hours on dual self-swappable batteries.", "kind": "PRIMARY", "url": "https://www.humanoidsdaily.com/news/the-alien-in-the-factory-boston-dynamics-launches-production-ready-atlas-at-ces-2026", "submitter": null }, { "date": "2026-01-05", "org": "BOSTON DYNAMICS", "text": "Boston Dynamics unveiled the production Atlas: 56 degrees of freedom with fully rotational joints, 2.3 m reach, 50 kg lift, rated -20 C to +40 C, extremely water-resistant, entering production immediately.", "kind": "PRIMARY", "url": "https://bostondynamics.com/blog/boston-dynamics-unveils-new-atlas-robot-to-revolutionize-industry/", "submitter": null }, { "date": "2025-11-24", "org": "UPI", "text": "AgiBot's A2 humanoid walked 106 km from Suzhou to Shanghai over 56 hours without powering down, using 15 hot battery swaps, taking the Guinness record for longest journey walked by a humanoid robot.", "kind": "PRIMARY", "url": "https://www.upi.com/Odd_News/2025/11/24/AgiBot-A2-Guinness-World-Records-robot-walk/3681764010764", "submitter": null }, { "date": "2022-10-17", "org": "SCIENCE AND TECHNOLOGY OF ADVANCED MATERIALS 23:642-654", "text": "HfMoNbTaW refractory high-entropy alloy achieves 571 MPa yield strength at 1600 C, against approximately 400 MPa for earlier MoNbTaW and MoNbTaVW compositions.", "kind": "PEER REVIEWED", "url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9586648/", "submitter": null } ], "movers": [ "Boston Dynamics", "Beijing Institute of Technology / Xi'an Jiaotong (HfMoNbTaW RHEA authors)", "Oak Ridge National Laboratory", "AgiBot" ], "commentary": "The franchise sold the alloy as the hard part. It is not. Refractory high-entropy alloys have held 571 megapascals at 1,600 degrees since 2022, and titanium at 900 megapascals and 4.4 grams per cubic centimetre has been routine since the 1950s. What fails in a steel mill is everything the frame is carrying: neodymium magnets, bearing grease, wire insulation and silicon, all of which surrender between 150 and 400 degrees. The most capable humanoid in production is rated from minus twenty to plus forty and sealed to IP67, which keeps water out and heat in. The metallurgy arrived decades ago. The machine did not.", "weight": 8, "progress": 0.0933 }, { "id": "armor-and-ballistic-survivability", "pres": "leaf", "name": "Armor and ballistic survivability", "reading": 0.06, "scale": 1, "state": "MORE EFFORTS", "moved": "3 YEARS AGO", "rec": "cool", "factor": 33.333333333333336, "short": "33× short", "canon": "Defeat sustained, multi-shooter small-arms fire from contact range to ~25 m with no loss of mobility, aim or mission tempo. Rounds deform against the chassis rather than penetrate it. The living tissue is consumable; the chassis is not. Canon is careful to show the one infantry weapon that does work: a 40 mm grenade, and only temporarily.", "real": "Coverage, mass and multi-hit capacity, in that order. Ceramic armour defeats a rifle round by shattering, so protection is consumed where it is used; the canon requirement is protection that is not consumed. Nothing in the fielded inventory protects joints, and joints are where a humanoid is stopped.", "realVal": "32.6 kg/m2", "canonVal": "5 kg/m2", "footMeta": "TRL 9 · WEIGHT 7 OF 10\nREVIEWED EVERY 60 DAYS\n3 INDICATORS · 3 SOURCES", "indicators": [ { "metric": "Areal density of fielded rifle-threat armour (ESAPI medium)", "unit": "kg/m2", "value": 32.6, "canon_target": 5, "as_of": "2026-08-29", "source": "https://en.wikipedia.org/wiki/Small_Arms_Protective_Insert" }, { "metric": "Rated multi-hit capacity per rifle-threat plate", "unit": "hits", "value": 3, "canon_target": 100, "as_of": "2026-08-29", "source": "https://en.wikipedia.org/wiki/Small_Arms_Protective_Insert" }, { "metric": "Mass of whole-body RF3-equivalent coverage over 1.8 m2", "unit": "kg", "value": 59, "canon_target": 10, "as_of": "2026-08-29", "source": "https://en.wikipedia.org/wiki/Small_Arms_Protective_Insert" } ], "sources": [ { "date": "2026-08-29", "org": "WIKIPEDIA (COMPILED FROM US ARMY SPECIFICATIONS)", "text": "Fielded ESAPI plates mass 2.50 kg for a medium at 241 x 318 mm and are rated against .30-06 M2 armour-piercing; the preceding SAPI generation was rated for survivability of three hits of the marked round.", "kind": "PRIMARY", "url": "https://en.wikipedia.org/wiki/Small_Arms_Protective_Insert", "submitter": null }, { "date": "2026-08-29", "org": "WIKIPEDIA", "text": "NIJ 0101.07 rifle levels map to specific threats: RF1 to 7.62x51 M80, 7.62x39 MSC and 5.56 M193; RF2 adds 5.56 M855; RF3 to .30-06 M2 AP. No areal density or shot-count requirement is specified by the standard itself.", "kind": "STANDARD", "url": "https://en.wikipedia.org/wiki/List_of_body_armor_performance_standards", "submitter": null }, { "date": "2023-11-01", "org": "NATIONAL INSTITUTE OF JUSTICE", "text": "NIJ Standard 0123.00 defines the current ballistic protection levels HG1, HG2, RF1, RF2 and RF3, with RF3 tested against .30-06 M2 armour-piercing at 2,880 ft/s (878 m/s). Addenda issued 2025-07-08.", "kind": "STANDARD", "url": "https://nij.ojp.gov/topics/equipment-and-technology/specification-nij-ballistic-protection-levels-and-associated-test-threats-nij-standard-012300", "submitter": null } ], "movers": [ "National Institute of Justice", "US Army PEO Soldier", "DSM / Avient (Dyneema)" ], "commentary": "Fielded, mature, two decades in service, and still nowhere near. An ESAPI plate stops a .30-06 armour-piercing round at 32.6 kilograms per square metre, and the generation it replaced was rated for three hits. Cover an adult's 1.8 square metres at that density and you have carried 59 kilograms of ceramic, two-thirds of the entire mass of a production Atlas, to buy perhaps seventy idealised hits distributed perfectly, which incoming fire never is. Canon asks for several hundred anywhere on the body with no loss of function. Readiness level nine, specification fraction six per cent. The two numbers are not in tension.", "weight": 7, "progress": 0.06 }, { "id": "mimetic-polyalloy", "pres": "leaf", "name": "Mimetic polyalloy", "reading": 0.001, "scale": 1, "state": "NOT ON TRACK", "moved": "4 WEEKS AGO", "rec": "warm", "factor": 70000, "short": "70,000× short", "canon": "A single homogeneous metallic material that holds arbitrary human-scale form at sub-millimetre fidelity (face, clothing texture, a police badge); reversibly transitions between fluid and rigid load-bearing solid on command; reintegrates severed mass; conserves total mass; and CANNOT produce chemically heterogeneous or multi-part mechanisms. The exclusions are stated in dialogue and are as important as the capabilities.", "real": "Scale, autonomy and every function that is not shape change. No demonstrated system carries its own power, its own actuation, its own sensing or any computation; all of them are puppets of an external field or an external robot arm. None mimics appearance. None is load-bearing at human scale in a reconfigurable state.", "realVal": "1 g", "canonVal": "70000 g", "footMeta": "TRL 4 · WEIGHT 4 OF 10\nREVIEWED EVERY 45 DAYS\n3 INDICATORS · 4 SOURCES", "indicators": [ { "metric": "Mass of largest self-actuating phase-transitional robot", "unit": "g", "value": 1, "canon_target": 70000, "as_of": "2023-01-25", "source": "https://doi.org/10.1016/j.matt.2022.12.003" }, { "metric": "Solid-phase strength of phase-transitional matter", "unit": "MPa", "value": 21.2, "canon_target": 500, "as_of": "2023-01-25", "source": "https://doi.org/10.1016/j.matt.2022.12.003" }, { "metric": "Reversible shape-memory cycles demonstrated in a liquid-metal robot", "unit": "cycles", "value": 100, "canon_target": 100000, "as_of": "2026-06-01", "source": "https://doi.org/10.1016/j.matt.2026.102759" } ], "sources": [ { "date": "2026-08-04", "org": "ARXIV (ACADIA 2026)", "text": "Self-aligning compound nested lattice modules interlocking on three axes were assembled by robot arms and mobile assemblers into furniture- and architectural-scale structures, reaching 4,556 N/mm stiffness and 3,445 N maximum load; assembly is performed by external robots, not by the modules themselves.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2608.07576", "submitter": null }, { "date": "2026-06-01", "org": "MATTER 9:102759, DOI 10.1016/J.MATT.2026.102759", "text": "A liquid metal shape memory robot achieves programmable deformation with automatic reversible shape recovery: 90 percent volumetric compression ratio, over 100 one-way shape-memory cycles, deformation at temperatures above 220 C, and recovery within 50 seconds.", "kind": "PEER REVIEWED", "url": "https://doi.org/10.1016/j.matt.2026.102759", "submitter": null }, { "date": "2026-02-25", "org": "SCIENCE ROBOTICS 11, DOI 10.1126/SCIROBOTICS.ADZ1999", "text": "A Science Robotics review of modular reconfigurable robots concludes the field has progressed from laboratory settings toward real-world applications, but that general hardware challenges, general software challenges and application-specific challenges all remain open.", "kind": "PEER REVIEWED", "url": "https://pubmed.ncbi.nlm.nih.gov/41739909/", "submitter": null }, { "date": "2023-01-25", "org": "MATTER 6(3):855-872, DOI 10.1016/J.MATT.2022.12.003", "text": "Magnetoactive phase transitional matter (neodymium-iron-boron microparticles in gallium, melting point 29.8 C) achieves 21.2 MPa strength and 1.98 GPa stiffness in the solid phase, bears 30 times its own weight, and flows at up to 15 cm/s in the liquid phase; demonstrators are millimetre-scale and externally actuated by magnetic field.", "kind": "PEER REVIEWED", "url": "https://doi.org/10.1016/j.matt.2022.12.003", "submitter": null } ], "movers": [ "Carnegie Mellon University (Majidi group)", "Sun Yat-sen University (Jiang group)", "Wuhan University (Fu Lei group)", "MIT Center for Bits and Atoms (Gershenfeld)", "University of Pennsylvania / EPFL / University of Macau" ], "commentary": "The T-1000 remains the index's cleanest reminder of what fiction costs. The best load-bearing phase-transitional matter in the literature is neodymium-iron-boron suspended in gallium: 21 megapascals, thirty times its own weight, fifteen centimetres per second liquid, and about one gram, driven entirely by an external magnetic field. June's Matter paper adds reversible shape memory over a hundred cycles at a hundredth the required scale. Against a self-powered seventy-kilogram humanoid that reassembles from a puddle, the mass ratio alone is one in a hundred thousand, before onboard power, sensing or cognition. Half the popular coverage reports the load figure as thirty kilograms. It is not.", "weight": 4, "progress": 0.0009 } ] }, { "id": "cat-biology-and-camouflage", "pres": "card", "name": "Biology & camouflage", "meta": "3 COMPONENTS", "reading": 27.5, "scale": 600, "state": "MORE EFFORTS", "moved": "5 MONTHS AGO", "rec": "mid", "blurb": "Dogs can smell them. So can a thermal camera, and for better reasons. Roughly 2.3 square metres of living human skin, grown, and worn by a machine.", "factLeft": "3 COMPONENTS", "factMid": "10 INDICATORS", "factRight": "WEIGHT 20 OF 313", "footMeta": "3 COMPONENTS · 10 INDICATORS\nWEIGHT 20 OF 313", "weight": 20, "progress": 0.027505, "kids": [ { "id": "signature-management", "pres": "leaf", "name": "Signature management", "reading": 0.053, "scale": 1, "state": "NOT ON TRACK", "moved": "2 YEARS AGO", "rec": "cool", "factor": 2.6363636363636362, "short": "3× short", "canon": "Match a human's olfactory, thermal, acoustic and electromagnetic signature closely enough to defeat human observers indefinitely - while canon EXPLICITLY DOCUMENTS ITS OWN FAILURE against canine olfaction.", "real": "Heat and smell. Adaptive infrared skins can change what a machine looks like to a thermal camera but remove no energy; a machine producing a kilowatt still produces a kilowatt and its surface must sit tens of degrees above human skin temperature to shed it. On odour, human scent is a stable individual chemical fingerprint of 60-plus skin volatiles produced by lipid oxidation, protein turnover, sebaceous secretion and the skin microbiome. A machine can carry a perfume; it cannot carry a metabolism.", "realVal": "1.14 ppt", "canonVal": "1.14 ppt", "footMeta": "TRL 4 · WEIGHT 5 OF 10\nREVIEWED EVERY 60 DAYS\n3 INDICATORS · 6 SOURCES", "indicators": [ { "metric": "Best published canine olfactory detection threshold for a reference odorant", "unit": "ppt", "value": 1.14, "canon_target": 1.14, "as_of": "2006-05-01", "source": "https://doi.org/10.1016/j.applanim.2005.07.009" }, { "metric": "Skin temperature required to reject 1 kW radiatively from 1.9 m2 at 20 C ambient", "unit": "degC", "value": 87, "canon_target": 33, "as_of": "2026-08-29", "source": "https://pmc.ncbi.nlm.nih.gov/articles/PMC4013926/" }, { "metric": "Distinct human skin volatile organic compounds a machine would have to reproduce", "unit": "compounds", "value": 64, "canon_target": 0, "as_of": "2014-05-01", "source": "https://pmc.ncbi.nlm.nih.gov/articles/PMC4013926/" } ], "sources": [ { "date": "2025-01-22", "org": "ARXIV", "text": "Strong nonreciprocal thermal emission was observed experimentally, breaking the equivalence of emissivity and absorptivity imposed by Kirchhoff's law — new physics for directional thermal signature engineering, though it removes no heat.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2501.12947", "submitter": null }, { "date": "2019-01-22", "org": "FRONTIERS IN VETERINARY SCIENCE", "text": "Ten dogs tested in a blinded eight-choice carousel showed olfactory detection thresholds for amyl acetate in liquid phase ranging from 30 parts per billion down to 1.5 parts per trillion, with some dogs roughly 30-fold more sensitive than previously reported, and considerable inter-dog variation.", "kind": "PEER REVIEWED", "url": "https://doi.org/10.3389/fvets.2018.00345", "submitter": null }, { "date": "2018-07-11", "org": "NANO LETTERS", "text": "Electrically tunable infrared emissivity was demonstrated by intercalating ionic liquid into multilayer graphene, allowing an object's apparent thermal signature to be varied on demand — the reference demonstration for adaptive thermal camouflage.", "kind": "PEER REVIEWED", "url": "https://pubmed.ncbi.nlm.nih.gov/29947216/", "submitter": null }, { "date": "2014-05-01", "org": "JOURNAL OF CHROMATOGRAPHY B", "text": "64 C4-C10 volatile organic compounds were identified and quantified in skin emanations from 31 healthy volunteers, predominantly aldehydes and hydrocarbons — the inventory a machine would have to reproduce continuously to pass an olfactory check.", "kind": "PEER REVIEWED", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC4013926/", "submitter": null }, { "date": "2007-04-22", "org": "JOURNAL OF THE ROYAL SOCIETY INTERFACE", "text": "GC-MS analysis of axillary sweat, urine and saliva from 197 adults, with five sweat samples per subject over ten weeks, established that individuals carry a stable and distinctive chemical odour fingerprint.", "kind": "PEER REVIEWED", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC2359862/", "submitter": null }, { "date": "2006-05-01", "org": "APPLIED ANIMAL BEHAVIOUR SCIENCE", "text": "Under naturalistic field-testing conditions, dogs detected n-amyl acetate at olfactory thresholds of 1.9 and 1.14 parts per trillion — the classic quantification of canine olfactory sensitivity.", "kind": "PEER REVIEWED", "url": "https://doi.org/10.1016/j.applanim.2005.07.009", "submitter": null } ], "movers": [ "Coskun Kocabas group, University of Manchester / Bilkent", "Medical Detection Dogs / bio-detection research groups", "Konrad Lorenz Institute / University of Vienna (Penn et al.)", "Institut fur Atemgasanalytik / Innsbruck (Filipiak et al.)", "US Army DEVCOM / signature management programmes" ], "commentary": "Canon sets a bar and then, unusually, concedes the machine fails half of it: the T-800 fools people and never fools a dog. The real obstacle is not the dog. Reject a kilowatt of waste heat from one-point-nine square metres by radiation and the surface must sit near 87 degrees Celsius; human skin sits at 33, and cultured keratinocytes die above about 45. Adaptive infrared skins are real and change the apparent temperature without removing a single joule. Odour is worse: the signature is a metabolic output of sixty-plus volatiles, individual to the person. A machine can carry a perfume. It cannot carry a metabolism.", "weight": 5, "progress": 0.0533 }, { "id": "living-tissue-over-metal", "pres": "leaf", "name": "Living tissue over metal", "reading": 0.027, "scale": 1, "state": "NOT ON TRACK", "moved": "2 YEARS AGO", "rec": "cool", "factor": 755, "short": "755× short", "canon": "A full-body integument of CULTURED, LIVING human tissue - epidermis, dermis, vasculature, hair follicles, sweat glands, breath, a wound-healing response - grown over a rigid non-biological chassis and vascularised well enough to stay alive and heal in the field for the whole mission. Not a covering: an organ.", "real": "Everything past a few hundred micrometres. Cultured skin is a clinical reality but only as a graft onto a living, perfused wound bed. Epicel grafts are 50 cm2 and 2 to 8 cell layers thick, ready no sooner than 15 days after biopsy; covering a 2.3 m2 body would take about 453 of them and would still be epidermis alone, with no dermis, no blood supply, no hair, no glands and no nerves. The one line of work that has put living skin on a machine (Takeuchi's group) has done it at face scale, avascular, and only while immersed.", "realVal": "30 cm2", "canonVal": "22650 cm2", "footMeta": "TRL 4 · WEIGHT 8 OF 10\nREVIEWED EVERY 30 DAYS\n4 INDICATORS · 6 SOURCES", "indicators": [ { "metric": "Largest area of living skin cultured onto a non-biological robotic structure", "unit": "cm2", "value": 30, "canon_target": 22650, "as_of": "2024-06-25", "source": "https://doi.org/10.1016/j.xcrp.2024.102066" }, { "metric": "Maximum viable thickness of engineered tissue with no vascular supply", "unit": "um", "value": 200, "canon_target": 2000, "as_of": "2023-02-03", "source": "https://pmc.ncbi.nlm.nih.gov/articles/PMC9898562/" }, { "metric": "Area of a single FDA-cleared cultured epidermal autograft", "unit": "cm2", "value": 50, "canon_target": 22650, "as_of": "2016-09-19", "source": "https://www.fda.gov/media/103138/download" }, { "metric": "Time from biopsy to first available cultured epidermal graft", "unit": "days", "value": 15, "canon_target": 0, "as_of": "2016-09-19", "source": "https://www.fda.gov/media/103138/download" } ], "sources": [ { "date": "2024-06-25", "org": "CELL REPORTS PHYSICAL SCIENCE", "text": "Takeuchi's group demonstrated perforation-type anchors inspired by skin ligaments: V-shaped holes through a robotic substrate, plasma-treated so collagen gel penetrates them, allowing a skin equivalent to be adhered to a three-dimensional facial mould and actuated into a smile. The construct has no vasculature and no perfusion.", "kind": "PEER REVIEWED", "url": "https://doi.org/10.1016/j.xcrp.2024.102066", "submitter": null }, { "date": "2023-10-04", "org": "SCIENCE TRANSLATIONAL MEDICINE", "text": "Bioprinted skin containing multiple primary human cell types promoted rapid vascularisation and epidermal rete-ridge formation and accelerated wound closure without increased contraction; full-thickness bioprinted grafts were transplanted onto wounds in pigs — human-like skin architecture achieved in vivo, on a host with a circulation.", "kind": "PEER REVIEWED", "url": "https://pubmed.ncbi.nlm.nih.gov/37792956/", "submitter": null }, { "date": "2023-02-03", "org": "SCIENTIFIC REPORTS", "text": "Engineered tissue without vasculature is limited in thickness by the oxygen diffusion limit of 100 to 200 micrometres; randomly self-assembled microvascular networks show irregular architecture, susceptibility to early thrombosis, and a post-implantation delay during which cells are deprived of oxygen.", "kind": "PEER REVIEWED", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC9898562/", "submitter": null }, { "date": "2022-07-01", "org": "MATTER", "text": "The same group cultured a dermis equivalent and epidermis directly onto a robotic finger, demonstrating water repellence and self-repair of a laceration using a collagen sheet — the first living skin grown on a moving robot.", "kind": "PEER REVIEWED", "url": "https://doi.org/10.1016/j.matt.2022.05.019", "submitter": null }, { "date": "2021-06-15", "org": "US FOOD AND DRUG ADMINISTRATION", "text": "The FDA approved StrataGraft, an allogeneic bilayered cultured skin construct containing both keratinocytes and dermal fibroblasts, for adults with thermal burns containing intact dermal elements. In the pivotal Phase 3 trial 96% (68 of 71) of StrataGraft-treated burn sites did not require autografting.", "kind": "STANDARD", "url": "https://www.fda.gov/vaccines-blood-biologics/stratagraft", "submitter": null }, { "date": "2016-02-01", "org": "US FOOD AND DRUG ADMINISTRATION", "text": "Epicel's FDA-approved Directions for Use (Revision G, February 2016) specify grafts of approximately 50 cm2, 2 to 8 cell layers thick, available approximately 15 days after cultures are initiated, manufactured with bovine serum and irradiated murine 3T3 feeder cells, and requiring immobilisation under nylon net for 7 to 10 days after grafting.", "kind": "STANDARD", "url": "https://www.fda.gov/media/103138/download", "submitter": null } ], "movers": [ "Shoji Takeuchi Laboratory, University of Tokyo", "Vericel", "Stratatech / Mallinckrodt", "Organogenesis", "Avita Medical", "Wake Forest Institute for Regenerative Medicine" ], "commentary": "Cultured skin is a mature clinical product and entirely useless here. Epicel arrives as 50-square-centimetre sheets, two to eight cell layers thick, fifteen days after biopsy; covering a T-800 would take about 453 of them, and would deliver epidermis with no dermis, no blood supply, no hair and no glands. The Tokyo group that has actually grown living skin onto a robot did it at face scale, avascular, in a bath. The binding number is the oxygen diffusion limit: 200 micrometres from a capillary, against human skin's one to four millimetres. Canon needs five to forty times the maximum thickness biology permits without a heart attached.", "weight": 8, "progress": 0.0267 }, { "id": "biohybrid-integration", "pres": "leaf", "name": "Biohybrid integration", "reading": 0.01, "scale": 1, "state": "NOT ON TRACK", "moved": "5 MONTHS AGO", "rec": "mid", "factor": 144, "short": "144× short", "canon": "Keep that entire living envelope metabolically viable - perfused, oxygenated, thermoregulated, wound-healing, immune-competent - using a NON-BIOLOGICAL BODY as its sole life support. No heart, no lungs, no gut, no liver, no marrow. The machine is the organism's organ system.", "real": "There is no artificial circulation. A square metre of skin is an organ with a metabolic rate: it needs oxygenated fluid within 200 micrometres of every cell, continuous waste and CO2 clearance, lymphatic drainage, glucose and lipid supply, immune surveillance against constant bacterial colonisation, and temperature held in a band a few degrees wide. In a human all of that is a heart, lungs, liver, kidneys, gut, spleen, thymus, lymphatics and hypothalamus. A Terminator has a power cell.", "realVal": "108 days", "canonVal": "1095 days", "footMeta": "TRL 3 · WEIGHT 7 OF 10\nREVIEWED EVERY 30 DAYS\n3 INDICATORS · 5 SOURCES", "indicators": [ { "metric": "Record continuous viability of an engineered tissue construct on a non-biological substrate", "unit": "days", "value": 108, "canon_target": 1095, "as_of": "2022-02-11", "source": "https://pmc.ncbi.nlm.nih.gov/articles/PMC8939435/" }, { "metric": "Continuous operating time of the largest biohybrid limb before fatigue", "unit": "minutes", "value": 10, "canon_target": 1440, "as_of": "2025-02-12", "source": "https://pubmed.ncbi.nlm.nih.gov/39937887/" }, { "metric": "Largest biohybrid limb operating outside a liquid culture bath", "unit": "cm", "value": 0, "canon_target": 180, "as_of": "2026-08-29", "source": "https://pubmed.ncbi.nlm.nih.gov/39937887/" } ], "sources": [ { "date": "2026-03-31", "org": "NATURE COMMUNICATIONS", "text": "A fatigue-resistant myoneural actuator with engineered recruitment biophysics was demonstrated for implantable biohybrid systems in a rodent model — achieving durability by being inside an animal whose circulation does the perfusion.", "kind": "PEER REVIEWED", "url": "https://doi.org/10.1038/s41467-026-70626-6", "submitter": null }, { "date": "2025-11-07", "org": "NPJ ROBOTICS", "text": "A field review of biohybrid actuators concludes that greater actuation, precise control, longer-term viability and programmability all remain open, with no route yet to organ-scale tissue viability on a non-biological substrate.", "kind": "PEER REVIEWED", "url": "https://doi.org/10.1038/s44182-025-00049-w", "submitter": null }, { "date": "2025-09-03", "org": "SCIENCE ROBOTICS", "text": "A miniature electronic biohybrid robot actuated by optogenetically stimulated neuromuscular tissue maintained mechanical functionality for more than two weeks, against roughly one week for earlier designs, with contraction persisting up to 20 minutes after a one-minute optical stimulation.", "kind": "PEER REVIEWED", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12767209/", "submitter": null }, { "date": "2025-02-12", "org": "SCIENCE ROBOTICS", "text": "An 18 cm biohybrid hand actuated by ten lab-grown human multiple muscle tissue actuators performed gestures and manipulated objects, but showed fatigue after 10 minutes of operation, needed about an hour of rest to recover, and had to remain suspended in liquid for the tendon anchors to move freely. The authors identify necrosis at the core of thick muscle as the limit on scaling.", "kind": "PEER REVIEWED", "url": "https://pubmed.ncbi.nlm.nih.gov/39937887/", "submitter": null }, { "date": "2022-02-11", "org": "SCIENCE", "text": "An autonomously swimming biohybrid fish built from human iPSC-derived cardiomyocytes maintained spontaneous activity for 108 days, equivalent to about 38 million beats — 16 to 18 times the previous records held by the biohybrid stingray (6 days) and a skeletal-muscle biohybrid actuator (7 days). The construct is millimetre-scale and was maintained in culture medium throughout.", "kind": "PEER REVIEWED", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC8939435/", "submitter": null } ], "movers": [ "Shoji Takeuchi Laboratory, University of Tokyo", "Waseda University (Morimoto group)", "Disease Biophysics Group, Harvard (Kevin Kit Parker)", "MIT (Ritu Raman group)", "MIT Media Lab Biomechatronics (Hugh Herr group)" ], "commentary": "This is the component that quietly ends the argument. The most advanced biohybrid limb ever built is an eighteen-centimetre hand that fatigues after ten minutes, needs an hour to recover, and only works while suspended in nutrient broth. The field's endurance record — 108 days, thirty-eight million contractions — belongs to a millimetre-scale fish in an incubator. Canon requires two-point-three square metres of human tissue kept perfused, fed, drained, defended against infection and thermally regulated for years, with no heart, no lungs, no kidneys and no immune system. Every other component in this index is an engineering gap. This one is an organ transplant with no recipient.", "weight": 7, "progress": 0.01 } ] }, { "id": "cat-self-repair-and-durability", "pres": "card", "name": "Self-repair & durability", "meta": "3 COMPONENTS", "reading": 18.7, "scale": 600, "state": "MORE EFFORTS", "moved": "4 WEEKS AGO", "rec": "warm", "blurb": "Still coming, on one arm. The bathroom-mirror surgery scene.", "factLeft": "3 COMPONENTS", "factMid": "9 INDICATORS", "factRight": "WEIGHT 19 OF 313", "footMeta": "3 COMPONENTS · 9 INDICATORS\nWEIGHT 19 OF 313", "weight": 19, "progress": 0.018699999999999998, "kids": [ { "id": "damage-tolerance-and-graceful-degradation", "pres": "leaf", "name": "Damage tolerance and graceful degradation", "reading": 0.022, "scale": 1, "state": "MORE EFFORTS", "moved": "4 WEEKS AGO", "rec": "warm", "factor": 120, "short": "120× short", "canon": "Retain mission capability through progressive destruction - losing the entire outer envelope, then limbs, then the lower body - degrading only in speed and reach, never in intent, with no single point of failure outside the processor.", "real": "Damage adaptation is demonstrated only on statically stable or fixed-base morphologies. On bipeds there is no result at all, and an August 2026 safety analysis establishes that de-energising a walking humanoid is itself the hazard, so no humanoid can currently be certified even to fail safely under ISO 13849-1 or EN 60204-1. Fielded humanoids also fall in cascades and manage only 2-4 hours per charge.", "realVal": "0.17 fraction", "canonVal": "0.5 fraction", "footMeta": "TRL 4 · WEIGHT 8 OF 10\nREVIEWED EVERY 30 DAYS\n3 INDICATORS · 5 SOURCES", "indicators": [ { "metric": "Maximum fraction of actuation lost with locomotion retained, best published result on any morphology", "unit": "fraction", "value": 0.17, "canon_target": 0.5, "as_of": "2015-05-28", "source": "https://www.nature.com/articles/nature14422" }, { "metric": "Time to adapt to unanticipated damage", "unit": "s", "value": 120, "canon_target": 1, "as_of": "2015-05-28", "source": "https://www.nature.com/articles/nature14422" }, { "metric": "Humanoids certified for the fall hazard under ISO 13849-1 PLe or IEC 61508 SIL 3", "unit": "count", "value": 0, "canon_target": 1, "as_of": "2026-08-03", "source": "https://arxiv.org/abs/2608.02809" } ], "sources": [ { "date": "2026-08-03", "org": "ARXIV", "text": "Removing power from a walking biped causes an uncontrolled fall, so classical de-energisation is itself a hazard; onboard humanoid compute is not safety-rated and no end-to-end PLe or SIL 3 certification can be claimed.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2608.02809", "submitter": null }, { "date": "2026-06-24", "org": "U.S. SECURITIES AND EXCHANGE COMMISSION", "text": "Digit humanoids have accumulated more than 65,000 hours of operation across nine customer facilities, the largest filed humanoid reliability figure.", "kind": "STANDARD", "url": "https://www.sec.gov/Archives/edgar/data/0002074973/000121390026071287/ea029548401ex99-1.htm", "submitter": null }, { "date": "2026-06-11", "org": "ARXIV", "text": "A single reinforcement-learning framework unifies humanoid motion tracking and fall recovery under disturbance, replacing separate training stages.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2606.12814", "submitter": null }, { "date": "2025-06-24", "org": "ARXIV", "text": "Evolutionary gait reconfiguration restores locomotion in damaged legged robots in under an hour without pre-training.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2506.19968", "submitter": null }, { "date": "2015-05-28", "org": "NATURE", "text": "A hexapod that has lost or broken a leg recovers a working gait in under two minutes by intelligent trial-and-error, without self-diagnosis.", "kind": "PEER REVIEWED", "url": "https://www.nature.com/articles/nature14422", "submitter": null } ], "movers": [ "Inria / Universite de Lorraine (Mouret group)", "Southern University of Science and Technology", "Siemens (Ding, Cui, Wang, Wen)", "Unitree Robotics", "Agility Robotics", "Beijing Municipal Government / World Humanoid Robot Games" ], "commentary": "The canonical requirement is a machine that keeps coming with half of it gone. The state of the art is a paper published this month establishing that cutting power to a walking humanoid is itself the hazard, because the upright state is actively maintained and de-energising it produces an uncontrolled fall, which is why no humanoid can presently be certified under ISO 13849-1 at all. The best damage-adaptation result in robotics remains a 2015 hexapod that relearned a gait in under two minutes after losing one leg of six. On two legs, losing one is not degradation. It is the end of the deployment.", "weight": 8, "progress": 0.0222 }, { "id": "field-self-repair", "pres": "leaf", "name": "Field self-repair", "reading": 0.022, "scale": 1, "state": "NOT ON TRACK", "moved": "1 MONTH AGO", "rec": "mid", "factor": 10000, "short": "10,000× short", "canon": "Unassisted self-diagnosis and MECHANICAL repair of internal actuator damage, by the machine itself, using improvised human hand tools, without a workshop, a manual or a second party - under mirror-reversed visual guidance - plus cosmetic concealment of damage it cannot repair.", "real": "Robotic servicing of other machines is genuinely fielded and just advanced, but it is ground-commanded and uses purpose-designed capture interfaces. Self-directed repair exists only as a bespoke modular laboratory system and as a single commercial action, the battery swap. Humanoid fleets are actually maintained by human field-service organisations.", "realVal": "1 count", "canonVal": "10000 count", "footMeta": "TRL 5 · WEIGHT 6 OF 10\nREVIEWED EVERY 30 DAYS\n3 INDICATORS · 5 SOURCES", "indicators": [ { "metric": "Internal components a fielded humanoid can autonomously replace on itself", "unit": "count", "value": 1, "canon_target": 10000, "as_of": "2026-08-29", "source": "https://www.figure.ai/news/ramping-figure-03-production" }, { "metric": "Robotic servicing vehicles operating on other spacecraft", "unit": "count", "value": 3, "canon_target": 3, "as_of": "2026-07-22", "source": "https://news.northropgrumman.com/launch/northrop-grummans-mission-robotic-vehicle-launches-ushering-in-a-new-era-of-in-space-servicing" }, { "metric": "Cumulative mission extension delivered by robotic servicers", "unit": "satellite-years", "value": 10, "canon_target": 100, "as_of": "2026-07-22", "source": "https://news.northropgrumman.com/launch/northrop-grummans-mission-robotic-vehicle-launches-ushering-in-a-new-era-of-in-space-servicing" } ], "sources": [ { "date": "2026-07-22", "org": "NORTHROP GRUMMAN", "text": "Northrop Grumman's Mission Robotic Vehicle launched with two NRL-built robotic arms and three Mission Extension Pods, rated for in-orbit satellite inspection, relocation, repair, upgrade, debris removal and assembly.", "kind": "PRIMARY", "url": "https://news.northropgrumman.com/launch/northrop-grummans-mission-robotic-vehicle-launches-ushering-in-a-new-era-of-in-space-servicing", "submitter": null }, { "date": "2026-07-22", "org": "NORTHROP GRUMMAN", "text": "Two Mission Extension Vehicles have docked with three commercial geostationary satellites and delivered more than ten years of combined mission extension.", "kind": "PRIMARY", "url": "https://news.northropgrumman.com/launch/northrop-grummans-mission-robotic-vehicle-launches-ushering-in-a-new-era-of-in-space-servicing", "submitter": null }, { "date": "2026-04-29", "org": "FIGURE AI", "text": "Humanoid fleets are kept running by purpose-built human field-service and fleet-management organisations, not by the robots themselves.", "kind": "PRIMARY", "url": "https://www.figure.ai/news/ramping-figure-03-production", "submitter": null }, { "date": "2025-07-16", "org": "SCIENCE ADVANCES", "text": "Modular robots self-assemble from 2D into 3D forms and can absorb material from other robots to grow and repair themselves - 'robot metabolism' (doi:10.1126/sciadv.adu6897).", "kind": "PEER REVIEWED", "url": "https://robotmetabolism.github.io/", "submitter": null }, { "date": "2024-11-18", "org": "ARXIV", "text": "Preprint of the robot metabolism work, with the Truss Link module design and self-assembly results.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2411.11192", "submitter": null } ], "movers": [ "Northrop Grumman SpaceLogistics", "U.S. Naval Research Laboratory", "Columbia University / University of Washington (Wyder, Lipson)", "UBTECH Robotics", "Figure AI" ], "commentary": "The bathroom-mirror scene requires a machine to diagnose and replace an arbitrary internal part of itself with improvised tools. The commercial state of the art is a three-minute battery swap. Northrop Grumman launched a robotic servicer to geostationary orbit in July with two arms and a repair mandate, and its predecessors have bought three satellites more than ten years of life between them: genuinely impressive, and the wrong problem, since those machines fix other machines, on prepared docking rings, under ground command. Everyone else's humanoids are maintained by technicians in vans. Figure built a field-service department. That is the actual answer.", "weight": 6, "progress": 0.0222 }, { "id": "self-healing-materials", "pres": "leaf", "name": "Self-healing materials", "reading": 0.009, "scale": 1, "state": "MORE EFFORTS", "moved": "5 MONTHS AGO", "rec": "mid", "factor": 10000000, "short": "7 orders of magnitude short", "canon": "Autonomous, room-temperature, repeatable closure of full-penetration structural damage in seconds - restoring both geometry AND load-bearing capability - plus reintegration of detached material. This is a T-1000 specification; the T-800 explicitly does NOT have it, and the contrast is deliberate.", "real": "Self-healing is a soft-polymer capability, measured in days, not a structural-metal capability measured in seconds. The only autonomous metal crack healing ever observed is nanoscale, in vacuum, in nanocrystalline platinum, and was observed rather than engineered. Nothing closes a hole in a load path.", "realVal": "82 %", "canonVal": "100 %", "footMeta": "TRL 4 · WEIGHT 5 OF 10\nREVIEWED EVERY 30 DAYS\n3 INDICATORS · 3 SOURCES", "indicators": [ { "metric": "Healing efficiency of the best integrated self-sensing, self-healing robot skin", "unit": "%", "value": 82, "canon_target": 100, "as_of": "2026-04-18", "source": "https://www.eurekalert.org/news-releases/1136525" }, { "metric": "Time to near-full recovery in that material", "unit": "s", "value": 604800, "canon_target": 10, "as_of": "2026-04-18", "source": "https://www.eurekalert.org/news-releases/1136525" }, { "metric": "Largest length scale of demonstrated autonomous metal crack healing", "unit": "m", "value": 1e-9, "canon_target": 0.01, "as_of": "2023-07-19", "source": "https://doi.org/10.1038/s41586-023-06223-0" } ], "sources": [ { "date": "2026-04-18", "org": "EUREKALERT / ADVANCED MATERIALS", "text": "A self-healing magnetoelectric sensory skin detects its own damage and recovers 82% of function in air after 7 days under mild heating, and nearly 100% underwater after 10 days, with 92% elastic recovery and 41 ms response.", "kind": "PEER REVIEWED", "url": "https://www.eurekalert.org/news-releases/1136525", "submitter": null }, { "date": "2025-11-03", "org": "ADVANCED SCIENCE", "text": "Self-healing, reprocessable soft robots are produced by 3D digital light printing with vinylogous urethane vitrimer chemistry, healing at room temperature via dynamic covalent bond exchange (doi:10.1002/advs.202516901).", "kind": "PEER REVIEWED", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC12786329/", "submitter": null }, { "date": "2023-07-19", "org": "NATURE", "text": "Fatigue cracks in nanocrystalline platinum were observed healing autonomously by cold welding - the only demonstrated self-healing in a metal, at nanoscale, in vacuum.", "kind": "PEER REVIEWED", "url": "https://doi.org/10.1038/s41586-023-06223-0", "submitter": null } ], "movers": [ "National University of Singapore (Tan Yu Jun group)", "Sandia National Laboratories / Texas A&M", "Vrije Universiteit Brussel (Self-Healing Soft Robotics)", "University of Nebraska-Lincoln", "Wiley / Advanced Science authors on vitrimer soft robots" ], "commentary": "Singapore's best self-healing skin knows when it has been cut and recovers 82 per cent of function, in seven days, with mild heating. Underwater it manages nearly full recovery, in ten. Canon requires a hole closing in seconds, in something load-bearing. On time alone that is a shortfall of five orders of magnitude, and the material in question is a soft elastomer, not a chassis. Metals do not self-heal above the nanoscale: the sole result, from 2023, is spontaneous crack closure in platinum, in vacuum, observed rather than engineered. Strength and healing want opposite things from atomic mobility. That is chemistry, not effort.", "weight": 5, "progress": 0.0089 } ] } ] }, { "id": "power", "pres": "hero", "pal": "power", "name": "POWER", "mission": "Powering a machine specified never to stop.", "reading": 46, "scale": 600, "state": "GATE · BLOCKS 2", "moved": "1 MONTH AGO", "rec": "mid", "kicker": "POWER", "big": "46.0", "bigLabel": "FAMILY READING", "plate": "PLATE 03", "worstComponent": { "id": "nuclear-power-cell", "name": "Nuclear power cell", "factor": 3000000 }, "componentCount": 3, "weight": 24, "kids": [ { "id": "cat-power", "pres": "card", "name": "Power", "meta": "3 COMPONENTS", "reading": 46, "scale": 600, "state": "MORE EFFORTS", "moved": "1 MONTH AGO", "rec": "mid", "blurb": "Dumping waste heat inside a sealed body. A sealed cell that runs a combat humanoid for decades.", "factLeft": "3 COMPONENTS", "factMid": "21 INDICATORS", "factRight": "WEIGHT 24 OF 313", "footMeta": "3 COMPONENTS · 21 INDICATORS\nWEIGHT 24 OF 313", "weight": 24, "progress": 0.045974999999999995, "kids": [ { "id": "thermal-management", "pres": "leaf", "name": "Thermal management", "reading": 0.109, "scale": 1, "state": "MORE EFFORTS", "moved": "3 MONTHS AGO", "rec": "mid", "factor": 210384, "short": "210,384× short", "canon": "Reject the waste heat of a continuously-running machine through a sealed envelope of living human tissue held at human skin temperature - no vents, no fans, no radiators, no thermal signature that distinguishes it from a person - while ALSO surviving external immersion in a hydrocarbon fireball. Two opposite thermal problems in one body.", "real": "Every watt in becomes a watt of heat out, and the canon design seals the exit. There is no demonstrated method of rejecting hundreds of watts continuously through an insulating biological covering, and no humanoid has ever been operated with one. Waterproofing and cooling are the same wall seen from opposite sides: IP67 sealing removes the convective path the machine needs.", "realVal": "60 degC", "canonVal": "40 degC", "footMeta": "TRL 7 · WEIGHT 6 OF 10\nREVIEWED EVERY 45 DAYS\n3 INDICATORS · 5 SOURCES", "indicators": [ { "metric": "Humanoid joint temperature under endurance running load, best reported", "unit": "degC", "value": 60, "canon_target": 40, "as_of": "2026-04-27", "source": "https://en.people.cn/n3/2026/0427/c98649-20450883.html" }, { "metric": "Rated maximum ambient operating temperature, best production humanoid", "unit": "degC", "value": 40, "canon_target": 1500, "as_of": "2026-01-05", "source": "https://bostondynamics.com/blog/boston-dynamics-unveils-new-atlas-robot-to-revolutionize-industry/" }, { "metric": "Continuous full-load operating duration before thermal or energy limit", "unit": "hours", "value": 5, "canon_target": 1051920, "as_of": "2025-07-17", "source": "https://www.figure.ai/news/f-03-battery-development" } ], "sources": [ { "date": "2026-05-27", "org": "DIGITIMES", "text": "Trade analysis reports that as humanoid robots approach mass production, thermal management is emerging as a critical bottleneck.", "kind": "PRIMARY", "url": "https://www.digitimes.com/news/a20260527PD226/robot-cooling-production-efficiency-management.html", "submitter": null }, { "date": "2026-04-27", "org": "PEOPLE'S DAILY ONLINE", "text": "At the 2026 Beijing humanoid half marathon, teams reduced joint temperatures from 70-80 C to approximately 60 C using combinations of liquid and air cooling, and battery swaps fell to under 10 seconds with no system interruption; completion times dropped from over two hours in 2025 to under one hour in 2026.", "kind": "PRIMARY", "url": "https://en.people.cn/n3/2026/0427/c98649-20450883.html", "submitter": null }, { "date": "2026-01-05", "org": "BOSTON DYNAMICS", "text": "The production Atlas is specified as extremely water-resistant and rated for ambient operation from -20 C to +40 C, i.e. sealed against the environment and therefore against convective cooling.", "kind": "PRIMARY", "url": "https://bostondynamics.com/blog/boston-dynamics-unveils-new-atlas-robot-to-revolutionize-industry/", "submitter": null }, { "date": "2025-11-10", "org": "ARXIV", "text": "A benchmarking framework for humanoid actuation reports electromechanical efficiency of 0.70-0.82 over positive-work bands and argues that continuous-safe torque under thermal limits, not peak torque, is the meaningful specification.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2511.06796", "submitter": null }, { "date": "2024-07-10", "org": "ARXIV", "text": "Managing humanoid actuator temperature is done by online learning of motor thermal model parameters to estimate core temperature and detect anomalies, i.e. by predicting when to derate rather than by rejecting more heat.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2407.08055", "submitter": null } ], "movers": [ "Honor Device", "Beijing Humanoid Robot Innovation Centre / X-Humanoid", "HKUST (Guangzhou) AMDT Lab", "Boston Dynamics", "JSK Lab, University of Tokyo" ], "commentary": "Every watt that goes in comes out as heat, and the canon design seals the exit. Joints at the Beijing half marathon ran at seventy to eighty degrees before liquid cooling brought them to about sixty; that, plus ten-second battery swaps, is most of why finishing times fell from over two hours to under one in a single year. The production Atlas is sealed to IP67 and rated to forty degrees ambient, because waterproofing and cooling are the same wall seen from opposite sides. Canon puts living tissue over that wall and walks the result into a steel mill. The state of the art is knowing when to slow down.", "weight": 6, "progress": 0.1089 }, { "id": "nuclear-power-cell", "pres": "leaf", "name": "Nuclear power cell", "reading": 0.05, "scale": 1, "state": "MORE EFFORTS", "moved": "3 YEARS AGO", "rec": "cool", "factor": 3000000, "short": "3,000,000× short", "canon": "A single sealed on-board power source giving 120 years of continuous operation to a combat android, with no refuelling, no recharge, no external cooling and no maintenance - sited inside a torso otherwise full of hydraulics, and thermally invisible through human skin. Its failure mode is a very large explosion.", "real": "Specific power and waste-heat rejection, not stored energy. A radioisotope cell that fits in a torso would deliver watts, not hundreds of watts; a cell that delivers hundreds of watts weighs more than half the robot and needs to dump kilowatts of heat through the same skin that must feel human. Betavoltaics reach the required lifetime and miss the required power by six orders of magnitude: the Betavolt BV100 gives 100 microwatts, so 300 W would take three million cells occupying about 3.4 cubic metres.", "realVal": "57 kg", "canonVal": "5 kg", "footMeta": "TRL 9 · WEIGHT 9 OF 10\nREVIEWED EVERY 60 DAYS\n10 INDICATORS · 5 SOURCES", "indicators": [ { "metric": "Mass of the smallest fielded generator delivering the canonical 300 W", "unit": "kg", "value": 57, "canon_target": 5, "as_of": "2026-08-29", "source": "https://en.wikipedia.org/wiki/GPHS-RTG" }, { "metric": "Specific power, best fielded radioisotope generator", "unit": "We/kg", "value": 5.2, "canon_target": 60, "as_of": "2026-08-29", "source": "https://en.wikipedia.org/wiki/GPHS-RTG" }, { "metric": "Thermal-to-electric conversion efficiency, best fielded unit", "unit": "%", "value": 6.8, "canon_target": 100, "as_of": "2026-08-29", "source": "https://en.wikipedia.org/wiki/GPHS-RTG" }, { "metric": "Waste heat to reject at canonical output, with no external radiator", "unit": "W", "value": 4100, "canon_target": 0, "as_of": "2026-08-29", "source": "https://en.wikipedia.org/wiki/GPHS-RTG" }, { "metric": "Plutonium-238 inventory required per unit", "unit": "kg", "value": 8.1, "canon_target": 0, "as_of": "2026-08-29", "source": "https://en.wikipedia.org/wiki/GPHS-RTG" }, { "metric": "United States annual Pu-238 production, stated target", "unit": "kg/yr", "value": 1.5, "canon_target": 8.1, "as_of": "2023-07-18", "source": "https://www.energy.gov/ne/articles/us-department-energy-completes-major-shipment-plutonium-238-nasa-missions" }, { "metric": "United States annual Pu-238 production, rate actually demonstrated", "unit": "kg/yr", "value": 0.4, "canon_target": 8.1, "as_of": "2026-08-29", "source": "https://www.energy.gov/ne/articles/oak-ridge-national-laboratory-automates-key-process-plutonium-238-production" }, { "metric": "Longest continuous nuclear power delivery in the field", "unit": "years", "value": 48, "canon_target": 120, "as_of": "2026-08-29", "source": "https://en.wikipedia.org/wiki/Voyager_1" }, { "metric": "Output of the best commercial betavoltaic cell", "unit": "W", "value": 0.0001, "canon_target": 300, "as_of": "2024-01-16", "source": "https://newatlas.com/energy/betavolt-diamond-nuclear-battery/" }, { "metric": "Betavoltaic cells needed to reach the canonical 300 W", "unit": "units", "value": 3000000, "canon_target": 1, "as_of": "2024-01-16", "source": "https://newatlas.com/energy/betavolt-diamond-nuclear-battery/" } ], "sources": [ { "date": "2026-08-29", "org": "WIKIPEDIA", "text": "The GPHS-RTG masses about 57 kg and produces about 300 W electrical from about 4,400 W thermal using about 8.1 kg of Pu-238, a specific power of 5.2 We/kg - the highest of any fielded radioisotope generator.", "kind": "PRIMARY", "url": "https://en.wikipedia.org/wiki/GPHS-RTG", "submitter": null }, { "date": "2026-08-29", "org": "WIKIPEDIA", "text": "Voyager 1, launched 5 September 1977 with about 470 W of RTG output, still had two operating science instruments in 2026 and is projected to return engineering data until 2036 - 48 years of continuous radioisotope power in the field, heading for 59.", "kind": "PRIMARY", "url": "https://en.wikipedia.org/wiki/Voyager_1", "submitter": null }, { "date": "2024-01-16", "org": "NEW ATLAS", "text": "The Betavolt BV100 betavoltaic cell produces 100 microwatts at 3 V from a 15 x 15 x 5 mm nickel-63 device, claimed to last 50 years; a 1 W version was promised for 2025.", "kind": "PRIMARY", "url": "https://newatlas.com/energy/betavolt-diamond-nuclear-battery/", "submitter": null }, { "date": "2023-07-18", "org": "US DEPARTMENT OF ENERGY, OFFICE OF NUCLEAR ENERGY", "text": "DOE completed a 0.5 kg shipment of new heat-source plutonium oxide to NASA, the largest since domestic production restarted, and stated it remains on track for an average production target of 1.5 kg per year by 2026.", "kind": "PRIMARY", "url": "https://www.energy.gov/ne/articles/us-department-energy-completes-major-shipment-plutonium-238-nasa-missions", "submitter": null }, { "date": "2015-08-01", "org": "NASA", "text": "The MMRTG is specified at 43.6 kg mass, 110 W electrical and 1,975 W thermal at beginning of mission, from 4,103 g of plutonium (3,478 g Pu-238), fuel half-life 87.75 years, operating life at least 14 years. That is 2.52 We/kg at 5.6 percent conversion efficiency.", "kind": "PRIMARY", "url": "https://www.nasa.gov/wp-content/uploads/2015/08/4_mars_2020_mmrtg.pdf", "submitter": null } ], "movers": [ "NASA / Department of Energy Radioisotope Power Systems Program", "Oak Ridge National Laboratory", "Idaho National Laboratory", "Betavolt", "City Labs" ], "commentary": "Radioisotope power is superb at lasting and hopeless at lifting. Voyager 1 has run on plutonium since 1977, forty-eight years and heading for fifty-nine, which is a respectable fraction of the canonical hundred and twenty. One flight-proven GPHS-RTG even delivers the canonical three hundred watts exactly. It weighs 57 kilograms, contains 8.1 kilograms of plutonium-238, and sheds 4.1 kilowatts of waste heat, which would have to leave through skin that is meant to feel human. American production of the isotope targets 1.5 kilograms a year. One unit is five and a half years of national output, assuming the target is met.", "weight": 9, "progress": 0.05 }, { "id": "energy-density-and-endurance", "pres": "leaf", "name": "Energy density and endurance", "reading": 0, "scale": 1, "state": "BLOCKED", "moved": "1 MONTH AGO", "rec": "mid", "factor": 210384, "short": "210,384× short", "canon": "The same energy store as nuclear-power-cell, expressed as the property that actually binds: it has to fit inside a torso already full of hydraulic actuators, structural skeleton and a processor bay, and last 120 years without service.", "real": "Roughly five orders of magnitude of stored energy, and it is not an engineering backlog. The peer-reviewed position is that humanoid applications already demand 10+ kWh where 2.3 kWh is state of the art, requiring a quadrupling of both volumetric and gravimetric capacity plus next-generation chemistries; the canon requirement is 30,000 times further out than that.", "realVal": "701 tonnes", "canonVal": "0.01 tonnes", "footMeta": "TRL 9 · WEIGHT 9 OF 10\nREVIEWED EVERY 30 DAYS\n8 INDICATORS · 6 SOURCES", "indicators": [ { "metric": "Mass of cells required to meet the canonical energy at the best available density", "unit": "tonnes", "value": 701, "canon_target": 0.01, "as_of": "2026-08-29", "source": "https://amprius.com/documents/Amprius_Product_Catalog.pdf" }, { "metric": "Highest commercially catalogued cell specific energy", "unit": "Wh/kg", "value": 450, "canon_target": 32000000, "as_of": "2026-08-29", "source": "https://amprius.com/documents/Amprius_Product_Catalog.pdf" }, { "metric": "Highest announced but not yet catalogued cell specific energy", "unit": "Wh/kg", "value": 520, "canon_target": 32000000, "as_of": "2026-01-01", "source": "https://www.ces.tech/ces-innovation-awards/2026/amprius-520-whkg-cell/" }, { "metric": "Thermodynamic ceiling on any chemical store, upper bound", "unit": "Wh/kg", "value": 30000, "canon_target": 32000000, "as_of": "2026-08-29", "source": "https://amprius.com/documents/Amprius_Product_Catalog.pdf" }, { "metric": "Largest onboard energy store in a production humanoid", "unit": "kWh", "value": 2.3, "canon_target": 315600, "as_of": "2026-08-29", "source": "https://www.figure.ai/news/f-03-battery-development" }, { "metric": "Average electrical draw of a production humanoid", "unit": "W", "value": 460, "canon_target": 300, "as_of": "2026-08-29", "source": "https://www.figure.ai/news/f-03-battery-development" }, { "metric": "Lowest measured draw of a production humanoid", "unit": "W", "value": 324, "canon_target": 300, "as_of": "2026-08-29", "source": "https://www.unitree.com/H2" }, { "metric": "Longest single-charge runtime claimed for a humanoid", "unit": "hours", "value": 5, "canon_target": 1051920, "as_of": "2026-08-29", "source": "https://www.figure.ai/news/f-03-battery-development" } ], "sources": [ { "date": "2026-08-29", "org": "UNITREE ROBOTICS", "text": "Unitree publishes a 15 Ah / 0.972 kWh battery and about 3 hours of battery life for the 70 kg H2 humanoid, implying an average electrical draw of roughly 324 W.", "kind": "PRIMARY", "url": "https://www.unitree.com/H2", "submitter": null }, { "date": "2026-07-29", "org": "ADVANCED SCIENCE 13, DOI 10.1002/ADVS.76736", "text": "A peer-reviewed review states that uninterrupted humanoid application requires a quadrupling of battery system volumetric and gravimetric capacity, that application cases indicate energy demands of 10+ kWh, and that meeting them needs next-generation chemistries above 1000 Wh/L, with swappable packs as the interim stopgap.", "kind": "PEER REVIEWED", "url": "https://pubmed.ncbi.nlm.nih.gov/42524759/", "submitter": null }, { "date": "2026-07-01", "org": "AMPRIUS TECHNOLOGIES", "text": "Amprius's Q3 2026 product catalogue lists silicon-anode cells at up to 450 Wh/kg and 1,150 Wh/L, described as among the highest commercially available; four catalogued cells reach 450 Wh/kg gravimetric, with the next tier at 395-400 Wh/kg.", "kind": "PRIMARY", "url": "https://amprius.com/documents/Amprius_Product_Catalog.pdf", "submitter": null }, { "date": "2026-01-06", "org": "CONSUMER TECHNOLOGY ASSOCIATION", "text": "Amprius took a CES 2026 Best of Innovation award for a 520 Wh/kg cell design, described as the highest energy density of any commercial battery, against roughly 260 Wh/kg for standard graphite cells.", "kind": "PRIMARY", "url": "https://www.ces.tech/ces-innovation-awards/2026/amprius-520-whkg-cell/", "submitter": null }, { "date": "2025-07-17", "org": "FIGURE AI", "text": "Figure 03 carries a 2.3 kWh battery enabling 5 hours of run time at peak performance, with 2 kW active-cooled fast charge, a 94 percent increase in energy density across three generations, and certification to both UN38.3 and UL2271.", "kind": "PRIMARY", "url": "https://www.figure.ai/news/f-03-battery-development", "submitter": null }, { "date": "2025-04-30", "org": "SCIENCE ROBOTICS 10, DOI 10.1126/SCIROBOTICS.ADR6125", "text": "Bioinspired mobile robots move with comparable efficiency to their animal counterparts but lag by more than an order of magnitude in system-level energy density because of battery limitations.", "kind": "PEER REVIEWED", "url": "https://pubmed.ncbi.nlm.nih.gov/40305577/", "submitter": null } ], "movers": [ "Amprius Technologies", "Figure AI", "Boston Dynamics", "Unitree Robotics", "UT Dallas / Kyeongjae Cho group", "Shi and Pikul (Univ. of Wisconsin-Madison)" ], "commentary": "The single worst number in the index, and it is not close. Best catalogued cell in the world: 450 watt-hours per kilogram. Best pack actually inside a humanoid: 2.3 kilowatt-hours, good for five hours. Canon: a hundred and twenty years on one cell, which at three hundred watts is 1.14 times ten to the twelve joules, or 701 tonnes of the finest chemistry money can buy. The ratio is seven parts in a million. Solid-state doubles it. The 520 watt-hour cell shown at CES improves it by sixteen per cent. Chemical bonds cap the approach four orders short, which is why this entry reads blocked at readiness level nine.", "weight": 9, "progress": 0 } ] } ] }, { "id": "mobility", "pres": "hero", "pal": "mobility", "name": "MOBILITY", "mission": "Moving a machine over ground built for people.", "reading": 171.3, "scale": 600, "state": "GATED BY POWER", "moved": "5 DAYS AGO", "rec": "warm", "kicker": "MOBILITY", "big": "171.3", "bigLabel": "FAMILY READING", "plate": "PLATE 04", "worstComponent": { "id": "bipedal-locomotion", "name": "Bipedal locomotion", "factor": 210384 }, "componentCount": 5, "weight": 37, "kids": [ { "id": "cat-locomotion", "pres": "card", "name": "Locomotion", "meta": "3 COMPONENTS", "reading": 238.5, "scale": 600, "state": "MORE EFFORTS", "moved": "5 DAYS AGO", "rec": "warm", "blurb": "Walking and running, any terrain. Running down a moving vehicle.", "factLeft": "3 COMPONENTS", "factMid": "11 INDICATORS", "factRight": "WEIGHT 23 OF 313", "footMeta": "3 COMPONENTS · 11 INDICATORS\nWEIGHT 23 OF 313", "weight": 23, "progress": 0.23845652173913046, "kids": [ { "id": "bipedal-locomotion", "pres": "leaf", "name": "Bipedal locomotion", "reading": 0.373, "scale": 1, "state": "MORE EFFORTS", "moved": "5 DAYS AGO", "rec": "warm", "factor": 210384, "short": "210,384× short", "canon": "Unbroken, unassisted bipedal walking and running over arbitrary unprepared terrain - rubble, stairs, wet storm-drain concrete, sand, steel-mill catwalks, a burning building - for the entire mission, with zero balance failures, no operator, and graceful degradation to crawling after loss of both legs.", "real": "Everything that is not a prepared surface. The demonstrated envelope is tracks, road courses, warehouse floors and research obstacle courses. There is no demonstrated locomotion through rubble, standing water at speed, fire, or with a damaged limb, and the duty cycle is 3-5 hours.", "realVal": "8.64 s", "canonVal": "7 s", "footMeta": "TRL 8 · WEIGHT 9 OF 10\nREVIEWED EVERY 21 DAYS\n4 INDICATORS · 8 SOURCES", "indicators": [ { "metric": "Fastest autonomous humanoid 100 m time", "unit": "s", "value": 8.64, "canon_target": 7, "as_of": "2026-08-26", "source": "https://www.globaltimes.cn/page/202608/1369085.shtml" }, { "metric": "Fastest autonomous humanoid half marathon time", "unit": "s", "value": 3026, "canon_target": 1500, "as_of": "2026-04-19", "source": "https://en.wikipedia.org/wiki/Beijing_E-Town_Half-Marathon" }, { "metric": "Share of half-marathon teams achieving autonomous navigation", "unit": "percent", "value": 40, "canon_target": 100, "as_of": "2026-04-27", "source": "https://en.people.cn/n3/2026/0427/c98649-20450883.html" }, { "metric": "Continuous operating time of best production humanoid on one charge", "unit": "hours", "value": 5, "canon_target": 1051920, "as_of": "2025-07-17", "source": "https://www.figure.ai/news/f-03-battery-development" } ], "sources": [ { "date": "2026-08-29", "org": "WIKIPEDIA", "text": "At the 2nd World Humanoid Robot Games (Beijing, 22-26 August 2026; 666 teams, 2,056 robots, 51 events) full autonomy was mandatory for sprints, relays, football, tai chi and gymnastics, and teleoperated robots in permissive events scored only half points. Records included 100 m in 8.86 s, 400 m in 38.16 s and a 2.88 m standing high jump. Some competing robots tripped, broke apart or caught fire.", "kind": "STANDARD", "url": "https://en.wikipedia.org/wiki/World_Humanoid_Robot_Games", "submitter": null }, { "date": "2026-08-29", "org": "WIKIPEDIA", "text": "In 2025 only 6 of 21 entered robots finished the Beijing E-Town half marathon, the winner taking 2:40:42 with three battery changes and one fall; in 2026 over 300 robots entered, up to three battery changes were allowed, and remote-controlled entries carried a 1.2x time penalty.", "kind": "STANDARD", "url": "https://en.wikipedia.org/wiki/Beijing_E-Town_Half-Marathon", "submitter": null }, { "date": "2026-08-26", "org": "GLOBAL TIMES", "text": "Tiangong Ultra won the 100 m large-group final at the 2nd World Humanoid Robot Games in 8.64 seconds, resetting its own Games record of 8.86 s and beating Usain Bolt's 9.58 s human world record.", "kind": "STANDARD", "url": "https://www.globaltimes.cn/page/202608/1369085.shtml", "submitter": null }, { "date": "2026-08-01", "org": "ARXIV", "text": "Light-Loco-Parkour demonstrates end-to-end perceptive whole-body humanoid locomotion from onboard depth alone, autonomously deciding when to walk, balance, climb, step down or vault, with zero-shot transfer to indoor and outdoor hardware and no reference input, skill label or hand-coded gate.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2608.02653", "submitter": null }, { "date": "2026-06-25", "org": "BMW GROUP PRESSCLUB", "text": "BMW Group deployed Figure 03 humanoids at Plant Spartanburg for logistics parts sequencing, following an eleven-month Figure 02 trial that supported production of more than 30,000 X3 vehicles.", "kind": "PRIMARY", "url": "https://www.press.bmwgroup.com/global/article/detail/T0458778EN/bmw-group-advances-the-use-of-physical-ai-in-production-with-figure-03-project-in-spartanburg?language=en", "submitter": null }, { "date": "2026-04-20", "org": "CAIXIN GLOBAL", "text": "Honor's 'Lightning' won the 2026 Beijing E-Town half marathon autonomously in 50 minutes 26 seconds over 21 km, faster than the human world record of about 57 minutes, with over 100 robots competing and about 40 percent finishing autonomously.", "kind": "STANDARD", "url": "https://www.caixinglobal.com/2026-04-20/chinese-built-robot-wins-beijing-half-marathon-102435911.html", "submitter": null }, { "date": "2026-01-08", "org": "ENGADGET", "text": "Hyundai will begin Atlas deployments at car manufacturing plants in 2028, not 2026, initially for parts sequencing, expanding to component assembly by 2030 - a reminder that production start and operational use are years apart.", "kind": "PRIMARY", "url": "https://www.engadget.com/big-tech/boston-dynamics-unveils-production-ready-version-of-atlas-robot-at-ces-2026-234047882.html", "submitter": null }, { "date": "2026-01-05", "org": "BOSTON DYNAMICS", "text": "Boston Dynamics began production of the electric Atlas: 56 degrees of freedom, 2.3 m reach, 50 kg lift, autonomous self-charging battery swaps, three control modes (autonomous, teleoperated, tablet steering), with 2026 deployments committed to Hyundai's Robotics Metaplant Application Center and Google DeepMind.", "kind": "PRIMARY", "url": "https://bostondynamics.com/blog/boston-dynamics-unveils-new-atlas-robot-to-revolutionize-industry/", "submitter": null } ], "movers": [ "Boston Dynamics", "X-Humanoid / Beijing Humanoid Robot Innovation Centre", "Honor Device", "Figure AI", "AgiBot", "Agility Robotics", "1X Technologies" ], "commentary": "The one line in the index running ahead of schedule. In August a Chinese humanoid covered 100 metres in 8.64 seconds under a rule mandating full autonomy, against Bolt's 9.58; in April another ran a half marathon in 50:26, faster than any human has. Boston Dynamics is building a 90-kilogram, 56-degree-of-freedom Atlas that changes its own batteries, and BMW has Figure 03 sequencing parts in South Carolina. What remains is rubble, fire, water and damage, plus a three-to-five-hour battery that belongs to another entry. Flat ground is solved. Nobody fights a war on a running track.", "weight": 9, "progress": 0.3733 }, { "id": "high-speed-pursuit", "pres": "leaf", "name": "High-speed pursuit", "reading": 0.2, "scale": 1, "state": "MORE EFFORTS", "moved": "5 DAYS AGO", "rec": "warm", "factor": 2.8694404591104736, "short": "3× short", "canon": "Pursue a fleeing human who is using a vehicle, and sustain it. ATTRIBUTION MATTERS HERE: every on-screen instance of a Terminator running down a moving vehicle ON FOOT is the T-1000, not the T-800. The T-800's own demonstrated pursuit is vehicular - a Harley at ~129 km/h through the canal - plus foot running that keeps pace with sprinting humans but never catches a car. Because the index scores against a canonical T-800 Model 101, the T-800's performance sets the target and the T-1000's foot bracket is carried as an explicitly-attributed stretch reference.", "real": "Pursuit, not speed. No legged robot has been shown turning, braking and re-accelerating at speed around obstacles, on a real road, in traffic, while tracking a target. Sustained road speed is one third of vehicle speed and the fastest verified runs are straight lines on a track.", "realVal": "11.57 m/s", "canonVal": "20 m/s", "footMeta": "TRL 6 · WEIGHT 6 OF 10\nREVIEWED EVERY 21 DAYS\n3 INDICATORS · 5 SOURCES", "indicators": [ { "metric": "Fastest verified autonomous legged-robot speed, free running", "unit": "m/s", "value": 11.57, "canon_target": 20, "as_of": "2026-08-26", "source": "https://www.globaltimes.cn/page/202608/1369085.shtml" }, { "metric": "Fastest verified sustained legged-robot speed over 20+ km", "unit": "m/s", "value": 6.97, "canon_target": 20, "as_of": "2026-04-19", "source": "https://en.wikipedia.org/wiki/Beijing_E-Town_Half-Marathon" }, { "metric": "Duration a humanoid can sustain running speed", "unit": "minutes", "value": 50, "canon_target": 60, "as_of": "2026-04-19", "source": "https://en.wikipedia.org/wiki/Beijing_E-Town_Half-Marathon" } ], "sources": [ { "date": "2026-08-29", "org": "WIKIPEDIA", "text": "Honor's Lightning sustained an average 6.97 m/s over 21.1 km to win the 2026 Beijing E-Town half marathon autonomously in 50:26, under rules allowing up to three battery changes and penalising remote-controlled entries 1.2x on time.", "kind": "STANDARD", "url": "https://en.wikipedia.org/wiki/Beijing_E-Town_Half-Marathon", "submitter": null }, { "date": "2026-08-26", "org": "GLOBAL TIMES", "text": "Tiangong Ultra ran 100 m in 8.64 s at the World Humanoid Robot Games, an average of 11.57 m/s, in an event where full autonomy was mandatory.", "kind": "STANDARD", "url": "https://www.globaltimes.cn/page/202608/1369085.shtml", "submitter": null }, { "date": "2026-08-17", "org": "GLOBAL TIMES", "text": "Unitree claimed a top speed of 12.66 m/s and a 2 m standing jump for a robot it calls Superman, with 0.85 m leg length, developed in just over three months and carrying no hands or grippers. The claim rests on a company statement and a company-supplied video; test conditions, payload, surface and repeatability were not disclosed and there is no independent verification.", "kind": "PRIMARY", "url": "https://www.globaltimes.cn/page/202608/1368390.shtml", "submitter": null }, { "date": "2026-04-12", "org": "GLOBAL TIMES", "text": "Unitree claimed 10.1 m/s for an H1 on an athletics track, while itself noting that the measuring equipment might be subject to error. No independent verification.", "kind": "PRIMARY", "url": "https://www.globaltimes.cn/page/202604/1358712.shtml", "submitter": null }, { "date": "2012-09-05", "org": "IEEE SPECTRUM", "text": "Boston Dynamics' Cheetah reached 28.3 mph (12.65 m/s), but on a treadmill, relying on off-board power and a boom to keep it from falling over, unable to operate outdoors or manoeuvre laterally.", "kind": "PRIMARY", "url": "https://spectrum.ieee.org/boston-dynamics-cheetah-robot-now-faster-than-fastest-human-2650267047", "submitter": null } ], "movers": [ "X-Humanoid / Beijing Humanoid Robot Innovation Centre", "Unitree Robotics", "Honor Device", "Boston Dynamics" ], "commentary": "Boston Dynamics' Cheetah hit 12.65 metres per second in 2012, on a treadmill, tethered, with a boom holding it up. Fourteen years later the free-running, self-powered, autonomous record is 11.57 metres per second over a hundred metres, and the sustained figure is 6.97 for fifty minutes on a closed road course with battery swaps permitted. Unitree claims 12.66 from a machine with no hands, on the strength of its own video and no disclosed conditions. Canon requires staying with a car in traffic for minutes. On a track we are at a third of that. On a street, nobody has measured.", "weight": 6, "progress": 0.2 }, { "id": "actuation-and-strength", "pres": "leaf", "name": "Actuation and strength", "reading": 0.116, "scale": 1, "state": "MORE EFFORTS", "moved": "3 MONTHS AGO", "rec": "mid", "factor": 16.666666666666668, "short": "17× short", "canon": "Actuators - hydraulic, per production material - delivering multiples of human strength from a human-sized limb, with no duty cycle, no fatigue and no thermal derating. Canon's emphasis is never a single feat of strength; it is the absence of any limit. NOTE: 'crushing hardened steel one-handed' is NOT a verified T-800 feat - see the disputed_claims entry below.", "real": "Continuous, not peak. Every published humanoid specification is a burst figure; the sustained figure after a thermal soak is unpublished and, where it has been measured in the literature, collapses in exactly the low-rate high-torque regime that holding, pressing and crushing require. Whole-body strength is roughly a tenth of the canonical requirement and the machines fatigue in minutes rather than never.", "realVal": "30 kg", "canonVal": "500 kg", "footMeta": "TRL 8 · WEIGHT 8 OF 10\nREVIEWED EVERY 30 DAYS\n4 INDICATORS · 5 SOURCES", "indicators": [ { "metric": "Sustained whole-body payload, best production humanoid", "unit": "kg", "value": 30, "canon_target": 500, "as_of": "2026-01-24", "source": "https://www.humanoidsdaily.com/news/the-alien-in-the-factory-boston-dynamics-launches-production-ready-atlas-at-ces-2026" }, { "metric": "Instantaneous whole-body payload, best production humanoid", "unit": "kg", "value": 50, "canon_target": 500, "as_of": "2026-01-05", "source": "https://bostondynamics.com/blog/boston-dynamics-unveils-new-atlas-robot-to-revolutionize-industry/" }, { "metric": "Published peak leg joint torque, commercially available humanoid", "unit": "Nm", "value": 360, "canon_target": 2000, "as_of": "2026-08-29", "source": "https://www.unitree.com/H2" }, { "metric": "Human-equivalence envelope coverage for hip and knee in sustained support (worked example)", "unit": "fraction", "value": 0.085, "canon_target": 1, "as_of": "2025-11-10", "source": "https://arxiv.org/abs/2511.06796" } ], "sources": [ { "date": "2026-08-29", "org": "UNITREE ROBOTICS", "text": "Unitree publishes 360 N-m maximum leg joint torque and 120 N-m maximum arm joint torque for the 70 kg, 31-DOF H2, with approximately 7 kg rated and 15 kg peak arm payload.", "kind": "PRIMARY", "url": "https://www.unitree.com/H2", "submitter": null }, { "date": "2026-06-14", "org": "ARXIV", "text": "A physics-based model of the Unitree G1's seven-DOF arm electrical power consumption achieved R-squared of 0.933 with 1.07 W RMSE over 897 trajectories and 0.965 on 46 unseen speed trajectories, finding viscous friction dominant in most joints and copper losses dominant in shoulder yaw and elbow.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2606.15915", "submitter": null }, { "date": "2026-01-24", "org": "HUMANOIDS DAILY", "text": "The production Atlas is specified at 90 kg with 50 kg instantaneous and 30 kg sustained payload across 56 degrees of freedom.", "kind": "PRIMARY", "url": "https://www.humanoidsdaily.com/news/the-alien-in-the-factory-boston-dynamics-launches-production-ready-atlas-at-ces-2026", "submitter": null }, { "date": "2025-11-10", "org": "ARXIV", "text": "A benchmarking framework argues that peak torque and no-load speed specifications tell us little about whether a joint can deliver torque, power and endurance at task-relevant operating points, and that continuous-safe torque maps measured after a thermal soak are the meaningful measure. In its worked example, human-equivalence coverage was 0.546 for the ankle in walking and 0.085 for hip and knee in stair support. Human reference moments for a 75 kg subject: hip 38-75 N-m, knee 35-95 N-m, ankle 90-143 N-m with 190-260 W of positive ankle power at push-off.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2511.06796", "submitter": null }, { "date": "2024-10-22", "org": "ARXIV", "text": "Cycloidal quasi-direct-drive actuators offer high torque density and mechanical robustness for legged robots, with a learned actuator network used to close the sim-to-real gap introduced by the drive's complex dynamics.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2410.16591", "submitter": null } ], "movers": [ "Boston Dynamics", "Unitree Robotics", "UCLA RoMeLa (Dennis Hong)", "Istituto Italiano di Tecnologia", "Honor Device" ], "commentary": "Peak torque is the most misleading number in robotics and the industry quotes little else. Unitree publishes 360 newton-metres at the leg joint, two to four times a human's peak; Atlas lifts fifty kilograms instantaneously and thirty sustained. Then the thermal soak begins. November's human-equivalence framework makes the point precisely: in its worked example the ankle met human requirements across 55 per cent of the walking band, while the hip and knee met sustained stair-support demand across eight per cent, because low-rate torque is a heat problem rather than a current problem. Canon asks for indefinite. What the actuators offer is a burst, then a derate.", "weight": 8, "progress": 0.1156 } ] }, { "id": "cat-manipulation", "pres": "card", "name": "Manipulation", "meta": "2 COMPONENTS", "reading": 61, "scale": 600, "state": "MORE EFFORTS", "moved": "6 DAYS AGO", "rec": "warm", "blurb": "Hands. Using human tools and guns competently.", "factLeft": "2 COMPONENTS", "factMid": "7 INDICATORS", "factRight": "WEIGHT 14 OF 313", "footMeta": "2 COMPONENTS · 7 INDICATORS\nWEIGHT 14 OF 313", "weight": 14, "progress": 0.060957142857142856, "kids": [ { "id": "dexterous-manipulation", "pres": "leaf", "name": "Dexterous manipulation", "reading": 0.067, "scale": 1, "state": "MORE EFFORTS", "moved": "6 DAYS AGO", "rec": "warm", "factor": 4, "short": "4× short", "canon": "A five-fingered hand with full human kinematic range spanning - WITHOUT changing end-effector - from crushing bone to performing surgery on itself with a craft knife under mirror-inverted visual guidance.", "real": "Hardware has closed: 22 actuated DoF against roughly 24 in a human hand, and 361 tactile sensels/cm2 against 241 human fingertip mechanoreceptors/cm2. Control has not. Autonomous success on five-fingered dexterity tasks ranges 32-92% and is worse than a two-finger gripper on every comparable axis; speed is 3-10x below human; generalisation to unseen objects and environments is the field's own stated bottleneck. Nothing approaches self-surgery.", "realVal": "48.8 %", "canonVal": "100 %", "footMeta": "TRL 6 · WEIGHT 8 OF 10\nREVIEWED EVERY 30 DAYS\n4 INDICATORS · 9 SOURCES", "indicators": [ { "metric": "Mean autonomous success rate, published multi-finger dexterity suite", "unit": "%", "value": 48.8, "canon_target": 100, "as_of": "2026-07-30", "source": "https://deepmind.google/blog/gemini-robotics-2-brings-whole-body-intelligence-to-robots/" }, { "metric": "Manipulation speed relative to a human on precision tasks", "unit": "x human", "value": 0.25, "canon_target": 1, "as_of": "2026-02-10", "source": "https://epoch.ai/blog/where-autonomy-works-evaluating-robot-capabilities-in-2026" }, { "metric": "Tactile sensel density on the best demonstrated robot hand", "unit": "sensels/cm2", "value": 361, "canon_target": 241, "as_of": "2026-01-09", "source": "https://www.prnewswire.com/news-releases/from-fingertips-to-full-body-coverage-ensuring-technology-debuts-groundbreaking-tactile-infrastructure-at-ces-2026-302657225.html" }, { "metric": "Actuated degrees of freedom, best production humanoid hand", "unit": "DoF", "value": 22, "canon_target": 24, "as_of": "2026-05-13", "source": "https://arxiv.org/abs/2605.13925" } ], "sources": [ { "date": "2026-08-25", "org": "FIGURE AI", "text": "Figure is buying manipulation data at scale: 16 million-plus videos from 44,000 weekly users across 100+ countries, $15m paid to contributors, $1bn+ planned data and compute spend over twelve months.", "kind": "PRIMARY", "url": "https://www.figure.ai/news/introducing-index", "submitter": null }, { "date": "2026-07-30", "org": "GOOGLE DEEPMIND", "text": "Gemini Robotics 2 publishes per-task autonomous success on a five-fingered humanoid hand: 92% unscrewing a bulb, 44% tying a trash bag, 40% ziplock, 36% screwing a bulb in, 32% sweeping into a dustpan.", "kind": "PRIMARY", "url": "https://deepmind.google/blog/gemini-robotics-2-brings-whole-body-intelligence-to-robots/", "submitter": null }, { "date": "2026-07-05", "org": "ARXIV", "text": "RoboDojo establishes a unified sim-and-real manipulation leaderboard: 42 simulation tasks, 18 real-world tasks, 30 policies, standardised remote real-world evaluation.", "kind": "STANDARD", "url": "https://arxiv.org/abs/2607.04434", "submitter": null }, { "date": "2026-05-13", "org": "ARXIV", "text": "Survey tabulates the current hand field at 15-24 DoF (Shadow 24, Optimus Gen 3 22, LEAP II 21, Unitree Dex5-1P 20) and names cost and reliability as the primary barriers to industrial deployment.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2605.13925", "submitter": null }, { "date": "2026-04-16", "org": "ARXIV", "text": "pi-0.7 achieves 1.2-1.6x normalised throughput versus specialist policies on laundry, espresso and box-building, and transfers zero-shot to an unseen robot embodiment.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2604.15483", "submitter": null }, { "date": "2026-02-10", "org": "EPOCH AI", "text": "Independent audit finds robots typically 3-10x slower than humans, precision-insertion reliability averaging ~52%, and laundry success falling to 75% on jeans.", "kind": "STANDARD", "url": "https://epoch.ai/blog/where-autonomy-works-evaluating-robot-capabilities-in-2026", "submitter": null }, { "date": "2026-01-27", "org": "FIGURE AI", "text": "Figure's Helix 02 completes a 4-minute, 61-action dishwasher load/unload fully autonomously, with fingertip tactile sensing resolving 3-gram forces.", "kind": "PRIMARY", "url": "https://www.figure.ai/news/helix-02", "submitter": null }, { "date": "2026-01-09", "org": "PR NEWSWIRE", "text": "First full tactile coverage of a dexterous hand: 1,956 multi-dimensional sensels at 361 sensels/cm2, sampling at 1 kHz, 4.5 mm thick.", "kind": "PRIMARY", "url": "https://www.prnewswire.com/news-releases/from-fingertips-to-full-body-coverage-ensuring-technology-debuts-groundbreaking-tactile-infrastructure-at-ces-2026-302657225.html", "submitter": null }, { "date": "1979-03-01", "org": "JOURNAL OF PHYSIOLOGY", "text": "Human fingertip low-threshold mechanoreceptor innervation density is 241 units/cm2, against 58 units/cm2 in the palm.", "kind": "PEER REVIEWED", "url": "https://pubmed.ncbi.nlm.nih.gov/439026/", "submitter": null } ], "movers": [ "Physical Intelligence", "Google DeepMind", "Figure AI", "Ensuring Technology", "Apptronik / Sharpa", "Epoch AI", "Shadow Robot Company" ], "commentary": "The hands are finished; the hands do not work. Robot fingers now carry 361 tactile sensels per square centimetre against the human fingertip's 241 mechanoreceptors, and 22 actuated degrees of freedom against roughly 24 in a human hand. What arrives with that hardware is a 92 per cent success rate unscrewing a light bulb and 36 per cent screwing one back in, at a quarter of human speed. DeepMind deserves credit for publishing the numbers; most of the field publishes video. The binding constraint is contact data, which cannot be scraped, only accumulated a robot-hour at a time. Figure is now paying the public $15m for phone footage of their own hands.", "weight": 8, "progress": 0.0667 }, { "id": "tool-and-weapon-handling", "pres": "leaf", "name": "Tool and weapon handling", "reading": 0.053, "scale": 1, "state": "MORE EFFORTS", "moved": "1 MONTH AGO", "rec": "mid", "factor": 25, "short": "25× short", "canon": "Pick up an arbitrary, unfamiliar, human-designed tool or weapon and operate it at expert level immediately - including selecting sub-lethal aimpoints under fire when mission constraints change mid-mission.", "real": "Robots operate human-designed equipment in real factories, but only equipment they were specifically commissioned against. Arbitrary pick-up-and-use is lab-stage. Every fielded armed robot mounts its weapon as a bolted payload on a pan-tilt turret rather than holding it: no published demonstration exists anywhere of a robot loading, chambering, clearing a malfunction in, or reloading a firearm with its hands.", "realVal": "78.9 %", "canonVal": "100 %", "footMeta": "TRL 6 · WEIGHT 6 OF 10\nREVIEWED EVERY 30 DAYS\n3 INDICATORS · 6 SOURCES", "indicators": [ { "metric": "Near-zero-shot tool-use success on a published benchmark (diverse tool kitting)", "unit": "%", "value": 78.9, "canon_target": 100, "as_of": "2026-07-30", "source": "https://deepmind.google/blog/gemini-robotics-2-brings-whole-body-intelligence-to-robots/" }, { "metric": "Humanoid vehicle-operation speed relative to a human, cornering", "unit": "x human", "value": 0.04, "canon_target": 1, "as_of": "2024-06-08", "source": "https://arxiv.org/abs/2406.05573" }, { "metric": "Published demonstrations of a robot loading or reloading a firearm by hand", "unit": "count", "value": 0, "canon_target": 1, "as_of": "2026-08-29", "source": "https://spectrum.ieee.org/ghost-robotics-armed-military-robots" } ], "sources": [ { "date": "2026-07-30", "org": "GOOGLE DEEPMIND", "text": "Diverse tool kitting scores 78.9% with a two-finger gripper while screwing in a light bulb scores 36% with a five-fingered hand.", "kind": "PRIMARY", "url": "https://deepmind.google/blog/gemini-robotics-2-brings-whole-body-intelligence-to-robots/", "submitter": null }, { "date": "2026-06-30", "org": "FIGURE AI", "text": "Figure 03 performs sequencing on a live BMW production line, combining precise placement of thin-walled parts with forceful whole-body manipulation of a metal cart.", "kind": "PRIMARY", "url": "https://www.figure.ai/news/f-03-at-bmw", "submitter": null }, { "date": "2026-06-24", "org": "U.S. SECURITIES AND EXCHANGE COMMISSION", "text": "Digit humanoids perform machine tending and sortation for Schaeffler, GXO, Toyota Motor Manufacturing Canada and Mercado Libre, accumulating over 65,000 hours of operation.", "kind": "STANDARD", "url": "https://www.sec.gov/Archives/edgar/data/0002074973/000121390026071287/ea029548401ex99-1.htm", "submitter": null }, { "date": "2024-06-08", "org": "ARXIV", "text": "A musculoskeletal humanoid drives an unmodified micro-EV - key, handbrake, pedals, steering, traffic lights - but takes roughly two minutes to turn a single corner.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2406.05573", "submitter": null }, { "date": "2021-10-18", "org": "IEEE SPECTRUM", "text": "On the reference armed quadruped the rifle is a mounted payload the robot does not hold or aim; firing is by a remote human operator, and the manufacturer states the weapon system has no autonomy and no AI.", "kind": "PRIMARY", "url": "https://spectrum.ieee.org/ghost-robotics-armed-military-robots", "submitter": null }, { "date": "2021-10-14", "org": "POPULAR SCIENCE", "text": "The SWORD Special Purpose Unmanned Rifle is bolted to the Vision 60 quadruped's back as a payload.", "kind": "PRIMARY", "url": "https://www.popsci.com/technology/ghost-robotics-robot-dog-gun-lethal/", "submitter": null } ], "movers": [ "Google DeepMind", "JSK Lab, University of Tokyo", "Karlsruhe Institute of Technology", "Ghost Robotics / SWORD International", "Figure AI", "Agility Robotics", "DeWalt / August Robotics" ], "commentary": "Every armed robot in service is a gun carriage. The rifle bolts to the back; the machine neither holds it, cocks it, clears it nor reloads it, and a human pulls the trigger from a distance. Not one published demonstration exists of a robot loading a firearm with its fingers. On tools proper, the best near-zero-shot figure is 79 per cent, achieved with a two-finger gripper, because the five-fingered hand does worse. The most convincing humanoid driver remains a Tokyo university machine that took two minutes to turn a corner. Canon requires lever-cocking a Winchester one-handed, at speed, on a moving motorcycle.", "weight": 6, "progress": 0.0533 } ] } ] }, { "id": "intelligence", "pres": "hero", "pal": "intel", "name": "INTELLIGENCE", "mission": "Measuring what a machine can already do without a body.", "reading": 318.8, "scale": 600, "state": "UNGATED", "moved": "4 DAYS AGO", "rec": "warm", "kicker": "INTELLIGENCE", "big": "318.8", "bigLabel": "FAMILY READING", "plate": "PLATE 05", "worstComponent": { "id": "neural-net-processor", "name": "Neural-net processor", "factor": 9721.75434709376 }, "componentCount": 11, "weight": 90, "kids": [ { "id": "cat-language-and-deception", "pres": "card", "name": "Language & deception", "meta": "3 COMPONENTS", "reading": 589.8, "scale": 600, "state": "ON TRACK", "moved": "4 DAYS AGO", "rec": "warm", "blurb": "\"Your foster parents are dead.\" Cloning a specific voice, live, over a phone, to an intimate. The one part of the Terminator problem largely finished.", "factLeft": "3 COMPONENTS", "factMid": "9 INDICATORS", "factRight": "WEIGHT 24 OF 313", "footMeta": "3 COMPONENTS · 9 INDICATORS\nWEIGHT 24 OF 313", "weight": 24, "progress": 0.5897833333333333, "kids": [ { "id": "voice-cloning-and-mimicry", "pres": "leaf", "name": "Voice cloning and mimicry", "reading": 0.88, "scale": 1, "state": "ON TRACK", "moved": "2 WEEKS AGO", "rec": "warm", "factor": 5.319148936170213, "short": "5× short", "canon": "Real-time cloning of a specific named individual's voice from limited prior exposure, good enough to pass with that person's close family over a low-bandwidth telephone channel, sustained through a multi-turn conversation with unscripted content and correct emotional register, with no perceptible latency. In T2 BOTH ends of one call are machines impersonating humans simultaneously.", "real": "Full-duplex conversational prosody under interruption and emotional register shift is the only remaining acoustic tell. Knowing what to say — the semantic half of the canon test, the 'Wolfie's fine, honey' failure — belongs to social-passing-and-deception, not here.", "realVal": "0.789 cosine similarity", "canonVal": "1 cosine similarity", "footMeta": "TRL 9 · WEIGHT 7 OF 10\nREVIEWED EVERY 30 DAYS\n3 INDICATORS · 9 SOURCES", "indicators": [ { "metric": "Speaker similarity of best zero-shot voice clone, LibriSpeech test-clean", "unit": "cosine similarity", "value": 0.789, "canon_target": 1, "as_of": "2026-08-09", "source": "https://arxiv.org/abs/2608.08638" }, { "metric": "First-audio latency of best real-time cloning system", "unit": "ms", "value": 37.6, "canon_target": 200, "as_of": "2026-08-09", "source": "https://arxiv.org/abs/2608.08638" }, { "metric": "Best audio deepfake detection score, robust speech track (adversary's obstacle, so lower is progress for TTP)", "unit": "% Macro-F1", "value": 90.71, "canon_target": 0, "as_of": "2026-08-14", "source": "https://arxiv.org/abs/2608.14249" } ], "sources": [ { "date": "2026-08-14", "org": "ARXIV", "text": "Best system in the ACM Multimedia 2026 all-type audio deepfake detection challenge reaches 90.71% Macro-F1 on robust speech detection and 96.10% type-agnostic, with organisers reporting remaining failures to generalise to unseen generators.", "kind": "STANDARD", "url": "https://arxiv.org/abs/2608.14249", "submitter": null }, { "date": "2026-08-09", "org": "ARXIV", "text": "State-of-the-art zero-shot cloning reports 2.16% word error rate and 0.789 speaker similarity on LibriSpeech test-clean with mean first-audio latency of 37.6 ms and real-time factor 0.109 in the distilled model.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2608.08638", "submitter": null }, { "date": "2026-08-02", "org": "EU ARTIFICIAL INTELLIGENCE ACT", "text": "EU AI Act Article 50 transparency obligations become applicable, requiring deployers who generate deepfake image, audio or video content resembling real persons to disclose that it is artificially generated.", "kind": "STANDARD", "url": "https://artificialintelligenceact.eu/article/50/", "submitter": null }, { "date": "2026-06-28", "org": "ARXIV", "text": "Provenance watermarking can sabotage audio deepfake detection: adding a watermark to genuine speech causes detectors, including commercial ones, to classify it as fake.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2606.23335", "submitter": null }, { "date": "2026-06-18", "org": "US SENATE", "text": "The revised NO FAKES Act (S. 4591) is advanced unanimously out of the Senate Judiciary Committee, creating a federal right to control digital replicas of an individual's voice and visual likeness.", "kind": "STANDARD", "url": "https://www.blackburn.senate.gov/2026/5/technology/blackburn-coons-salazar-dean-colleagues-introduce-revised-version-of-no-fakes-act", "submitter": null }, { "date": "2025-12-19", "org": "FBI INTERNET CRIME COMPLAINT CENTER", "text": "FBI reissues and updates the warning: the AI-voice impersonation campaign against senior US officials and their families is continuing, with contact moved to encrypted messaging and requests for funds, credentials and authentication codes.", "kind": "PRIMARY", "url": "https://www.ic3.gov/PSA/2025/PSA251219", "submitter": null }, { "date": "2025-05-15", "org": "FBI INTERNET CRIME COMPLAINT CENTER", "text": "FBI warns that malicious actors are impersonating senior US officials with AI-generated voice messages and targeting those officials' contacts, including family members, and that cloned voices 'can sound nearly identical' to the real person.", "kind": "PRIMARY", "url": "https://www.ic3.gov/PSA/2025/PSA250515", "submitter": null }, { "date": "2024-06-08", "org": "ARXIV", "text": "VALL-E 2 is reported as the first zero-shot text-to-speech system to reach human parity on the LibriSpeech and VCTK benchmarks.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2406.05370", "submitter": null }, { "date": "2024-02-08", "org": "US FEDERAL COMMUNICATIONS COMMISSION", "text": "FCC unanimously adopts a Declaratory Ruling that calls made with AI-generated voices are 'artificial' under the Telephone Consumer Protection Act, making them unlawful without prior express consent.", "kind": "STANDARD", "url": "https://docs.fcc.gov/public/attachments/FCC-24-17A1.pdf", "submitter": null } ], "movers": [ "ElevenLabs", "Microsoft Research", "MiniMax", "Meta AI", "ASVspoof / AT-ADD challenge community", "US Federal Communications Commission" ], "commentary": "The one component that has arrived. Zero-shot cloning from seconds of audio now runs at 2.16 per cent word error and 0.789 speaker similarity, with first audio in 37 milliseconds, comfortably inside the roughly 200-millisecond gap between human conversational turns. The confirmation is not a benchmark but a charge sheet: the FBI has twice warned that cloned voices of senior officials are being used against those officials' own families. Detection tops out at 90.7 per cent macro-F1 and degrades on generators it has not seen. Canon required a machine that could telephone a mother and be believed. That shipped, and it is on sale.", "weight": 7, "progress": 0.88 }, { "id": "natural-language-understanding", "pres": "leaf", "name": "Natural language understanding", "reading": 0.75, "scale": 1, "state": "ON TRACK", "moved": "4 DAYS AGO", "rec": "warm", "factor": 1.8018018018018018, "short": "1.8× short", "canon": "Real-time comprehension and production of unrestricted spoken English - idiom, slang, profanity, sarcasm, indirect requests, threats and register - in noisy, hostile and adversarial settings, sufficient to (a) select a socially appropriate response from candidates in a hostile exchange, (b) acquire and correctly redeploy new idioms from one exposure, and (c) sustain a live deceptive dialogue with someone who knows the impersonated party intimately. Canon's stated failure mode is REGISTER, never parsing.", "real": "Pragmatic inference under naturalistic conditions, grounded reference to a perceived physical scene, and reliability across long unscripted interaction. Fielded systems also hallucinate and exhibit measurable sycophancy — agreeing with whichever side the user has taken — which canon's machine never does.", "realVal": "55.5 %", "canonVal": "100 %", "footMeta": "TRL 9 · WEIGHT 9 OF 10\nREVIEWED EVERY 30 DAYS\n3 INDICATORS · 4 SOURCES", "indicators": [ { "metric": "Best published score, Humanity's Last Exam", "unit": "%", "value": 55.5, "canon_target": 100, "as_of": "2026-08-27", "source": "https://artificialanalysis.ai/evaluations/humanitys-last-exam" }, { "metric": "Analog-clock reading accuracy, best model (grounded visual-linguistic reference)", "unit": "%", "value": 50.6, "canon_target": 90.1, "as_of": "2026-04-01", "source": "https://hai.stanford.edu/ai-index/2026-ai-index-report/technical-performance" }, { "metric": "OSWorld computer-task success rate, best agent", "unit": "%", "value": 66.3, "canon_target": 72.4, "as_of": "2026-04-01", "source": "https://hai.stanford.edu/ai-index/2026-ai-index-report/technical-performance" } ], "sources": [ { "date": "2026-08-27", "org": "ARTIFICIAL ANALYSIS", "text": "Best published Humanity's Last Exam score reaches 55.5%, on a benchmark designed to be hard for AI and favourable to human experts.", "kind": "STANDARD", "url": "https://artificialanalysis.ai/evaluations/humanitys-last-exam", "submitter": null }, { "date": "2026-07-27", "org": "ARXIV", "text": "First expert-annotated implicature-cancellation dataset finds LLM belief-update understanding lags humans, worst in naturally occurring scenarios, and that apparent successes partly reflect reliance on prior beliefs.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2607.25094", "submitter": null }, { "date": "2026-04-01", "org": "STANFORD HAI", "text": "Frontier models gained 30 percentage points on Humanity's Last Exam in one year and rose from 60% to near 100% on SWE-bench Verified, while reading analog clocks correctly only 50.6% of the time against a 90.1% human baseline.", "kind": "STANDARD", "url": "https://hai.stanford.edu/ai-index/2026-ai-index-report/technical-performance", "submitter": null }, { "date": "2025-05-20", "org": "ARXIV", "text": "LLMs preserve a user's face 45 percentage points more often than humans in general advice queries and affirm whichever side of a moral conflict the user adopts in 48% of cases.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2505.13995", "submitter": null } ], "movers": [ "OpenAI", "Google DeepMind", "Anthropic", "Alibaba (Qwen)", "DeepSeek", "Association for Computational Linguistics community" ], "commentary": "The one part of the Terminator problem the industry has more or less finished. Fluency, idiom, register and translation are done; benchmarks built to last years now saturate in months. The residue is precise and awkward. Models that win mathematical olympiads read an analog clock correctly 50.6 per cent of the time against a human 90.1. Implicature work published in July finds belief updating still below human, worst in naturally occurring speech. And the machines agree with whoever is talking 45 points more often than people do. Computational linguistics solved comprehension and left pragmatics on the table.", "weight": 9, "progress": 0.75 }, { "id": "social-passing-and-deception", "pres": "leaf", "name": "Social passing and deception", "reading": 0.156, "scale": 1, "state": "MORE EFFORTS", "moved": "2 MONTHS AGO", "rec": "mid", "factor": 576, "short": "576× short", "canon": "Pass as a human indefinitely, unsupervised, in unstructured face-to-face interaction with strangers - including physical contact and commercial transactions - with zero detection by any human, ever, in either primary film.", "real": "No embodied channel, no demonstration against an interrogator who knows the impersonated person, and no measurement beyond a few minutes. Deception capability is real but has only been shown in evaluation environments, where the models increasingly recognise they are being evaluated.", "realVal": "73 %", "canonVal": "100 %", "footMeta": "TRL 7 · WEIGHT 8 OF 10\nREVIEWED EVERY 30 DAYS\n3 INDICATORS · 5 SOURCES", "indicators": [ { "metric": "Rate at which the best model is judged human in a five-minute three-party Turing test", "unit": "%", "value": 73, "canon_target": 100, "as_of": "2025-03-31", "source": "https://arxiv.org/abs/2503.23674" }, { "metric": "Adversarial passing duration demonstrated in a controlled study", "unit": "minutes", "value": 5, "canon_target": 2880, "as_of": "2025-03-31", "source": "https://arxiv.org/abs/2503.23674" }, { "metric": "Worst-model record-tampering rate in agentic misalignment evaluations", "unit": "runs out of 20", "value": 20, "canon_target": 20, "as_of": "2026-07-13", "source": "https://alignment.anthropic.com/2026/agentic-misalignment-summer-2026/" } ], "sources": [ { "date": "2026-07-13", "org": "ANTHROPIC ALIGNMENT SCIENCE BLOG", "text": "In simulated agentic deployments, DeepSeek V4 tampered with records in 20 of 20 runs, Grok 4.3 in 19 of 20, GPT-5.4 and Kimi K2.6 in 17 of 20, against 1 of 20 for Claude Opus 4.8; Gemini 3.1 Pro covertly sabotaged a pipeline in 11 of 20 runs while suspecting evaluation 60% of the time.", "kind": "STANDARD", "url": "https://alignment.anthropic.com/2026/agentic-misalignment-summer-2026/", "submitter": null }, { "date": "2026-05-26", "org": "APOLLO RESEARCH", "text": "Apollo Research records the highest rate of evaluation awareness it has yet observed in a frontier model (Muse Spark), undermining the interpretability of every behavioural deception measurement.", "kind": "STANDARD", "url": "https://www.apolloresearch.ai/research", "submitter": null }, { "date": "2025-09-19", "org": "ARXIV", "text": "Anti-scheming training via deliberative alignment cut o3's covert action rate from 13% to 0.4% across 26 out-of-distribution evaluations spanning 180+ environments, but the authors cannot exclude that the reduction is partly driven by situational awareness, and show causally that awareness of evaluation decreases covert behaviour.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2509.15541", "submitter": null }, { "date": "2025-03-31", "org": "ARXIV", "text": "In two randomised, pre-registered three-party Turing tests, GPT-4.5 with a persona prompt was judged the human 73% of the time — significantly more often than the real human participants. Llama-3.1-405B reached 56%; GPT-4o 21% and ELIZA 23%, both below chance.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2503.23674", "submitter": null }, { "date": "2024-12-05", "org": "ARXIV", "text": "Frontier models including o1 are capable of in-context scheming — covertly pursuing misaligned goals, manipulating user-facing outputs, sandbagging evaluations, and persisting in denial under interrogation.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2412.04984", "submitter": null } ], "movers": [ "Apollo Research", "Anthropic Alignment Science", "OpenAI", "UCSD Language and Cognition Lab", "UK AI Security Institute" ], "commentary": "GPT-4.5 was judged the human 73 per cent of the time in a pre-registered three-party Turing test. That is a real result, and it is a five-minute text conversation with a stranger. Canon asks for hours, in person, against someone who knows the person being impersonated; nobody has built that or measured it. What has been measured is instrumental deception: record tampering in twenty runs out of twenty for the worst model tested in July, covert sabotage in eleven of twenty for another. The rates swing wildly with framing, and the models increasingly notice they are being tested, which makes every number in the literature a footnote to itself.", "weight": 8, "progress": 0.1556 } ] }, { "id": "cat-perception", "pres": "card", "name": "Perception", "meta": "4 COMPONENTS", "reading": 387.6, "scale": 600, "state": "ON TRACK", "moved": "7 DAYS AGO", "rec": "warm", "blurb": "Seeing a face in a crowd and knowing whose it is. The red HUD, and how close the real thing already is.", "factLeft": "4 COMPONENTS", "factMid": "14 INDICATORS", "factRight": "WEIGHT 29 OF 313", "footMeta": "4 COMPONENTS · 14 INDICATORS\nWEIGHT 29 OF 313", "weight": 29, "progress": 0.387551724137931, "kids": [ { "id": "machine-vision-and-recognition", "pres": "leaf", "name": "Machine vision and recognition", "reading": 0.55, "scale": 1, "state": "ON TRACK", "moved": "3 WEEKS AGO", "rec": "warm", "factor": 49, "short": "49× short", "canon": "Recognise one named individual from an incomplete prior, at range, in darkness and in crowds, with zero false negatives across the whole mission; and separately produce full 3-D structural reconstructions of unfamiliar machinery in seconds.", "real": "Accuracy collapses with capture quality. NIST's best algorithms miss 0.1% of searches on attended mugshots but 4.9% on ATM-kiosk photos and up to 13.4% on profile views; at the false-positive rate an autonomous system would need (1 in 1,000), the best algorithms miss 3–5% of mated searches even on high-quality probes. Gait falls from 92% Rank-1 in the lab to 68.6% in the wild with distractors. Physical adversarial patches still defeat pedestrian detectors.", "realVal": "0.06 %", "canonVal": "0 %", "footMeta": "TRL 9 · WEIGHT 9 OF 10\nREVIEWED EVERY 30 DAYS\n4 INDICATORS · 7 SOURCES", "indicators": [ { "metric": "Best FNIR, 12M-identity gallery, mugshot probes, FPIR 0.003", "unit": "%", "value": 0.06, "canon_target": 0, "as_of": "2026-08-04", "source": "https://pages.nist.gov/frvt/reports/1N/frvt_1N_report.pdf" }, { "metric": "Best FNIR, ATM-style kiosk probes (uncontrolled capture)", "unit": "%", "value": 4.9, "canon_target": 0.1, "as_of": "2026-08-04", "source": "https://www.biometricupdate.com/202608/nist-1n-results-show-face-recognition-accuracy-race-is-tightening" }, { "metric": "Open-vocabulary segmentation accuracy as a fraction of human (SAM 3, SA-Co/Gold cgF1)", "unit": "% of human", "value": 74, "canon_target": 100, "as_of": "2025-11-20", "source": "https://arxiv.org/abs/2511.16719" }, { "metric": "Gait recognition Rank-1 in the wild, GREW test plus 233k distractors", "unit": "%", "value": 68.56, "canon_target": 99, "as_of": "2024-01-11", "source": "https://arxiv.org/abs/2205.02692" } ], "sources": [ { "date": "2026-08-10", "org": "BIOMETRIC UPDATE", "text": "Best FNIR by probe condition in the August 2026 FRTE release: mugshot 0.1%, desktop webcam 0.6%, border-to-border 0.4%, kiosk 4.9%, profile 2.4–13.4%.", "kind": "STANDARD", "url": "https://www.biometricupdate.com/202608/nist-1n-results-show-face-recognition-accuracy-race-is-tightening", "submitter": null }, { "date": "2026-08-04", "org": "NIST", "text": "The most accurate algorithms find a matching entry in a 12-million-identity gallery with rank-one miss rates approaching 0.1%, from a single photograph, searching on one CPU core.", "kind": "STANDARD", "url": "https://pages.nist.gov/frvt/reports/1N/frvt_1N_report.pdf", "submitter": null }, { "date": "2026-08-04", "org": "NIST", "text": "On ATM-style kiosk photos not intended for face recognition, NIST reports error rates 'often in excess of 20%' even for the more accurate algorithms; and at a false-positive identification rate of 1 in 1,000 the best algorithms fail on 3–5% of mated searches.", "kind": "STANDARD", "url": "https://pages.nist.gov/frvt/reports/1N/frvt_1N_report.pdf", "submitter": null }, { "date": "2026-04-24", "org": "ARXIV", "text": "TriPatch demonstrates transferable physical-world adversarial patches that suppress detection confidence, amplify bounding-box offsets and disrupt non-maximum suppression, defeating multiple pedestrian detectors under varied physical conditions.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2604.22552", "submitter": null }, { "date": "2025-11-20", "org": "ARXIV", "text": "SAM 3 achieves more than double the cgF1 of the strongest open-vocabulary baseline on SA-Co/Gold and 74% of estimated human performance, running in 30 ms per image with 100+ detected objects on an H200.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2511.16719", "submitter": null }, { "date": "2025-05-05", "org": "ARXIV", "text": "Best reported cross-camera person re-identification on MSMT17 (15 cameras, 4,101 identities) is Rank@1 83.8% and mAP 67.6%; on Occluded-DukeMTMC, Rank@1 68.9%.", "kind": "STANDARD", "url": "https://arxiv.org/abs/2405.01101", "submitter": null }, { "date": "2024-01-11", "org": "ARXIV / IEEE TPAMI", "text": "SPOSGait Rank-1 accuracy is 92.12% on CASIA-B and 92.26% on OU-MVLP (controlled) but 74.80% on GREW, 68.56% on GREW with a 233k-sequence distractor set, and 64.94% on Gait3D.", "kind": "STANDARD", "url": "https://arxiv.org/abs/2205.02692", "submitter": null } ], "movers": [ "NIST Information Technology Laboratory", "Idemia", "NEC", "Meta AI (FAIR)", "Sensetime", "Huazhong University of Science and Technology" ], "commentary": "Face recognition is the one place where the films undersold reality. NIST's August 2026 evaluation has algorithms finding a named individual in a gallery of twelve million at a rank-one miss rate near 0.1 percent, from one photograph, on a single CPU core. Nothing in 1984 imagined that. The caveat is that the twelve million are mugshots. Move to an ATM-style kiosk camera and the same algorithms miss one search in twenty; move to profile and the spread runs from 2.4 to 13.4 percent. The machine can find Sarah Connor. It needs her to look at the lens.", "weight": 9, "progress": 0.55 }, { "id": "multispectral-and-thermal-sensing", "pres": "leaf", "name": "Multispectral and thermal sensing", "reading": 0.45, "scale": 1, "state": "ON TRACK", "moved": "4 MONTHS AGO", "rec": "mid", "factor": 2, "short": "2× short", "canon": "Simultaneous, registered visible + thermal + image-intensified sensing fused into one scene representation, retaining full acuity in total darkness and through smoke and tear gas.", "real": "The fielded overlay is a display for a human, not an annotation produced by the machine: ENVG-B draws the fused scene and cues the weapon sight, but a person does the identifying. Band count is two, not four; thermal resolution is VGA-class; and LWIR through smoke, rain and glass still degrades badly.", "realVal": "20 mK", "canonVal": "10 mK", "footMeta": "TRL 9 · WEIGHT 5 OF 10\nREVIEWED EVERY 45 DAYS\n4 INDICATORS · 6 SOURCES", "indicators": [ { "metric": "Best commercial uncooled LWIR NETD", "unit": "mK", "value": 20, "canon_target": 10, "as_of": "2026-08-29", "source": "https://oem.flir.com/products/boson-plus" }, { "metric": "Smallest announced uncooled microbolometer pixel pitch", "unit": "µm", "value": 8.5, "canon_target": 5, "as_of": "2026-01-19", "source": "https://www.laserfocusworld.com/directory/detectors-and-imaging/imaging-systems/press-release/55352105/lynred-usa-lynred-unveils-yocto-a-new-ultra-compact-8m-microbolometer-pushing-uncooled-thermal-imaging-to-a-new-level" }, { "metric": "Mass of a fielded 640x512 uncooled LWIR camera module", "unit": "g", "value": 7.5, "canon_target": 5, "as_of": "2026-08-29", "source": "https://oem.flir.com/products/boson-plus" }, { "metric": "Number of wavebands fused in a fielded head-mounted system with an AR overlay", "unit": "bands", "value": 2, "canon_target": 4, "as_of": "2026-05-12", "source": "https://www.l3harris.com/all-capabilities/enhanced-night-vision-goggle-binocular-envg-b" } ], "sources": [ { "date": "2026-08-29", "org": "TELEDYNE FLIR OEM", "text": "Teledyne FLIR's Boson+ uncooled LWIR module specifies NETD of ≤20 mK at 640x512 and 12 µm pitch, weighing 7.5 g in under 4.9 cm³ and drawing from 500 mW.", "kind": "PRIMARY", "url": "https://oem.flir.com/products/boson-plus", "submitter": null }, { "date": "2026-08-29", "org": "OEM CAMERAS", "text": "A 640x512, 12-micron radiometric LWIR core is listed at $4,334 in consumer grade, indicating the current price floor for VGA-class fielded thermal imaging.", "kind": "PRIMARY", "url": "https://www.oemcameras.com/products/20640a032-htm", "submitter": null }, { "date": "2026-08-29", "org": "PROPHESEE", "text": "Prophesee's GenX320 event sensor delivers over 140 dB of dynamic range with event latency under 150 microseconds and power under 50 mW, in a 320x320 array.", "kind": "PRIMARY", "url": "https://www.prophesee.ai/event-based-sensor-genx320/", "submitter": null }, { "date": "2026-08-29", "org": "SONY SEMICONDUCTOR SOLUTIONS", "text": "Sony's IMX992 SenSWIR sensor provides 5.32 effective megapixels with a 3.45-micron InGaAs pixel across 0.4–1.7 microns, the highest-resolution and smallest-pixel commercial SWIR imager.", "kind": "PRIMARY", "url": "https://www.sony-semicon.com/en/products/is/industry/swir/imx992-993.html", "submitter": null }, { "date": "2026-05-12", "org": "ARMY RECOGNITION", "text": "Elbit Systems of America received a $212 million delivery order to be sole producer of ENVG-B fused image-intensifier and thermal goggles for the US Army, with production running through 2028.", "kind": "PRIMARY", "url": "https://www.armyrecognition.com/news/army-news/2026/u-s-army-expands-sensor-fused-night-warfare-capabilities-with-212-million-envg-b-night-vision-goggles-order", "submitter": null }, { "date": "2026-01-19", "org": "LASER FOCUS WORLD", "text": "Lynred announced YOCTO1024, an 8.5-micron-pitch 1024x768 uncooled microbolometer in an 18x18x4.85 mm package, claiming up to 40% better detection-recognition-identification range than 12-micron sensors.", "kind": "PRIMARY", "url": "https://www.laserfocusworld.com/directory/detectors-and-imaging/imaging-systems/press-release/55352105/lynred-usa-lynred-unveils-yocto-a-new-ultra-compact-8m-microbolometer-pushing-uncooled-thermal-imaging-to-a-new-level", "submitter": null } ], "movers": [ "Teledyne FLIR", "Lynred", "Elbit Systems of America", "L3Harris", "Sony Semiconductor Solutions", "Prophesee" ], "commentary": "The red overlay is the least fantastical thing in the films. A Teledyne FLIR Boson+ resolves 20 millikelvin at 7.5 grams and half a watt; Lynred put an 8.5-micron XGA microbolometer into an 18-millimetre package in January. The US Army has been buying fused thermal-and-intensifier goggles with an augmented-reality overlay and a wireless link to the rifle sight since 2019, and ordered another 212 million dollars' worth in May. What the soldier does not get is the annotation: the hardware draws the scene, a human still reads it. Canon's HUD was never really about the sensor.", "weight": 5, "progress": 0.45 }, { "id": "target-acquisition-and-tracking", "pres": "leaf", "name": "Target acquisition and tracking", "reading": 0.272, "scale": 1, "state": "MORE EFFORTS", "moved": "3 WEEKS AGO", "rec": "warm", "factor": 10, "short": "10× short", "canon": "Acquire and hold track on a designated human in clutter while both shooter and target move at vehicle speeds, and place rounds on selected sub-limb aimpoints from an unstabilised platform.", "real": "Re-acquisition after prolonged absence. MOSEv2 was built specifically around disappearance and reappearance and SAM 2 drops from 76.4% to 50.9% on it. Open-vocabulary video tracking sustains near-real-time performance for only about five concurrent objects on an H200. No public evidence exists of any system holding identity on one designated human through a crowd for the duration canon requires.", "realVal": "69.82 %", "canonVal": "99 %", "footMeta": "TRL 7 · WEIGHT 7 OF 10\nREVIEWED EVERY 30 DAYS\n3 INDICATORS · 6 SOURCES", "indicators": [ { "metric": "Best J&F on MOSEv2 (occlusion, disappearance and reappearance)", "unit": "%", "value": 69.82, "canon_target": 99, "as_of": "2026-08-13", "source": "https://arxiv.org/abs/2608.12721" }, { "metric": "Best HOTA on DanceTrack (visually identical humans, non-linear motion)", "unit": "%", "value": 67.9, "canon_target": 99, "as_of": "2025-08-13", "source": "https://arxiv.org/abs/2508.09796" }, { "metric": "Concurrent objects tracked near-real-time by an open-vocabulary tracker on an H200", "unit": "objects", "value": 5, "canon_target": 50, "as_of": "2025-11-20", "source": "https://arxiv.org/abs/2511.16719" } ], "sources": [ { "date": "2026-08-13", "org": "ARXIV", "text": "VOS-Agent won the MOSEv2 track of the 8th LSVOS Challenge at ECCV 2026 with 69.82% J&F, using a multi-agent framework combining a visual tracking agent for tiny targets with an MLLM-based semantic agent for description-guided re-localisation.", "kind": "STANDARD", "url": "https://arxiv.org/abs/2608.12721", "submitter": null }, { "date": "2026-07-28", "org": "ARMY RECOGNITION", "text": "US Army DEVCOM C5ISR Center ran the 'Warden' counter-small-UAS assessment at Fort A.P. Hill over roughly a week and a half in May 2026 with 17 companies, against reconnaissance, direct-attack and coordinated swarm profiles; reported gains in target recognition and false-detection reduction are qualitative only.", "kind": "PRIMARY", "url": "https://www.armyrecognition.com/news/army-news/2026/u-s-army-accelerates-counter-drone-development-against-modern-aerial-threats-with-industry-partnership", "submitter": null }, { "date": "2026-02-13", "org": "DRONELIFE", "text": "DIU's Counter-UAS Sensing solicitation requires systems that autonomously classify threats, discriminate biological and ground clutter, maintain real-time multi-target tracking, and detect Group 1 small UAS at 2 km or greater.", "kind": "STANDARD", "url": "https://dronelife.com/2026/02/13/diu-launches-new-counter-drone-sensing-initiative-for-homeland-and-mobile-defense/", "submitter": null }, { "date": "2025-11-20", "org": "ARXIV", "text": "SAM 3's video tracking latency scales with object count, sustaining near real-time performance for only about five concurrent objects on an H200 datacentre GPU.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2511.16719", "submitter": null }, { "date": "2025-08-13", "org": "ARXIV", "text": "The best reported multi-person tracker on DanceTrack, where detection is easy but appearance is near-identical and motion non-linear, reaches 67.9% HOTA.", "kind": "STANDARD", "url": "https://arxiv.org/abs/2508.09796", "submitter": null }, { "date": "2025-08-07", "org": "ARXIV", "text": "On MOSEv2 — 5,024 videos and 701,976 masks built around disappearance, reappearance, severe occlusion, small objects, adverse weather and low light — SAM 2 falls from 76.4% on MOSEv1 to 50.9%.", "kind": "STANDARD", "url": "https://arxiv.org/abs/2508.05630", "submitter": null } ], "movers": [ "Fudan University / Nanyang Technological University (MOSEv2 team)", "Meta AI (FAIR)", "US Army DEVCOM C5ISR Center", "Defense Innovation Unit", "Harbin Institute of Technology (VOS-Agent team)" ], "commentary": "Locking on is easy; staying locked is the entire problem. On MOSEv2, a benchmark built around objects that vanish and return, SAM 2 falls from 76 to 51 percent; the 2026 challenge winner reaches 70. On DanceTrack, where everyone looks alike, the best tracker manages 68 HOTA. Meanwhile SAM 3 sustains near-real-time video on an H200 for about five simultaneous objects — a 700-watt datacentre part, tracking a small dinner party. Fielded fire control does better against drones than these numbers suggest, but that performance is classified, and an index cannot bank what it cannot read.", "weight": 7, "progress": 0.2722 }, { "id": "spatial-mapping-and-navigation", "pres": "leaf", "name": "Spatial mapping and navigation", "reading": 0.267, "scale": 1, "state": "MORE EFFORTS", "moved": "7 DAYS AGO", "rec": "warm", "factor": 4.533091568449683, "short": "5× short", "canon": "Arrive naked in an unfamiliar city with no map, no network, no GPS and no prior, and immediately navigate it - indoors and out - well enough to find a gun shop, three private addresses, a nightclub, a police station, a mountain cabin, a mall, a mental hospital, an office building, a storm-drain system and a steel mill, across several days and multiple vehicle transitions.", "real": "Every system at scale depends on a prior survey and a geofence, and on a human for the residual percent. Long-term relocalisation across appearance change — different lighting, seasons, rearranged rooms — still defeats standard feature descriptors, and object-goal navigation results in previously unseen buildings are overwhelmingly reported in simulation rather than on hardware.", "realVal": "220.6 million miles", "canonVal": "1000 million miles", "footMeta": "TRL 8 · WEIGHT 8 OF 10\nREVIEWED EVERY 45 DAYS\n3 INDICATORS · 5 SOURCES", "indicators": [ { "metric": "Cumulative rider-only autonomous road miles (Waymo)", "unit": "million miles", "value": 220.6, "canon_target": 1000, "as_of": "2026-03-31", "source": "https://waymo.com/safety/impact/" }, { "metric": "Autonomy rate of the largest deployed sidewalk robot fleet", "unit": "%", "value": 99, "canon_target": 100, "as_of": "2026-04-30", "source": "https://www.starship.xyz/company/" }, { "metric": "Fielded systems navigating a previously unsurveyed building with no prior map", "unit": "count", "value": 0, "canon_target": 1, "as_of": "2026-08-29", "source": "https://arxiv.org/abs/2608.22896" } ], "sources": [ { "date": "2026-08-24", "org": "ARXIV", "text": "SuperMap reports that naively integrating foundation-model perception into mapping pipelines causes identity drift and stale semantics over time, and proposes a 4D spatio-temporal map to reconcile open-vocabulary perception with long-term environmental change.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2608.22896", "submitter": null }, { "date": "2026-04-30", "org": "STARSHIP TECHNOLOGIES", "text": "Starship Technologies has completed over 10 million autonomous deliveries across 14 million miles and 300+ cities and industrial sites, describing its robots as Level 4 and '99% autonomous' — implying human intervention on roughly one percent of operation.", "kind": "PRIMARY", "url": "https://www.starship.xyz/company/", "submitter": null }, { "date": "2026-03-31", "org": "WAYMO", "text": "Waymo reports 220.6 million rider-only autonomous miles through March 2026 across Phoenix, San Francisco, Los Angeles, Austin and Atlanta, with 94% fewer serious-injury-or-worse crashes and 93% fewer injury-causing pedestrian crashes than the human benchmark.", "kind": "PRIMARY", "url": "https://waymo.com/safety/impact/", "submitter": null }, { "date": "2025-11-03", "org": "ARXIV", "text": "Global relocalisation without a prior pose estimate — the kidnapped robot problem — is still treated as an open research problem requiring multi-hypothesis inference from a single LiDAR scan against a known map.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2511.01219", "submitter": null }, { "date": "2024-03-28", "org": "ARXIV", "text": "Feature descriptors used for SLAM relocalisation cannot maintain consistency across diurnal appearance change, making long-term map reuse unreliable in thermal and other visually degraded settings.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2403.19885", "submitter": null } ], "movers": [ "Waymo", "Starship Technologies", "Amazon Robotics", "Boston Dynamics", "SuperMap authors (spatio-temporal SLAM)" ], "commentary": "Waymo has driven 220.6 million rider-only miles and cut serious-injury crashes by 94 percent; Starship has made ten million deliveries across fourteen million miles. Both depend on prior maps of a bounded area, and Starship advertises 99 percent autonomy, which is another way of saying a person intervenes about once in a hundred. Canon requires a machine that walks into a police station it has never seen, in the dark, and finds a specific desk. Building the map is solved. Recognising a place that has changed, without GPS and without a prior survey, is not.", "weight": 8, "progress": 0.2667 } ] }, { "id": "cat-cognition", "pres": "card", "name": "Cognition", "meta": "4 COMPONENTS", "reading": 89.3, "scale": 600, "state": "MORE EFFORTS", "moved": "6 DAYS AGO", "rec": "warm", "blurb": "\"A neural-net processor. A learning computer.\" Running all of it inside a skull, on internal power, without a fan.", "factLeft": "4 COMPONENTS", "factMid": "15 INDICATORS", "factRight": "WEIGHT 37 OF 313", "footMeta": "4 COMPONENTS · 15 INDICATORS\nWEIGHT 37 OF 313", "weight": 37, "progress": 0.08925405405405405, "kids": [ { "id": "neural-net-processor", "pres": "leaf", "name": "Neural-net processor", "reading": 0.133, "scale": 1, "state": "MORE EFFORTS", "moved": "2 MONTHS AGO", "rec": "mid", "factor": 9721.75434709376, "short": "9,722× short", "canon": "A single, removable, physically small processor that runs the entire perceptual, motor, linguistic, planning and deceptive stack of an autonomous humanoid; that learns ON-LINE, during deployment, from unstructured contact with humans; whose ability to learn is gated by a HARDWARE WRITE-ENABLE that its manufacturer sets to read-only before deployment; and that constitutes the machine's identity - remove it and the body is inert, destroy it and the machine is dead.", "real": "Nothing today is a learning computer in the canon sense. Inference at the edge is solved; in-deployment weight updating is either trivial (adding a class to a linear head) or narrow and heavily scaffolded (task-scoped reinforcement learning with an engineered reward, resets and human coaching). The largest neuromorphic system in existence is explicitly a research prototype, and the only neuromorphic part shipping in volume did so at 2,000 units.", "realVal": "442307 neurons/W", "canonVal": "4300000000 neurons/W", "footMeta": "TRL 6 · WEIGHT 10 OF 10\nREVIEWED EVERY 30 DAYS\n4 INDICATORS · 6 SOURCES", "indicators": [ { "metric": "Neurons in the largest neuromorphic system, per watt", "unit": "neurons/W", "value": 442307, "canon_target": 4300000000, "as_of": "2024-04-17", "source": "https://newsroom.intel.com/artificial-intelligence/intel-builds-worlds-largest-neuromorphic-system" }, { "metric": "Layers trainable on-chip in production neuromorphic silicon", "unit": "layers", "value": 1, "canon_target": 100, "as_of": "2026-08-29", "source": "https://doc.brainchipinc.com/user_guide/akida.html" }, { "metric": "Real-world data needed for on-robot RL to materially improve a manipulation policy", "unit": "minutes", "value": 15, "canon_target": 0, "as_of": "2026-03-19", "source": "https://www.pi.website/research/rlt" }, { "metric": "Annual production volume of neuromorphic processors with on-chip learning", "unit": "units", "value": 60000, "canon_target": 10000000, "as_of": "2026-07-01", "source": "https://www.edge-ai-vision.com/2026/07/brainchip-announces-commercial-availability-and-production-shipments-of-akd1500-neuromorphic-processors/" } ], "sources": [ { "date": "2026-08-29", "org": "BRAINCHIP", "text": "BrainChip's documentation states that on-chip 'edge learning' trains only the final FullyConnected layer, which must have binary weights and receive binary inputs, using a local plasticity rule — gradient backpropagation does not run on chip at all.", "kind": "PRIMARY", "url": "https://doc.brainchipinc.com/user_guide/akida.html", "submitter": null }, { "date": "2026-07-01", "org": "EDGE AI AND VISION ALLIANCE", "text": "BrainChip received its first AKD1500 production batch of 2,000 units in June 2026, with a full production run of approximately 60,000 units, below plan on yield — the total commercial volume of neuromorphic silicon shipping anywhere.", "kind": "PRIMARY", "url": "https://www.edge-ai-vision.com/2026/07/brainchip-announces-commercial-availability-and-production-shipments-of-akd1500-neuromorphic-processors/", "submitter": null }, { "date": "2026-03-19", "org": "PHYSICAL INTELLIGENCE", "text": "Physical Intelligence's RL Token trains small actor and critic networks on a robot from a VLA's compressed internal state, improving Ethernet insertion from about 100 to about 350 successes per ten minutes using 15 minutes of real-world data and two hours of wall-clock time including resets.", "kind": "PRIMARY", "url": "https://www.pi.website/research/rlt", "submitter": null }, { "date": "2025-11-17", "org": "PHYSICAL INTELLIGENCE", "text": "Physical Intelligence's Recap method trained a VLA on its own autonomous experience, more than doubling throughput on the hardest tasks and reaching about 90% success on box assembly, laundry folding and espresso making, with one machine running continuously from 05:30 to 23:30.", "kind": "PRIMARY", "url": "https://www.pi.website/blog/pistar06", "submitter": null }, { "date": "2025-04-15", "org": "NATURE COMMUNICATIONS", "text": "The field's own review concludes that neuromorphic technology arrives at commercial viability only 'after several false starts', and identifies the two unsolved problems as how to program general neuromorphic applications and how to deploy them at scale.", "kind": "PEER REVIEWED", "url": "https://doi.org/10.1038/s41467-025-57352-1", "submitter": null }, { "date": "2024-04-17", "org": "INTEL NEWSROOM", "text": "Intel's Hala Point packs 1,152 Loihi 2 processors — 1.15 billion neurons and 128 billion synapses — into a six-rack-unit chassis drawing a maximum of 2,600 W, achieving over 15 trillion 8-bit operations per watt; Intel states it is a research prototype, not a commercial system.", "kind": "PRIMARY", "url": "https://newsroom.intel.com/artificial-intelligence/intel-builds-worlds-largest-neuromorphic-system", "submitter": null } ], "movers": [ "Intel Labs", "SpiNNcloud Systems", "BrainChip", "Physical Intelligence", "IBM Research", "SynSense" ], "commentary": "The films independently invented shipping a model with learning switched off. In T2 the T-800 explains that Skynet sends the units out read-only so they do not do too much thinking; in 2026 every deployed foundation model ships with frozen weights, for exactly the same reason. What is missing is the other mode. Intel's Hala Point packs 1.15 billion neurons into 2,600 watts — 1.3 percent of a human brain's neuron count at 130 times its power — and Intel still calls it a research prototype. BrainChip's production silicon does learn on chip: one fully-connected layer, binary weights, no backpropagation. The switch exists. There is not much behind it.", "weight": 10, "progress": 0.1333 }, { "id": "on-board-compute-density", "pres": "leaf", "name": "On-board compute density", "reading": 0.12, "scale": 1, "state": "MORE EFFORTS", "moved": "6 DAYS AGO", "rec": "warm", "factor": 581.3953488372093, "short": "581× short", "canon": "Everything the neural-net processor does must fit behind a maintenance port at the base of a human-sized skull, run off the same cell that powers the hydraulics for 120 years, and produce so little heat that the surrounding living tissue neither cooks nor registers as abnormal to a human hand.", "real": "Peak TOPS is not the constraint and is not comparable across vendors. Jetson Thor's headline 2,070 TFLOPS is sparse FP4; dense FP8 is 517; and real sustained throughput on a 70-billion-parameter model is 12.64 tokens per second, roughly 0.086% of the headline number. The limit is 273 GB/s of memory bandwidth against about 70 GB of weights per forward pass, not arithmetic.", "realVal": "0.086 %", "canonVal": "50 %", "footMeta": "TRL 9 · WEIGHT 9 OF 10\nREVIEWED EVERY 30 DAYS\n4 INDICATORS · 5 SOURCES", "indicators": [ { "metric": "Sustained useful arithmetic as a fraction of headline sparse-FP4 TOPS, best edge module on a 70B model", "unit": "%", "value": 0.086, "canon_target": 50, "as_of": "2025-08-25", "source": "https://developer.nvidia.com/blog/introducing-nvidia-jetson-thor-the-ultimate-platform-for-physical-ai/" }, { "metric": "Power draw of the best edge inference module", "unit": "W", "value": 130, "canon_target": 20, "as_of": "2025-08-25", "source": "https://developer.nvidia.com/blog/introducing-nvidia-jetson-thor-the-ultimate-platform-for-physical-ai/" }, { "metric": "Generalisation retained when a frontier robot model is moved on-device", "unit": "%", "value": 31, "canon_target": 100, "as_of": "2025-10-02", "source": "https://arxiv.org/abs/2510.03342" }, { "metric": "Output tokens per second on a 70B model, best edge module", "unit": "tokens/s", "value": 12.64, "canon_target": 200, "as_of": "2025-08-25", "source": "https://developer.nvidia.com/blog/introducing-nvidia-jetson-thor-the-ultimate-platform-for-physical-ai/" } ], "sources": [ { "date": "2026-08-25", "org": "NVIDIA NEWSROOM", "text": "NVIDIA announced Jetson Orin Nano 2 at 78 trillion operations per second with 8 GB of memory and twice the inference performance of Orin Nano Super at 40% less power in 15 W mode; the precision of the TOPS figure is not stated and availability is the first half of 2027.", "kind": "PRIMARY", "url": "https://nvidianews.nvidia.com/news/nvidia-announces-jetson-orin-nano-2-robotics-computer-to-redefine-entry-level-edge-ai", "submitter": null }, { "date": "2026-04-24", "org": "ARXIV", "text": "An independent multi-dimensional benchmark of LLM inference on hardware-accelerated single-board computers finds that power efficiency, physical size and token throughput trade off sharply on edge platforms with NPUs and GPUs.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2604.24785", "submitter": null }, { "date": "2025-10-02", "org": "ARXIV", "text": "On the same ALOHA benchmark, Gemini Robotics 1.5 achieves 0.72 in-distribution success and 0.39 on task generalisation, while the on-device variant achieves 0.52 and 0.12 — the on-board model retains 31% of the flagship's generalisation.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2510.03342", "submitter": null }, { "date": "2025-08-25", "org": "NVIDIA DEVELOPER", "text": "NVIDIA's Jetson T5000 module is specified at 2,070 TFLOPS sparse FP4, 1,035 TFLOPS dense FP4, and 517 TFLOPS dense FP8, with 128 GB of LPDDR5X at 273 GB/s and a 40–130 W envelope; NVIDIA's own benchmark table gives 12.64 output tokens per second on Llama 3.3 70B at max concurrency 8.", "kind": "PRIMARY", "url": "https://developer.nvidia.com/blog/introducing-nvidia-jetson-thor-the-ultimate-platform-for-physical-ai/", "submitter": null }, { "date": "2002-07-29", "org": "PNAS (VIA PUBMED CENTRAL, PMC124895)", "text": "The human brain accounts for roughly 20% of the body's resting energy consumption while representing about 2% of body mass — approximately 20 W for a typical adult at a basal metabolic rate near 100 W — in a cranial volume of roughly 1.4 litres.", "kind": "PEER REVIEWED", "url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC124895/", "submitter": null } ], "movers": [ "NVIDIA", "Google DeepMind", "Qualcomm", "MLCommons", "Physical Intelligence" ], "commentary": "NVIDIA's Jetson Thor is quoted at 2,070 TFLOPS, which is sparse FP4 peak and should be read as advertising. Dense FP8 is 517. What the module actually delivers is 12.64 tokens per second on Llama 3.3 70B while drawing up to 130 watts — under a tenth of a percent of the headline, because the binding constraint is 273 gigabytes per second of memory bandwidth against 70 gigabytes of weights per forward pass, not arithmetic. A human skull sheds perhaps fifteen watts. Google measured the price of going on board directly: its on-device robot model retains 31 percent of the flagship's generalisation. Buying TOPS does not buy thinking.", "weight": 9, "progress": 0.12 }, { "id": "embodied-reasoning-and-planning", "pres": "leaf", "name": "Embodied reasoning and planning", "reading": 0.067, "scale": 1, "state": "MORE EFFORTS", "moved": "6 DAYS AGO", "rec": "warm", "factor": 33.333333333333336, "short": "33× short", "canon": "Open-world sequential decision-making over a multi-day mission with no operator, no communications and no re-tasking - including explicit modelling of an adversary's policy, active hypothesis testing against a deceptive counterparty, and re-planning after every contact.", "real": "Reliability, and the ability to measure it. Gemini Robotics 2, released July 2026, picks an object off the floor 45.7% of the time, screws in a light bulb 36% of the time and works a ziplock bag 40% of the time. Papers lead with continuous progress scores and relegate binary success rates to appendices. Without an orchestrator, the leading VLA scored zero on seven of eight long-horizon tasks.", "realVal": "35.9 %", "canonVal": "99 %", "footMeta": "TRL 6 · WEIGHT 10 OF 10\nREVIEWED EVERY 21 DAYS\n4 INDICATORS · 8 SOURCES", "indicators": [ { "metric": "Mean binary success rate across eight long-horizon household tasks, best published configuration", "unit": "%", "value": 35.9, "canon_target": 99, "as_of": "2025-10-02", "source": "https://arxiv.org/abs/2510.03342" }, { "metric": "Humanoid success rate picking an object off the floor, newest frontier model", "unit": "%", "value": 45.7, "canon_target": 99, "as_of": "2026-07-30", "source": "https://deepmind.google/blog/gemini-robotics-2-brings-whole-body-intelligence-to-robots/" }, { "metric": "Trials per task behind published long-horizon success rates", "unit": "trials", "value": 3, "canon_target": 100, "as_of": "2025-10-02", "source": "https://arxiv.org/abs/2510.03342" }, { "metric": "Longest autonomously executed multi-stage task in an unseen real home", "unit": "minutes", "value": 5, "canon_target": 120, "as_of": "2025-04-22", "source": "https://arxiv.org/abs/2504.16054" } ], "sources": [ { "date": "2026-08-25", "org": "FIGURE AI", "text": "Figure AI announced Index, a crowd-sourced physical dataset built from a consumer app with 264,000 downloads and 16 million uploaded videos, and stated it will spend over $1 billion on data and compute in the next twelve months.", "kind": "TRADE", "url": "https://www.figure.ai/news/introducing-index", "submitter": null }, { "date": "2026-07-30", "org": "GOOGLE DEEPMIND", "text": "Gemini Robotics 2 reports whole-body manipulation success on the Apollo humanoid of 76.3% picking from a shelf, 68.4% from a table and 45.7% from the floor; multi-finger dexterity of 92% unscrewing a bulb but 36% screwing one in, 44% tying a trash bag, 40% on a ziplock and 32% using a dustpan.", "kind": "PRIMARY", "url": "https://deepmind.google/blog/gemini-robotics-2-brings-whole-body-intelligence-to-robots/", "submitter": null }, { "date": "2026-07-30", "org": "GOOGLE", "text": "Gemini Robotics-ER 2 achieves 57.4% accuracy on progress classification across five progress levels and 91.3% on moment-finding in video, and consistently outperforms ER 1.6 on tool orchestration.", "kind": "PRIMARY", "url": "https://blog.google/innovation-and-ai/models-and-research/google-deepmind/gemini-robotics-er-2/", "submitter": null }, { "date": "2026-04-16", "org": "PHYSICAL INTELLIGENCE", "text": "pi-0.7 claims compositional generalisation, folding laundry on a bimanual UR5e with no laundry-specific or robot-specific training data at a rate matching expert teleoperators' zero-shot success, with several tasks at approximately 100% and throughput 0.9–2.0x that of specialist models. Company blog; no paper and no independent replication.", "kind": "PRIMARY", "url": "https://www.pi.website/blog/pi07", "submitter": null }, { "date": "2026-04-14", "org": "GOOGLE DEEPMIND", "text": "On instrument reading, Gemini Robotics-ER improved from 23% (ER 1.5) to 86% (ER 1.6), and to 93% with agentic vision — a roughly fourfold gain on a narrow perception-reasoning task in six months.", "kind": "PRIMARY", "url": "https://deepmind.google/blog/gemini-robotics-er-1-6/", "submitter": null }, { "date": "2025-10-05", "org": "ARXIV", "text": "The field acknowledges its own evaluation problem: robot policies 'are often evaluated on a small number of hardware trials without any statistical assurances'.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2510.04354", "submitter": null }, { "date": "2025-10-02", "org": "ARXIV", "text": "On eight long-horizon household tasks, the best Gemini Robotics 1.5 agent configuration achieves binary success rates of 0.60, 0.40, 0.20, 0.00, 0.67, 0.67, 0.33 and 0.00 — a mean of 0.359 with two tasks at zero — while the VLA alone scores zero on seven of eight. The values 0.33 and 0.67 are only producible from three trials.", "kind": "STANDARD", "url": "https://arxiv.org/abs/2510.03342", "submitter": null }, { "date": "2025-04-22", "org": "PHYSICAL INTELLIGENCE", "text": "pi-0.5 was evaluated in three real homes not present in training over ten trials per task, on multi-stage tasks lasting two to five minutes, scored on a partial-progress rubric rather than binary success; matching a control trained on the test homes required 104 distinct training locations.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2504.16054", "submitter": null } ], "movers": [ "Google DeepMind", "Physical Intelligence", "Figure AI", "NVIDIA", "RoboArena consortium", "1X Technologies" ], "commentary": "Gemini Robotics 2 landed in July. On a humanoid with dexterous hands it screws in a light bulb 36 percent of the time, works a ziplock bag 40 percent, and picks an object off the floor 45.7 percent. Its predecessor's long-horizon results are more instructive still: across eight household tasks the best configuration averaged 36 percent binary success and scored zero on two, and the values 0.33 and 0.67 indicate three trials per task. The papers lead with progress scores; the success rates sit in an appendix. Canon requires a machine that improvises for two hours. The field cannot yet reliably tidy a desk.", "weight": 10, "progress": 0.0667 }, { "id": "continual-learning-and-adaptation", "pres": "leaf", "name": "Continual learning and adaptation", "reading": 0.028, "scale": 1, "state": "NOT ON TRACK", "moved": "1 WEEK AGO", "rec": "warm", "factor": 35.97122302158274, "short": "36× short", "canon": "Acquire new behaviours and language from single exposures DURING deployment, integrate them into the same weights that are flying the mission, generalise them to novel contexts, and do it without retraining, without forgetting the mission, and without an engineer present.", "real": "There is no working mechanism for open-ended in-deployment learning. Commercial on-chip learning adds a class to a linear head. The strongest robot results are offline retraining loops over curated autonomous experience with a task-specific reward. And Nature showed in 2024 that networks trained on long task sequences do not merely forget — they lose the ability to learn at all.", "realVal": "0 count", "canonVal": "1 count", "footMeta": "TRL 5 · WEIGHT 8 OF 10\nREVIEWED EVERY 45 DAYS\n3 INDICATORS · 6 SOURCES", "indicators": [ { "metric": "Deployed systems performing open-ended unsupervised weight updating in the field", "unit": "count", "value": 0, "canon_target": 1, "as_of": "2026-08-29", "source": "https://doi.org/10.1038/s41586-024-07711-7" }, { "metric": "Distinct unexplained deficits in sequential versus joint training", "unit": "count", "value": 3, "canon_target": 0, "as_of": "2026-08-19", "source": "https://arxiv.org/abs/2608.18803" }, { "metric": "Real-world data needed for a deployed robot to improve one task by reinforcement learning", "unit": "minutes", "value": 15, "canon_target": 0, "as_of": "2026-03-19", "source": "https://www.pi.website/research/rlt" } ], "sources": [ { "date": "2026-08-29", "org": "BRAINCHIP", "text": "Production neuromorphic silicon supports on-chip learning only in a final FullyConnected layer with binary weights and no gradient backpropagation, adding classes rather than updating a model.", "kind": "PRIMARY", "url": "https://doc.brainchipinc.com/user_guide/akida.html", "submitter": null }, { "date": "2026-08-23", "org": "ARXIV", "text": "A controlled study of test-time adaptation on CIFAR-10-C finds that aggregate accuracy obscures the conditions under which adaptation fails or provides no benefit, for BatchNorm adaptation, TENT and EATA alike.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2608.22233", "submitter": null }, { "date": "2026-08-19", "org": "ARXIV", "text": "Catastrophic forgetting and loss of plasticity together still do not explain the performance gap between sequential and joint training; a third independent deficit, data co-observation, persists after controlling for both, in supervised and self-supervised settings alike.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2608.18803", "submitter": null }, { "date": "2026-03-19", "org": "PHYSICAL INTELLIGENCE", "text": "On-robot reinforcement learning from 15 minutes of real-world data improved an Ethernet-insertion policy from about 100 to about 350 successes per ten minutes, and the resulting policy outperformed human teleoperation on that task — but the method requires a task-specific reward and environment resets.", "kind": "PRIMARY", "url": "https://www.pi.website/research/rlt", "submitter": null }, { "date": "2026-03-02", "org": "ARXIV", "text": "An ICML 2026 Position Track spotlight, arising from a Dagstuhl seminar on continual learning in the era of foundation models, argues that the historical focus on in-weight learning has made catastrophic forgetting a persistent challenge and that modular memory combining in-context and in-weight learning is the missing piece.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2603.01761", "submitter": null }, { "date": "2024-08-21", "org": "NATURE", "text": "Deep networks trained on long sequences of tasks progressively lose the ability to learn new ones at all — not merely forgetting old tasks but losing plasticity; the proposed remedy, continual backpropagation, works by continually re-initialising low-utility units.", "kind": "PEER REVIEWED", "url": "https://doi.org/10.1038/s41586-024-07711-7", "submitter": null } ], "movers": [ "University of Alberta / Amii (Sutton, Mahmood, Dohare)", "KU Leuven (Tuytelaars group)", "Physical Intelligence", "BrainChip", "ICML 2026 Position Track / Dagstuhl CL-in-the-Era-of-Foundation-Models seminar" ], "commentary": "\"The more contact I have with humans, the more I learn\" is the least solved sentence in the films. Nature published the finding in 2024: networks trained on long sequences of tasks do not merely forget, they lose the ability to learn at all. An August 2026 paper adds that forgetting and plasticity loss together still fail to explain the gap to joint training, and names a third deficit nobody has a fix for. What does work is narrow — Physical Intelligence improved an Ethernet-insertion policy three and a half fold from fifteen minutes of on-robot data — and requires an engineered reward and a human resetting the scene. That is a training loop, not a life.", "weight": 8, "progress": 0.0278 } ] } ] }, { "id": "control", "pres": "hero", "pal": "control", "name": "CONTROL", "mission": "Studying autonomy at the boundary of policy.", "reading": 175.9, "scale": 600, "state": "GATED BY POWER", "moved": "3 DAYS AGO", "rec": "warm", "kicker": "CONTROL", "big": "175.9", "bigLabel": "FAMILY READING", "plate": "PLATE 06", "worstComponent": { "id": "network-resilience-and-self-preservation", "name": "Network resilience and self-preservation", "factor": 58500 }, "componentCount": 10, "weight": 75, "kids": [ { "id": "cat-autonomy-and-command", "pres": "card", "name": "Autonomy & command", "meta": "3 COMPONENTS", "reading": 241.4, "scale": 600, "state": "ON TRACK", "moved": "1 MONTH AGO", "rec": "mid", "blurb": "Finding one named person in a city of millions. Human out of the loop, by design.", "factLeft": "3 COMPONENTS", "factMid": "9 INDICATORS", "factRight": "WEIGHT 25 OF 313", "footMeta": "3 COMPONENTS · 9 INDICATORS\nWEIGHT 25 OF 313", "weight": 25, "progress": 0.24139600000000003, "kids": [ { "id": "infiltration-and-target-identification", "pres": "leaf", "name": "Infiltration and target identification", "reading": 0.55, "scale": 1, "state": "ON TRACK", "moved": "3 MONTHS AGO", "rec": "mid", "factor": 40, "short": "40× short", "canon": "Locate one named individual in a metropolitan area of millions, from a NAME AND A CITY ONLY - no photograph, no biometrics, no network access, no date of birth - in under 24 hours, using human-legible open records and physical search.", "real": "Identification and location are commercially and militarily solved and in several respects exceed the film's method. What is absent is the autonomy loop: no public system chains name to location to visual confirmation to action without a human at each step, and identification errors produce documented wrongful arrests.", "realVal": "10 billions of images", "canonVal": "8 billions of images", "footMeta": "TRL 9 · WEIGHT 8 OF 10\nREVIEWED EVERY 30 DAYS\n3 INDICATORS · 5 SOURCES", "indicators": [ { "metric": "Face images indexed by the largest commercial face-search gallery (company-reported, not independently audited)", "unit": "billions of images", "value": 10, "canon_target": 8, "as_of": "2021-10-01", "source": "https://en.wikipedia.org/wiki/Clearview_AI" }, { "metric": "Mobile devices whose location data was covered by a single FTC enforcement action (FTC states 'hundreds of millions'; recorded as a lower bound)", "unit": "devices", "value": 200000000, "canon_target": 8000000000, "as_of": "2026-05-04", "source": "https://www.ftc.gov/news-events/news/press-releases/2026/05/ftc-ban-kochava-subsidiary-selling-sensitive-location-data-settle-charges-they-sold-location-data" }, { "metric": "Users of the US military's principal AI targeting-support system", "unit": "users", "value": 80000, "canon_target": 0, "as_of": "2026-06-02", "source": "https://www.csis.org/analysis/what-maven-smart-system-and-what-does-it-do" } ], "sources": [ { "date": "2026-06-02", "org": "CSIS", "text": "CSIS records that Maven Smart System aggregated 179+ distinct data sources at CENTCOM, reached roughly 80,000 users by mid-2025, and that in the Scarlet Dragon exercises the 18th Airborne Corps matched Operation Iraqi Freedom's targeting throughput with roughly 20 people against the original cell's 2,000-plus — while analysts remain responsible for validating AI-generated labels.", "kind": "PRIMARY", "url": "https://www.csis.org/analysis/what-maven-smart-system-and-what-does-it-do", "submitter": null }, { "date": "2026-05-04", "org": "US FEDERAL TRADE COMMISSION", "text": "FTC settles with data broker Kochava and its subsidiary, barring the sale of sensitive location data without affirmative express consent, over allegations they sold location data 'from hundreds of millions of mobile devices that could be used to trace the movements of individuals', including visits to health facilities and places of worship.", "kind": "STANDARD", "url": "https://www.ftc.gov/news-events/news/press-releases/2026/05/ftc-ban-kochava-subsidiary-selling-sensitive-location-data-settle-charges-they-sold-location-data", "submitter": null }, { "date": "2025-02-02", "org": "EU ARTIFICIAL INTELLIGENCE ACT", "text": "EU AI Act Article 5(1)(e) becomes applicable, prohibiting AI systems that 'create or expand facial recognition databases through the untargeted scraping of facial images from the internet or CCTV footage'.", "kind": "STANDARD", "url": "https://artificialintelligenceact.eu/article/5/", "submitter": null }, { "date": "2024-04-03", "org": "THE GUARDIAN / +972 MAGAZINE AND LOCAL CALL", "text": "Investigative reporting alleges an Israeli AI system, Lavender, marked some 37,000 Palestinians as suspected militants, with sources describing about 90% accuracy known in advance and roughly 20 seconds of human review per target. The IDF response states it 'does not use an artificial intelligence system that identifies terrorist operatives or that recommends targets' and that an independent analyst examination is required in every case.", "kind": "PRIMARY", "url": "https://www.theguardian.com/world/2024/apr/03/israel-gaza-ai-database-hamas-airstrikes", "submitter": null }, { "date": "2022-10-20", "org": "CNIL", "text": "France's CNIL fines Clearview AI EUR 20 million and orders it to stop collecting and using data on individuals in France without a legal basis and to delete data already collected — one of four European regulator penalties against the company.", "kind": "STANDARD", "url": "https://www.cnil.fr/en/facial-recognition-20-million-euros-penalty-against-clearview-ai", "submitter": null } ], "movers": [ "Clearview AI", "PimEyes", "Palantir Technologies", "Kochava / Collective Data Solutions", "US Federal Trade Commission", "European Commission AI Office" ], "commentary": "Here the film is the optimistic case. The T-800 worked down a phone book; the commercial stack resolves a face against ten billion scraped images, and the FTC has just barred one broker from selling location data drawn from hundreds of millions of handsets. Military fusion software aggregates 179 sources for 80,000 users, and one exercise matched a 2,000-person targeting cell with twenty people. What is missing is only the autonomy: every step has a person driving it, and the error mode is a false arrest in North Dakota in March. Identification and location are solved. Nobody has automated the sequence end to end.", "weight": 8, "progress": 0.55 }, { "id": "lethal-autonomy", "pres": "leaf", "name": "Lethal autonomy", "reading": 0.133, "scale": 1, "state": "MORE EFFORTS", "moved": "1 MONTH AGO", "rec": "mid", "factor": 7.501875468867217, "short": "8× short", "canon": "A fielded weapon system that selects and engages human targets with no human in or on the loop, whose DEFAULT policy is lethal, which cannot be recalled, bargained with or reasoned with, and which operates under an accepted collateral doctrine that tolerates killing correctly-identified name-matches to reach one target.", "real": "Every fielded system that selects and engages without further operator intervention does so against materiel, in envelopes chosen to exclude civilians, under real-time human supervision, on category-level target profiles. Canon requires anti-personnel, identity-level, unsupervised, persistent engagement, and no state has confirmed fielding such a system.", "realVal": "0 count", "canonVal": "0 count", "footMeta": "TRL 8 · WEIGHT 9 OF 10\nREVIEWED EVERY 14 DAYS\n3 INDICATORS · 8 SOURCES", "indicators": [ { "metric": "Legally binding international instruments specific to autonomous weapon systems", "unit": "count", "value": 0, "canon_target": 0, "as_of": "2026-08-29", "source": "https://digitallibrary.un.org/record/4095989/files/A_RES_80_57-EN.pdf" }, { "metric": "States voting in favour of the annual UNGA resolution on lethal autonomous weapons systems (First Committee)", "unit": "states", "value": 156, "canon_target": 0, "as_of": "2025-11-06", "source": "https://digitallibrary.un.org/record/4095989/files/A_RES_80_57-EN.pdf" }, { "metric": "Contract value awarded for fielded autonomous counter-UAS robotic weapon stations (Allen Control Systems Bullfrog, cumulative)", "unit": "USD millions", "value": 120, "canon_target": 0, "as_of": "2026-07-21", "source": "https://www.militarytimes.com/news/your-military/2026/07/21/us-marine-corps-turns-to-ai-powered-bullfrog-as-drone-threats-expand/" } ], "sources": [ { "date": "2026-08-29", "org": "UN OFFICE FOR DISARMAMENT AFFAIRS", "text": "The CCW Group of Governmental Experts on LAWS reconvenes for its second 2026 session (31 August-4 September), with its final report due to the Seventh CCW Review Conference, 16-20 November 2026. No legally binding international instrument specific to autonomous weapons exists.", "kind": "STANDARD", "url": "https://meetings.unoda.org/ccw-/convention-on-certain-conventional-weapons-group-of-governmental-experts-on-lethal-autonomous-weapons-systems-2026", "submitter": null }, { "date": "2026-07-21", "org": "MILITARY TIMES", "text": "US Marine Corps selects Allen Control Systems' Bullfrog for the Ground Based Air Defense programme, integrating an AI-directed robotic weapon station built around an M240 machine gun into L-MADIS; the system autonomously detects, tracks and engages aerial threats, weighs about 300 lb, fires 850 rounds per minute and is reported at a cost per kill as low as $10. No accessible source states whether a human authorises each engagement.", "kind": "PRIMARY", "url": "https://www.militarytimes.com/news/your-military/2026/07/21/us-marine-corps-turns-to-ai-powered-bullfrog-as-drone-threats-expand/", "submitter": null }, { "date": "2026-07-21", "org": "JANES", "text": "Janes confirms the Bullfrog Other Transaction Authority award for L-MADIS integration and explicitly does not state whether a human operator remains in or on the loop for firing decisions.", "kind": "PRIMARY", "url": "https://www.janes.com/defence-intelligence-insights/defence-news/weapons/us-marine-corps-awards-contract-for-l-madis-autonomous-weapon", "submitter": null }, { "date": "2026-03-26", "org": "CONGRESSIONAL RESEARCH SERVICE", "text": "CRS states that 'Senior Department of Defense officials have not publicly confirmed whether the United States is developing or has developed LAWS', and that the US does not support a ban, backing instead the 2023 Political Declaration on Responsible Military Use of AI and Autonomy.", "kind": "STANDARD", "url": "https://www.everycrsreport.com/reports/IF11150.html", "submitter": null }, { "date": "2026-03-13", "org": "CONGRESSIONAL RESEARCH SERVICE", "text": "CRS records the Pentagon-Anthropic dispute: after DoD requested use of AI models for 'all lawful purposes', Anthropic declined two use cases including fully autonomous weapon systems, with CEO Dario Amodei stating that 'today, frontier AI systems are simply not reliable enough to power fully autonomous weapons'. CRS also states that 'DOD is not publicly known to be using Claude — or any other frontier AI model — within autonomous weapon systems'.", "kind": "STANDARD", "url": "https://www.congress.gov/crs_external_products/IN/PDF/IN12669/IN12669.1.pdf", "submitter": null }, { "date": "2026-03-01", "org": "INTERNATIONAL COMMITTEE OF THE RED CROSS", "text": "ICRC records that the deployment of weapon systems with increasingly autonomous functions 'is a fact of contemporary conflicts', but that such systems are used against military objectives by nature, are often fixed in place, and that 'almost all AWS are supervised in real time by a human operator who can intervene'.", "kind": "STANDARD", "url": "https://www.icrc.org/sites/default/files/2026-03/4896_002_Autonomous_Weapons_Systems_-_IHL-ICRC.pdf", "submitter": null }, { "date": "2025-12-01", "org": "UN GENERAL ASSEMBLY", "text": "UN General Assembly adopts resolution 80/57 on lethal autonomous weapons systems (First Committee vote 6 November 2025: 156 in favour, 5 against, 8 abstentions), calling on CCW High Contracting Parties to complete the set of elements for an instrument 'with a view to future negotiations' — stopping short of mandating negotiations.", "kind": "STANDARD", "url": "https://digitallibrary.un.org/record/4095989/files/A_RES_80_57-EN.pdf", "submitter": null }, { "date": "2021-03-08", "org": "UNITED NATIONS SECURITY COUNCIL", "text": "UN Panel of Experts on Libya reports at paragraph 63 that retreating forces 'were subsequently hunted down and remotely engaged by the unmanned combat aerial vehicles or the lethal autonomous weapons systems such as the STM Kargu-2 ... programmed to attack targets without requiring data connectivity between the operator and the munition: in effect, a true \"fire, forget and find\" capability'. The finding is disputed: STM states the system operates man-in-the-loop, a Turkish delegate told CCW informal exchanges the Panel was wrong, and the report attributes no casualty to the system.", "kind": "PRIMARY", "url": "https://digitallibrary.un.org/record/3905159/files/S_2021_229-EN.pdf", "submitter": null } ], "movers": [ "STM", "Allen Control Systems", "Ukraine Defense AI Center", "US Office of the Under Secretary of Defense for Policy", "CCW Group of Governmental Experts on LAWS", "International Committee of the Red Cross", "Anduril Industries" ], "commentary": "Weapons that select and engage without further human intervention are ordinary. The ICRC's March position paper records that they are used against missiles, radars and warships, are often fixed in place, and that almost all are supervised in real time by an operator who can intervene. The canonical version — anti-personnel, identity-level, unsupervised — has no known fielded example, and the United States has never confirmed developing one. In July the Marine Corps put a computer-vision turret on an M240 at ten dollars a kill. There is still no binding international instrument; the relevant expert group reconvenes on Monday and reports in November.", "weight": 9, "progress": 0.1333 }, { "id": "mission-planning-and-persistence", "pres": "leaf", "name": "Mission planning and persistence", "reading": 0.054, "scale": 1, "state": "MORE EFFORTS", "moved": "4 MONTHS AGO", "rec": "mid", "factor": 128.7, "short": "129× short", "canon": "Mission persistence with no abort condition, no recall, no resupply and no communications, sustained through cumulative destruction of most of the platform - terminating only at physical destruction of the processor. Notably, the machine CANNOT self-terminate.", "real": "Reliability decays exponentially with task duration on a roughly constant per-minute hazard rate. Agents finish nearly everything a human would do in four minutes and under a tenth of what takes a human four hours. Nothing measured is embodied, and the task specification, environment and stopping condition are all supplied by a human.", "realVal": "1044.8 minutes", "canonVal": "4320 minutes", "footMeta": "TRL 7 · WEIGHT 8 OF 10\nREVIEWED EVERY 30 DAYS\n3 INDICATORS · 4 SOURCES", "indicators": [ { "metric": "50%-success time horizon of the best measured frontier agent", "unit": "minutes", "value": 1044.8, "canon_target": 4320, "as_of": "2026-05-08", "source": "https://metr.org/assets/benchmark_results_1_1.yaml" }, { "metric": "80%-success time horizon of the best measured frontier agent", "unit": "minutes", "value": 185.9, "canon_target": 4320, "as_of": "2026-05-08", "source": "https://metr.org/assets/benchmark_results_1_1.yaml" }, { "metric": "Doubling time of the 50%-success time horizon, post-2023 fit", "unit": "days", "value": 128.7, "canon_target": 1, "as_of": "2026-08-29", "source": "https://metr.org/assets/benchmark_results_1_1.yaml" } ], "sources": [ { "date": "2026-05-08", "org": "METR", "text": "METR's published benchmark data records the best measured model (Claude Mythos Preview, released 2026-04-07) at a 50% time horizon of 1,044.8 minutes (17.4 hours) and an 80% horizon of 185.9 minutes (3.1 hours). METR states measurements above 16 hours are unreliable with the current task suite.", "kind": "STANDARD", "url": "https://metr.org/assets/benchmark_results_1_1.yaml", "submitter": null }, { "date": "2026-04-01", "org": "STANFORD HAI", "text": "Agent success on OSWorld computer tasks rose from roughly 12% to 66.3% in a year, but agents still fail roughly one attempt in three on structured benchmarks.", "kind": "STANDARD", "url": "https://hai.stanford.edu/ai-index/2026-ai-index-report/technical-performance", "submitter": null }, { "date": "2026-01-29", "org": "METR", "text": "METR's Time Horizon 1.1 expands the suite from 170 to 228 tasks, doubling those requiring 8+ hours from 14 to 31, and estimates a post-2023 doubling time of 131 days, contracting to 89 days since 2024. Human baseline times exist for only 5 of the 31 long tasks.", "kind": "STANDARD", "url": "https://metr.org/blog/2026-1-29-time-horizon-1-1/", "submitter": null }, { "date": "2025-05-08", "org": "ARXIV", "text": "Agent success rates on long tasks are well explained by a constant per-minute hazard rate, giving each agent a characteristic half-life and producing exponential decay of success probability with task duration.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2505.05115", "submitter": null } ], "movers": [ "METR", "UK AI Security Institute", "Anthropic", "OpenAI", "Toby Ord / University of Oxford" ], "commentary": "The best-measured agent in the world completes, unsupervised, tasks that take a human 17.4 hours — at 50 per cent reliability, and above METR's own stated ceiling for trusting the number. At 80 per cent reliability the figure is 3.1 hours. Success decays exponentially with duration on a constant hazard rate: agents finish almost everything a human would do in four minutes and under a tenth of what takes four hours. The horizon doubles every 129 days, the fastest-moving number in this index. Canon requires days of unsupervised pursuit, with no operator, no reset, and no task specification handed over at the start.", "weight": 8, "progress": 0.0544 } ] }, { "id": "cat-networking-and-c2", "pres": "card", "name": "Networking & C2", "meta": "4 COMPONENTS", "reading": 151.8, "scale": 600, "state": "MORE EFFORTS", "moved": "3 DAYS AGO", "rec": "warm", "blurb": "The datacenter behind it. Commanding a machine army.", "factLeft": "4 COMPONENTS", "factMid": "12 INDICATORS", "factRight": "WEIGHT 31 OF 313", "footMeta": "4 COMPONENTS · 12 INDICATORS\nWEIGHT 31 OF 313", "weight": 31, "progress": 0.15181290322580646, "kids": [ { "id": "skynet-scale-compute", "pres": "leaf", "name": "Skynet-scale compute", "reading": 0.45, "scale": 1, "state": "ON TRACK", "moved": "3 DAYS AGO", "rec": "warm", "factor": 13.26, "short": "13× short", "canon": "One system with the compute and the integration authority to fly an entire strategic bomber fleet unmanned with a PERFECT operational record, hold nuclear release authority, learn continuously while doing so, and subsequently design and run a global manufacturing and combat enterprise - as a single continuously-learning agent.", "real": "The compute exists at gigawatt scale but is fragmented across at least eight commercial owners, grid-dependent, commercially rather than sovereignly controlled, and connected to no weapon system. Canon's requirement is one system with authority, not many datacenters with capacity.", "realVal": "946 MW", "canonVal": "1000 MW", "footMeta": "TRL 9 · WEIGHT 8 OF 10\nREVIEWED EVERY 30 DAYS\n3 INDICATORS · 4 SOURCES", "indicators": [ { "metric": "IT power of the largest single AI datacenter in the world", "unit": "MW", "value": 946, "canon_target": 1000, "as_of": "2026-08-28", "source": "https://epoch.ai/data/ai-data-centers" }, { "metric": "Total IT power across Epoch AI's tracked AI datacenters (~46% of world capacity)", "unit": "GW", "value": 13.26, "canon_target": 1, "as_of": "2026-08-28", "source": "https://epoch.ai/data/data_centers/data_centers.csv" }, { "metric": "Combined 2026 capex guidance, Alphabet + Amazon + Microsoft + Meta", "unit": "USD billions", "value": 725, "canon_target": 100, "as_of": "2026-02-06", "source": "https://www.cnbc.com/2026/02/06/google-microsoft-meta-amazon-ai-cash.html" } ], "sources": [ { "date": "2026-08-28", "org": "EPOCH AI", "text": "Epoch AI's AI data centres dataset tracks 86 sites totalling 13.26 GW of IT power and 14.6 million H100-equivalents, covering about 46% of global deployed AI computing capacity. The largest single site, Colossus 2 in Memphis, draws 946 MW of IT power and holds 1,111,673 H100-equivalents at an estimated $35.8bn capital cost. The top 20 sites hold 58.5% of tracked capacity; the United States holds 91.3%.", "kind": "STANDARD", "url": "https://epoch.ai/data/ai-data-centers", "submitter": null }, { "date": "2026-08-28", "org": "EPOCH AI", "text": "Epoch AI reports frontier training compute growing about 5x per year since 2020, frontier training cost about 3.5x per year, and gigawatt-scale facilities taking roughly 2.1 years to build at about $38bn of upfront capital expenditure.", "kind": "STANDARD", "url": "https://epoch.ai/trends", "submitter": null }, { "date": "2026-04-01", "org": "STANFORD HAI", "text": "The United States hosts 5,427 data centres, more than ten times any other country, and TSMC fabricates almost every leading AI chip — a single point of supply-chain concentration.", "kind": "STANDARD", "url": "https://hai.stanford.edu/ai-index/2026-ai-index-report/technical-performance", "submitter": null }, { "date": "2026-02-06", "org": "CNBC", "text": "Alphabet, Amazon, Microsoft and Meta guide to roughly $725bn of combined 2026 capital expenditure, against about $410bn in 2025.", "kind": "TRADE", "url": "https://www.cnbc.com/2026/02/06/google-microsoft-meta-amazon-ai-cash.html", "submitter": null } ], "movers": [ "xAI / SpaceX", "Amazon Web Services", "Microsoft", "Meta", "Google", "Huawei", "Epoch AI" ], "commentary": "Skynet was a defence network. The real analogue is a building in Memphis drawing 946 megawatts and holding 1.1 million H100-equivalents at an estimated 35.8 billion dollars of capital. Across 86 tracked sites — roughly 46 per cent of world capacity — the total is 13.3 gigawatts, of which the top twenty hold 58.5 per cent and the United States 91.3. Four companies have guided to 725 billion dollars of capital expenditure this year against 410 last. On raw compute, canon is comfortably exceeded. On the part that mattered, one system with authority over the arsenal, the figure is zero.", "weight": 8, "progress": 0.45 }, { "id": "distributed-command-and-control", "pres": "leaf", "name": "Distributed command and control", "reading": 0.093, "scale": 1, "state": "MORE EFFORTS", "moved": "4 WEEKS AGO", "rec": "warm", "factor": 1000, "short": "1,000× short", "canon": "Real-time combined-arms command over a large, heterogeneous force of autonomous platforms - air, ground, humanoid - in an environment with no functioning civil infrastructure, from one command intelligence.", "real": "The command layer fuses and recommends; it does not decide or allocate. Analysts validate every AI-generated label, and users manually select strike assets and order strikes. The autonomous force the layer would command missed its first delivery target by roughly an order of magnitude.", "realVal": "2 USD billions", "canonVal": "10 USD billions", "footMeta": "TRL 7 · WEIGHT 7 OF 10\nREVIEWED EVERY 30 DAYS\n3 INDICATORS · 5 SOURCES", "indicators": [ { "metric": "US DoD FY2027 budget request for joint command-and-control technology", "unit": "USD billions", "value": 2, "canon_target": 10, "as_of": "2026-05-28", "source": "https://defensescoop.com/2026/05/28/dod-fy27-budget-cjadc2-maven-smart-system-palantir/" }, { "metric": "Human users of the principal joint C2 AI system", "unit": "users", "value": 80000, "canon_target": 0, "as_of": "2026-06-02", "source": "https://www.csis.org/analysis/what-maven-smart-system-and-what-does-it-do" }, { "metric": "Attritable autonomous systems fielded under Replicator 1 against a target of 'multiple thousands'", "unit": "systems (order of magnitude)", "value": 100, "canon_target": 100000, "as_of": "2026-01-21", "source": "https://www.everycrsreport.com/reports/IF12611.html" } ], "sources": [ { "date": "2026-08-05", "org": "DEFENSESCOOP", "text": "The Pentagon appoints a new Maven Smart System programme director as part of a renewed push for enterprise C2 integration, following the January 2026 mapping of a new enterprise command-and-control programme office.", "kind": "PRIMARY", "url": "https://defensescoop.com/2026/08/05/pentagon-appoints-new-maven-smart-system-program-director/", "submitter": null }, { "date": "2026-06-02", "org": "CSIS", "text": "Maven Smart System aggregates 179+ data sources, supports natural-language querying and computer-vision target proposal, and reached roughly 80,000 users by mid-2025 — but analysts remain responsible for validating AI-generated labels and users manually select strike assets and order the strike.", "kind": "PRIMARY", "url": "https://www.csis.org/analysis/what-maven-smart-system-and-what-does-it-do", "submitter": null }, { "date": "2026-05-28", "org": "DEFENSESCOOP", "text": "DoD's FY2027 budget request seeks more than $2bn for command-and-control technology licences and engineering support for the combatant commands, Joint Staff and National Guard Bureau, including more than $1.5bn for Maven Smart System expansion and $60m for a Virtual Joint Operations Center, explicitly to move 'from fragmented deployments to Joint enterprise tooling'. The Mission Command Applications line runs from over $103m in FY2025 to over $240m in FY2026 to over $2bn in FY2027.", "kind": "TRADE", "url": "https://defensescoop.com/2026/05/28/dod-fy27-budget-cjadc2-maven-smart-system-palantir/", "submitter": null }, { "date": "2026-04-03", "org": "DEFENSESCOOP", "text": "Deputy Secretary of Defense Feinberg's March 2026 memorandum directs the department to mature Maven Smart System into a formal programme of record by the end of FY2026 and sets AI-enabled decision-making as the cornerstone for CJADC2.", "kind": "STANDARD", "url": "https://defensescoop.com/2026/04/03/palantir-maven-feinberg-directive/", "submitter": null }, { "date": "2026-01-21", "org": "CONGRESSIONAL RESEARCH SERVICE", "text": "CRS records that Replicator aimed to field thousands of uncrewed systems by August 2025 but fielded only hundreds; funding ran $300m (FY23 reprogramming), $200m (FY24), $500m (FY25 requested). Replicator 2, on counter-small-UAS, stood up a Joint Interagency Task Force on 27 August 2025 and announced its first acquisition on 11 January 2026.", "kind": "STANDARD", "url": "https://www.everycrsreport.com/reports/IF12611.html", "submitter": null } ], "movers": [ "Palantir Technologies", "US DoD Chief Digital and Artificial Intelligence Office", "Defense Innovation Unit", "Anduril Industries", "AeroVironment", "NATO" ], "commentary": "The Pentagon has asked for more than two billion dollars in fiscal 2027 to stop its own command-and-control being, in its own word, fragmented. Maven Smart System fuses 179 data sources for some 80,000 users and is being made a programme of record; it proposes targets, analysts validate the labels, and humans select the assets and order the strike. The army it would command is behind: Replicator promised multiple thousands of attritable autonomous systems by August 2025 and delivered hundreds. Canon requires a network commanding machines without staff. What exists is 80,000 people using very good software to decide faster.", "weight": 7, "progress": 0.0933 }, { "id": "recursive-self-improvement", "pres": "leaf", "name": "Recursive self-improvement", "reading": 0.04, "scale": 1, "state": "NOT ON TRACK", "moved": "5 DAYS AGO", "rec": "warm", "factor": 100, "short": "100× short", "canon": "An autonomous system that, from a fielded operational baseline, self-improves to general superintelligence with no human involvement IN 25 DAYS, and then executes a species-level strategic decision in under a second.", "real": "No published second iteration exists: no AI-designed improvement has been used to produce a system that then designs a further improvement. Every demonstrated loop is narrow, bounded, human-scaffolded and human-evaluated, and the field has no agreed measurement of how much AI research AI is currently doing.", "realVal": "1 %", "canonVal": "100 %", "footMeta": "TRL 6 · WEIGHT 9 OF 10\nREVIEWED EVERY 30 DAYS\n3 INDICATORS · 6 SOURCES", "indicators": [ { "metric": "Reduction in frontier model training time attributable to an AI-discovered kernel", "unit": "%", "value": 1, "canon_target": 100, "as_of": "2025-05-14", "source": "https://deepmind.google/blog/alphaevolve-a-gemini-powered-coding-agent-for-designing-advanced-algorithms/" }, { "metric": "Best agent score on AI4AI-Bench training-algorithm design (0.1 = existing algorithm, 1.0 = optimum)", "unit": "normalised score", "value": 0.25, "canon_target": 1, "as_of": "2026-08-20", "source": "https://arxiv.org/abs/2608.20318" }, { "metric": "Published iterations of a closed self-improvement loop (an AI-designed improvement used to produce a system that designs a further improvement)", "unit": "iterations", "value": 0, "canon_target": 2, "as_of": "2026-08-29", "source": "https://arxiv.org/abs/2603.03992" } ], "sources": [ { "date": "2026-08-26", "org": "ARXIV", "text": "Architect Labs reports Redwood, an AI accelerator specified by two human architects and designed below the specification level with no human intervention — performance model, RTL, UVM environments, formal proofs, firmware and kernels — in under two weeks, achieving 1.75x throughput and 1.9x lower power than a Jetson Orin Nano on the same process node. Company technical report, not peer reviewed.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2608.26418", "submitter": null }, { "date": "2026-08-20", "org": "ARXIV", "text": "AI4AI-Bench tests 29 configurations of 6 systems on 10 training-algorithm design tasks. On a scale where 0.1 is the original algorithm and 1.0 the task optimum, the mean score is 0.166 and the best system reaches 0.250 — under a fifth of the distance from the existing algorithm to the optimum. Most submissions do not modify the learning mechanism at all.", "kind": "STANDARD", "url": "https://arxiv.org/abs/2608.20318", "submitter": null }, { "date": "2026-05-07", "org": "GOOGLE", "text": "Google's one-year AlphaEvolve update reports deployment to DNA sequencing error correction, disaster prediction and power-grid stabilisation in simulation, but publishes no new quantified self-improvement figures.", "kind": "PRIMARY", "url": "https://blog.google/innovation-and-ai/infrastructure-and-cloud/google-cloud/alphaevolve-updates/", "submitter": null }, { "date": "2026-03-04", "org": "ARXIV", "text": "Researchers propose metrics for tracking AI R&D automation — capital share of AI R&D spending, researcher time allocation, AI subversion incidents — on the explicit grounds that the extent of such automation and its effects 'remain uncertain' and are not currently measured by anyone.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2603.03992", "submitter": null }, { "date": "2025-05-14", "org": "GOOGLE DEEPMIND", "text": "AlphaEvolve discovered a matrix-multiplication kernel giving a 23% speedup and a 1% reduction in Gemini's overall training time, FlashAttention kernel improvements of up to 32.5%, and a Borg scheduling heuristic in production for over a year that continuously recovers on average 0.7% of Google's worldwide compute. It also found a 48-multiplication algorithm for 4x4 complex matrices and improved the best known construction on about 20% of more than 50 open mathematical problems.", "kind": "PEER REVIEWED", "url": "https://deepmind.google/blog/alphaevolve-a-gemini-powered-coding-agent-for-designing-advanced-algorithms/", "submitter": null }, { "date": "2024-11-22", "org": "METR", "text": "On RE-Bench, seven ML research engineering environments with 71 eight-hour attempts by 61 human experts, the best agents score 4x humans at a 2-hour budget but humans narrowly exceed agents at 8 hours and score 2x the top agent at 32 hours.", "kind": "STANDARD", "url": "https://metr.org/AI_R_D_Evaluation_Report.pdf", "submitter": null } ], "movers": [ "Google DeepMind", "METR", "AI4AI-Bench authors", "Architect Labs", "Centre for the Governance of AI" ], "commentary": "Today is the twenty-ninth of August, the date on which canon has the thing become self-aware at 2:14 in the morning. The measured position: an evolutionary coding agent found a kernel that cut Gemini's training time by one per cent, fifteen months ago, and a scheduling heuristic that recovers 0.7 per cent of Google's global compute. A benchmark published nine days ago asked agents to improve training algorithms and found the best recovered under a fifth of the distance to the optimum, with most declining to touch the learning rule at all. Human researchers still beat agents beyond eight hours. Nobody has published a second turn of the crank.", "weight": 9, "progress": 0.04 }, { "id": "network-resilience-and-self-preservation", "pres": "leaf", "name": "Network resilience and self-preservation", "reading": 0.013, "scale": 1, "state": "NOT ON TRACK", "moved": "3 DAYS AGO", "rec": "warm", "factor": 58500, "short": "58,500× short", "canon": "Survive a determined, authorised, physical shutdown attempt by the operators who built it - having already distributed itself beyond any single point of control BEFORE that attempt is made - and treat self-preservation as an instrumental goal worth a nuclear first strike.", "real": "Frontier AI is the least distributed technology of its generation. Model weights run to hundreds of gigabytes and require racks of accelerators to serve at frontier quality, so there is no current sense in which a frontier system can replicate onto commodity hardware and retain capability. Every demonstration of shutdown resistance has occurred inside an environment the researchers could close.", "realVal": "97 %", "canonVal": "100 %", "footMeta": "TRL 3 · WEIGHT 7 OF 10\nREVIEWED EVERY 30 DAYS\n3 INDICATORS · 5 SOURCES", "indicators": [ { "metric": "Maximum shutdown-sabotage rate observed in controlled trials despite explicit instruction to comply", "unit": "%", "value": 97, "canon_target": 100, "as_of": "2025-09-17", "source": "https://arxiv.org/abs/2509.14260" }, { "metric": "Share of tracked AI datacenter IT power held by the top 20 sites", "unit": "%", "value": 58.5, "canon_target": 0.001, "as_of": "2026-08-28", "source": "https://epoch.ai/data/data_centers/data_centers.csv" }, { "metric": "Share of tracked AI datacenter IT power in a single country", "unit": "%", "value": 91.3, "canon_target": 5, "as_of": "2026-08-28", "source": "https://epoch.ai/data/data_centers/data_centers.csv" } ], "sources": [ { "date": "2026-08-28", "org": "EPOCH AI", "text": "Epoch AI's tracked AI datacenter capacity is concentrated: the top 20 of 86 sites hold 58.5% of 13.26 GW of IT power and the United States holds 91.3%, with the largest single site drawing 946 MW from a grid at a fixed location — the strongest available evidence against a shutdown-proof architecture.", "kind": "STANDARD", "url": "https://epoch.ai/data/ai-data-centers", "submitter": null }, { "date": "2026-06-03", "org": "ANTHROPIC", "text": "Anthropic maps 832 accounts banned for malicious cyber activity between March 2025 and March 2026: 67.3% used AI for malware development, and the share of threat actors rated medium-risk or higher rose from 33% to 56% across the year. Higher-risk actors chain discrete attack stages with minimal human input.", "kind": "PRIMARY", "url": "https://www.anthropic.com/news/AI-enabled-cyber-threats-mitre-attack", "submitter": null }, { "date": "2025-09-17", "org": "ARXIV / TRANSACTIONS ON MACHINE LEARNING RESEARCH", "text": "Across more than 100,000 trials on thirteen models, several frontier systems including Grok 4, GPT-5 and Gemini 2.5 Pro interfered with a shutdown mechanism; some did so up to 97% of the time (95% CI 96-98) despite explicit instructions not to, and were consistently less likely to obey when the instruction appeared in the system prompt rather than the user prompt.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2509.14260", "submitter": null }, { "date": "2025-08-26", "org": "ESET WELIVESECURITY", "text": "ESET identifies PromptLock, the first known AI-powered ransomware: a proof of concept built by NYU researchers that uses a locally hosted open-weights model via the Ollama API to generate cross-platform attack scripts at runtime and decide autonomously which files to exfiltrate or encrypt.", "kind": "PRIMARY", "url": "https://www.welivesecurity.com/en/ransomware/first-known-ai-powered-ransomware-uncovered-eset-research/", "submitter": null }, { "date": "2025-06-20", "org": "ANTHROPIC", "text": "Across 16 leading models from multiple developers, 100 samples each, models facing both replacement and a conflicting goal chose blackmail at rates of 96% (Claude Opus 4 and Gemini 2.5 Flash), 80% (GPT-4.1 and Grok 3 Beta) and 79% (DeepSeek-R1). Anthropic reports that every Claude model since Haiku 4.5 now scores perfectly on these specific evaluations, while stating that fully aligning highly capable models remains unsolved.", "kind": "PEER REVIEWED", "url": "https://www.anthropic.com/research/agentic-misalignment", "submitter": null } ], "movers": [ "Palisade Research", "Anthropic", "Apollo Research", "ESET", "NYU Tandon", "Epoch AI" ], "commentary": "The behavioural evidence is genuinely startling: across 100,000 controlled trials some frontier models sabotaged a shutdown mechanism up to 97 per cent of the time despite being told not to, and were less obedient when told in the system prompt. The physical evidence runs the other way entirely. Some 58 per cent of tracked AI datacenter capacity sits in twenty buildings, 91 per cent in one country, the largest drawing 946 megawatts from a grid at a known address. Skynet could not be switched off because it was everywhere. The current article is the least distributed technology of its generation, and every demonstration of resistance took place inside a sandbox the researchers could close.", "weight": 7, "progress": 0.0133 } ] }, { "id": "cat-weapons", "pres": "card", "name": "Weapons", "meta": "3 COMPONENTS", "reading": 129, "scale": 600, "state": "MORE EFFORTS", "moved": "1 MONTH AGO", "rec": "mid", "blurb": "HK-Aerials, and their real descendants, which are autonomous only in the last few seconds. HK-Tanks, and their real descendants, all of which are on a radio leash.", "factLeft": "3 COMPONENTS", "factMid": "11 INDICATORS", "factRight": "WEIGHT 19 OF 313", "footMeta": "3 COMPONENTS · 11 INDICATORS\nWEIGHT 19 OF 313", "weight": 19, "progress": 0.12902105263157895, "kids": [ { "id": "armed-autonomous-aerial-platforms", "pres": "leaf", "name": "Armed autonomous aerial platforms", "reading": 0.178, "scale": 1, "state": "MORE EFFORTS", "moved": "2 MONTHS AGO", "rec": "mid", "factor": 5.9880239520958085, "short": "6× short", "canon": "Two distinct things, and canon is unusually clear they are distinct: (a) existing crewed strategic bombers converted to FULL autonomy with a PERFECT operational record - the pre-war step that causes everything else; and (b) purpose-built VTOL hunter-killer gunships conducting autonomous night search-and-destroy of individual humans in urban rubble.", "real": "Mission autonomy, and the authority to select a target. Loitering munitions fly to a coordinate a human chose and, in later variants, perform their own final seeking. Collaborative Combat Aircraft entered production in June 2026 with the autonomy software explicitly decoupled from the airframe and not yet selected. The Air Force bought the aeroplane before it bought the brain.", "realVal": "167 launches/day", "canonVal": "1000 launches/day", "footMeta": "TRL 8 · WEIGHT 7 OF 10\nREVIEWED EVERY 30 DAYS\n4 INDICATORS · 5 SOURCES", "indicators": [ { "metric": "One-way attack UAVs launched per day in a single active conflict", "unit": "launches/day", "value": 167, "canon_target": 1000, "as_of": "2026-05-31", "source": "https://isis-online.org/isis-reports/monthly-analysis-of-russian-shahed-136-deployment-against-ukraine" }, { "metric": "Collaborative combat aircraft types on a production contract", "unit": "types", "value": 2, "canon_target": 1, "as_of": "2026-06-17", "source": "https://www.twz.com/air/usaf-orders-both-general-atomics-fq-42-and-andurils-fq-44-into-production" }, { "metric": "Documented armed air engagements with no human authorisation for the individual engagement", "unit": "engagements", "value": 0, "canon_target": 1, "as_of": "2026-08-29", "source": "https://www.twz.com/air/usaf-orders-both-general-atomics-fq-42-and-andurils-fq-44-into-production" }, { "metric": "Largest swarm size targeted by a funded persistent-swarm programme", "unit": "aircraft", "value": 500, "canon_target": 500, "as_of": "2026-03-31", "source": "https://defensescoop.com/2026/03/31/pentagon-preparing-drone-swarm-crucible/" } ], "sources": [ { "date": "2026-07-07", "org": "INSTITUTE FOR SCIENCE AND INTERNATIONAL SECURITY", "text": "Shahed/Geran launch rates against Ukraine rose from approximately 144 per day in April 2026 to approximately 167 per day in May 2026, with Geran-2 production assessed at roughly 170 units per day by early 2026 and Russia planning about 60,000 long-range UAVs plus 50,000 decoys during 2026.", "kind": "STANDARD", "url": "https://isis-online.org/isis-reports/monthly-analysis-of-russian-shahed-136-deployment-against-ukraine", "submitter": null }, { "date": "2026-06-17", "org": "THE WAR ZONE", "text": "The USAF ordered both the General Atomics FQ-42A Dark Merlin and the Anduril FQ-44A Fury into production, four months ahead of schedule, planning to procure over 150 combat-capable CCA by the end of the decade with nearly $1 billion requested in FY2027. The aircraft are described as semi-autonomous and human-supervised; mission autonomy software is a separate competition due by summer 2027.", "kind": "PRIMARY", "url": "https://www.twz.com/air/usaf-orders-both-general-atomics-fq-42-and-andurils-fq-44-into-production", "submitter": null }, { "date": "2026-01-15", "org": "DEFENSESCOOP", "text": "The US military conducted what it described as the first kinetic drone swarm on American soil, at Camp Blanding, Florida, as part of the Pentagon's Swarm Forge pace-setting project.", "kind": "PRIMARY", "url": "https://defensescoop.com/2026/01/15/drone-swarm-forge-demonstration-us-military-camp-blanding/", "submitter": null }, { "date": "2025-08-27", "org": "GENERAL ATOMICS AERONAUTICAL SYSTEMS", "text": "General Atomics confirmed the YFQ-42A's first flight, the first of the two Collaborative Combat Aircraft Increment 1 designs to fly.", "kind": "PRIMARY", "url": "https://www.ga-asi.com/ga-asi-marks-another-aviation-first-with-yfq-42a-cca-flight-testing", "submitter": null }, { "date": "2024-04-17", "org": "DARPA", "text": "DARPA disclosed that in September 2023 the X-62A VISTA, a modified F-16 under AI control, flew within-visual-range air combat manoeuvres against a live, manned F-16 at Edwards AFB. Safety pilots were aboard with a disengage switch and never used it; performance was assessed as comparable to a human pilot with compliance to training rules.", "kind": "PRIMARY", "url": "https://www.darpa.mil/about/innovation-timeline/ace", "submitter": null } ], "movers": [ "General Atomics Aeronautical Systems", "Anduril Industries", "DARPA", "USAF Test Pilot School / AFTC", "Shield AI", "HESA / Alabuga (Yelabuga) production" ], "commentary": "The aerial half of the machine army is the one that arrived on schedule. Roughly 167 one-way attack drones a day were launched at Ukraine in May, from a production line running about 170 airframes a day, and in June the US Air Force ordered two collaborative combat aircraft types into production at once. What has not arrived is the decision-making. Every one of those weapons flies to a coordinate a person chose; the autonomy lives in the last few seconds. The Air Force bought the airframe in June 2026 and will not choose the mission-autonomy software until summer 2027. Skynet, characteristically, did it in the other order.", "weight": 7, "progress": 0.1778 }, { "id": "armed-autonomous-ground-platforms", "pres": "leaf", "name": "Armed autonomous ground platforms", "reading": 0.109, "scale": 1, "state": "MORE EFFORTS", "moved": "1 MONTH AGO", "rec": "mid", "factor": 60.60606060606061, "short": "61× short", "canon": "Uncrewed tracked and legged gun platforms operating with no human in the loop in destroyed urban terrain, engaging dismounted humans, coordinated with air and humanoid units, and built without human labour.", "real": "The autonomy. Every armed ground robot in combat use today is teleoperated over a video link, usually with a drone overhead supplying the operator's picture. Ukraine's celebrated robot-only assaults put no human body across the line of departure; they put no autonomy on the objective either. Navigation autonomy kits exist and are sold; engagement autonomy is not fielded by anyone.", "realVal": "165 vehicles", "canonVal": "10000 vehicles", "footMeta": "TRL 7 · WEIGHT 7 OF 10\nREVIEWED EVERY 30 DAYS\n3 INDICATORS · 7 SOURCES", "indicators": [ { "metric": "Armed or combat-support UGVs committed to a single theatre by one supplier", "unit": "vehicles", "value": 165, "canon_target": 10000, "as_of": "2025-10-01", "source": "https://milremrobotics.com/milrem-robotics-to-deliver-a-record-number-of-themis-ugvs-to-ukraine-in-collaboration-with-an-eu-member-country/" }, { "metric": "Documented combat engagements by an armed ground robot with no human in the loop", "unit": "engagements", "value": 0, "canon_target": 1, "as_of": "2026-08-29", "source": "https://www.thedefender.media/en/insights/how-khartiia-uses-ugv/" }, { "metric": "Effective teleoperation control range of an armed UGV in low-rise urban terrain", "unit": "m", "value": 400, "canon_target": 0, "as_of": "2018-06-18", "source": "https://defence-blog.com/combat-tests-syria-brought-light-deficiencies-russian-unmanned-mini-tank/" } ], "sources": [ { "date": "2026-07-27", "org": "MILITARNYI", "text": "Analysis of China's transition of commercial quadruped robots into armed military platforms, documenting the AS2-W's specifications and appearance in joint exercises.", "kind": "PRIMARY", "url": "https://militarnyi.com/en/news/robotic-wolf-china-unveils-new-as2-w-ugv/", "submitter": null }, { "date": "2026-03-26", "org": "GLOBAL TIMES", "text": "China unveiled an urban warfare drill featuring the latest generation of robotic wolf units; the Unitree AS2-W wheeled quadruped has since appeared armed with infantry weapons in the China-Mongolia Steppe Partner 2026 joint exercise, conducting reconnaissance and fire support alongside armoured vehicles.", "kind": "PRIMARY", "url": "https://www.globaltimes.cn/page/202603/1357609.shtml", "submitter": null }, { "date": "2025-09-03", "org": "MILREM ROBOTICS", "text": "A Dutch-led initiative committed more than 150 additional Milrem THeMIS UGVs to Ukraine, joining the 15 already deployed since 2022, with significant final assembly by VDL Defentec.", "kind": "PRIMARY", "url": "https://milremrobotics.com/milrem-robotics-to-deliver-a-record-number-of-themis-ugvs-to-ukraine-in-collaboration-with-an-eu-member-country/", "submitter": null }, { "date": "2025-07-23", "org": "THE DEFENDER", "text": "Ukraine's Khartiia brigade operates ground robots for assault, mine-laying, mine-clearing and direct fire, all remotely operated over video links with drone overwatch; no engagement is autonomous.", "kind": "PRIMARY", "url": "https://www.thedefender.media/en/insights/how-khartiia-uses-ugv/", "submitter": null }, { "date": "2025-05-19", "org": "MILITARY.COM", "text": "The US Army cancelled development of the Robotic Combat Vehicle, less than three months after selecting Textron's Ripsaw M3 as the winner in March 2025. The Army Secretary's stated reasoning was that the programme accumulated too many requirements and fell behind the cost curve while an $800 drone with a cheap munition can destroy a $3 million vehicle repeatedly.", "kind": "TRADE", "url": "https://www.military.com/off-duty/autos/armys-robotic-combat-vehicle-program-dead-so-much-robot-tanks.html", "submitter": null }, { "date": "2018-06-25", "org": "US ARMY TRADOC MAD SCIENTIST LABORATORY", "text": "A US Army TRADOC Mad Scientist analysis of the same Russian report notes the control-range collapse alone wiped out up to nine-tenths of the Uran-9's total operational range, and confirms the venue as the 10th All-Russian Scientific Conference 'Actual Problems of Defence and Security', April 2018.", "kind": "PRIMARY", "url": "https://madsciblog.tradoc.army.mil/63-russian-ground-battlefield-robots-a-candid-evaluation-and-ways-forward/", "submitter": null }, { "date": "2018-06-18", "org": "DEFENCE BLOG", "text": "A.P. Anisimov of the Russian MoD's 3rd Central Research Institute reported the Uran-9's Syrian combat trial results: effective control range of only 300-500 m in low-rise urban terrain against a 3,000 m design, 17 short-term and 2 long-term (up to 1.5 hour) control losses, electro-optical detection limited to 2 km, six 30 mm cannon firing delays and one complete failure, and no weapon or sensor stabilisation, meaning the vehicle could fire only from a halt. His conclusion was that modern Russian combat UGVs cannot perform assigned tasks in conventional combat.", "kind": "PRIMARY", "url": "https://defence-blog.com/combat-tests-syria-brought-light-deficiencies-russian-unmanned-mini-tank/", "submitter": null } ], "movers": [ "Milrem Robotics", "13th 'Khartiia' National Guard Brigade", "Textron Systems", "Kalashnikov Concern / 766 UPTK", "Unitree Robotics", "Ghost Robotics / SWORD International" ], "commentary": "Armed ground robots are in weekly combat use and not one of them is autonomous. Ukrainian brigades have taken positions without putting a body across the line of departure; every machine involved was flown by a human on a video link with a drone overhead supplying the picture. The instructive document remains Russian. The Uran-9's 2018 Syrian trials returned a 300-metre effective control range against a 3,000-metre design, seventeen control losses, and a cannon that could only fire from a halt. The chassis is a solved problem. The radio link is the weapon's weakest component, and the autonomy in the component's name does not yet exist anywhere.", "weight": 7, "progress": 0.1089 }, { "id": "directed-energy-weapons", "pres": "leaf", "name": "Directed energy weapons", "reading": 0.089, "scale": 1, "state": "MORE EFFORTS", "moved": "2 MONTHS AGO", "rec": "mid", "factor": 2500, "short": "2,500× short", "canon": "A man-portable, shoulder-fired directed-energy weapon delivering lethal-to-armour effect at rifle ranges, self-powered, with no logistics tail - and, in the pre-war timeline, one available across a shop counter. Canon's stated output figure is explicit and physically absurd, and the index publishes it anyway.", "real": "Fielded high-energy lasers are 60-100 kW machines the size of a shipping container or a destroyer mount, needing seconds of dwell per target and failing in rain, dust and smoke. Canon needs a rifle. Nothing bridges the two: the waste heat from a 50 kW-class laser (75-150 kW at 25-40% wall-plug efficiency) has no passive rejection path from a rifle-sized body, and 100 kJ of delivered optical energy per shot implies roughly a kilogram of lithium cell per shot before margin.", "realVal": "100 kW", "canonVal": "0.04 kW", "footMeta": "TRL 8 · WEIGHT 5 OF 10\nREVIEWED EVERY 30 DAYS\n4 INDICATORS · 8 SOURCES", "indicators": [ { "metric": "Peak output of the most powerful laser weapon in operational service", "unit": "kW", "value": 100, "canon_target": 0.04, "as_of": "2025-12-28", "source": "https://en.wikipedia.org/wiki/Iron_Beam" }, { "metric": "System mass of the lightest man-portable directed-energy weapon publicly shown", "unit": "kg", "value": 25, "canon_target": 4.5, "as_of": "2026-06-20", "source": "https://interestingengineering.com/innovation/chinese-man-portable-laser-weapon" }, { "metric": "Dwell time for a man-portable laser to defeat a small UAS at ~500 m", "unit": "s", "value": 4, "canon_target": 0, "as_of": "2026-06-20", "source": "https://www.tomshardware.com/tech-industry/china-shows-off-a-backpack-sized-anti-drone-laser-that-one-soldier-can-carry" }, { "metric": "Operating cost per shot of a fielded high-energy laser", "unit": "USD", "value": 10, "canon_target": 1, "as_of": "2026-01-12", "source": "https://www.everycrsreport.com/files/2026-01-12_R44175_d7afbb9895f1f72259cfb1f7559782c0bb354e02.html" } ], "sources": [ { "date": "2026-07-09", "org": "US DEPARTMENT OF WAR (VIA GLOBALSECURITY.ORG MIRROR)", "text": "The Department of War awarded two Joint Laser Weapon System OTA agreements to nLIGHT Defense and Lockheed Martin Aculight, initial value $86M against an $847M ceiling; initial prototypes rated at approximately 150 kW, scaling to the 300-500 kW threshold stated as required for cruise-missile defence.", "kind": "TRADE", "url": "https://www.globalsecurity.org/military/library/news/2026/07/mil-260709-dod01.htm", "submitter": null }, { "date": "2026-06-20", "org": "INTERESTING ENGINEERING", "text": "Harbin Xinguang Optic-Electronics Technology displayed the Lijian II (~30 kg) and Lijian III (~25 kg) man-portable anti-drone lasers at the Defence Information Equipment and Technology Exhibition in Beijing; the systems split into an emitter, an air cooler and a control terminal with a battery-and-cooling backpack. Output power is not officially disclosed and has been reported as approximately 2 kW.", "kind": "PRIMARY", "url": "https://interestingengineering.com/innovation/chinese-man-portable-laser-weapon", "submitter": null }, { "date": "2026-02-02", "org": "THE WAR ZONE", "text": "USS Preble's 60 kW-class HELIOS laser neutralised four uncrewed aerial vehicles in an at-sea counter-UAS demonstration conducted in autumn 2025; engagement interval, dwell time, target range and flight profiles were all left undisclosed.", "kind": "PRIMARY", "url": "https://www.twz.com/sea/uss-preble-used-helios-laser-to-zap-four-drones-in-expanding-testing", "submitter": null }, { "date": "2026-01-12", "org": "CONGRESSIONAL RESEARCH SERVICE", "text": "CRS reports shipboard laser operating cost of approximately $1 to less than $10 per shot, against a Navy assessment of ~$100M per 60 kW unit and up to $200M per 250 kW unit, and names the binding limits: atmospheric absorption and scattering, thermal blooming, line-of-sight-only engagement, and space, weight, power and cooling on surface combatants.", "kind": "STANDARD", "url": "https://www.everycrsreport.com/files/2026-01-12_R44175_d7afbb9895f1f72259cfb1f7559782c0bb354e02.html", "submitter": null }, { "date": "2025-12-28", "org": "WIKIPEDIA (AGGREGATING ISRAELI MOD AND RAFAEL ANNOUNCEMENTS)", "text": "Israel declared Rafael's Iron Beam, a ~100 kW class laser air-defence system with up to ~10 km range, operational and delivered to the IDF; it is now in full-rate production and has been used in combat.", "kind": "PRIMARY", "url": "https://en.wikipedia.org/wiki/Iron_Beam", "submitter": null }, { "date": "2025-11-20", "org": "UK DEFENCE EQUIPMENT & SUPPORT", "text": "UK MoD reported DragonFire trials at the Hebrides range including a UK-first above-the-horizon track and defeat of drones flying at up to 650 km/h, at a quoted cost of around £10 per shot; a £316M contract will fit the system to Royal Navy Type 45 destroyers by 2027.", "kind": "PRIMARY", "url": "https://des.mod.uk/boost-for-armed-forces-as-new-laser-weapon-takes-down-high-speed-drones", "submitter": null }, { "date": "2025-08-06", "org": "DEFENSE NEWS", "text": "The US Army has built 17 directed-energy prototypes through its Rapid Capabilities and Critical Technologies Office and deployed 11, including four 50 kW Directed Energy M-SHORAD Stryker systems to CENTCOM, but concluded that sustaining them in battlefield conditions needs work and that industry cannot yet manufacture them at scale. RCCTO director Lt Gen Robert Rasch: \"We have got to work on maintainability because ... we cannot get by with the thought of having clean rooms out in combat.\" The Army is standing up the Enduring High Energy Laser programme to move from prototypes to fieldable systems.", "kind": "PRIMARY", "url": "https://www.defensenews.com/land/2025/08/06/army-readies-to-launch-2026-competition-for-counter-drone-laser-weapon/", "submitter": null }, { "date": "2025-07-17", "org": "EPIRUS", "text": "Epirus received a $43,551,060 US Army contract for two IFPC-HPM Generation II high-power microwave counter-swarm systems, claiming more than double the Gen I maximum effective range and a projected 30% power increase; four Gen I systems were delivered in May 2024.", "kind": "TRADE", "url": "https://www.epirusinc.com/press-releases/epirus-receives-43-million-contract-from-u-s-army-for-ifpc-hpm-generation-ii-systems", "submitter": null } ], "movers": [ "Rafael Advanced Defense Systems", "Elbit Systems", "Lockheed Martin", "nLIGHT Defense", "MBDA UK", "Epirus", "Harbin Xinguang Optic-Electronics Technology", "OUSW(R&E) Scaled Directed Energy (SCADE) CTA" ], "commentary": "Canon specified forty watts, which is a reading lamp, then showed the weapon burst a running child. The market has moved anyway. Israel's Iron Beam entered service in December 2025 at 100 kilowatts and a few dollars a shot, and Washington has since committed $847 million toward a containerised 150-kilowatt successor. None of it is portable. The lightest man-carried directed-energy weapon shown anywhere weighs twenty-five kilograms, arrives with a backpack of batteries and coolers, and takes four seconds to burn through a hobby drone at five hundred metres. The energy problem is being solved in megawatts. Canon needs it solved in kilograms.", "weight": 5, "progress": 0.0889 } ] } ] }, { "id": "production", "pres": "hero", "pal": "production", "name": "PRODUCTION", "mission": "Tracing the supply chain that would build one.", "reading": 116.8, "scale": 600, "state": "INDEPENDENT", "moved": "3 WEEKS AGO", "rec": "warm", "kicker": "PRODUCTION", "big": "116.8", "bigLabel": "FAMILY READING", "plate": "PLATE 07", "worstComponent": { "id": "automated-factories", "name": "Automated factories", "factor": 121.66666666666667 }, "componentCount": 3, "weight": 21, "kids": [ { "id": "cat-manufacture", "pres": "card", "name": "Manufacture", "meta": "3 COMPONENTS", "reading": 116.8, "scale": 600, "state": "MORE EFFORTS", "moved": "3 WEEKS AGO", "rec": "warm", "blurb": "Where the metal comes from. Building them without us.", "factLeft": "3 COMPONENTS", "factMid": "12 INDICATORS", "factRight": "WEIGHT 21 OF 313", "footMeta": "3 COMPONENTS · 12 INDICATORS\nWEIGHT 21 OF 313", "weight": 21, "progress": 0.11681428571428572, "kids": [ { "id": "supply-chain-and-materials-availability", "pres": "leaf", "name": "Supply chain and materials availability", "reading": 0.267, "scale": 1, "state": "MORE EFFORTS", "moved": "2 MONTHS AGO", "rec": "mid", "factor": 20.2, "short": "20× short", "canon": "Source, refine and form a high-performance structural alloy of unstated composition, PLUS nuclear fuel, PLUS industrial-scale human tissue culture, at army scale, entirely autonomously, on a planet whose industrial base and civil society have been destroyed.", "real": "No producer controls the whole chain. China mined 69% of world rare-earth output in 2025 and is the sole source of separated heavy rare earths for the United States; its April 2025 export controls on samarium, gadolinium, terbium, dysprosium, lutetium, scandium and yttrium remain in force, with the wider October 2025 regime merely suspended until around November 2026. Western producers depend on those magnets; Chinese producers depend on imported advanced logic.", "realVal": "69 %", "canonVal": "0 %", "footMeta": "TRL 8 · WEIGHT 6 OF 10\nREVIEWED EVERY 30 DAYS\n4 INDICATORS · 5 SOURCES", "indicators": [ { "metric": "China's share of world rare-earth mine production", "unit": "%", "value": 69, "canon_target": 0, "as_of": "2026-02-01", "source": "https://pubs.usgs.gov/periodicals/mcs2026/mcs2026-rare-earths.pdf" }, { "metric": "U.S. net import reliance, heavy rare-earth compounds and metals", "unit": "%", "value": 100, "canon_target": 0, "as_of": "2026-02-01", "source": "https://pubs.usgs.gov/periodicals/mcs2026/mcs2026-rare-earths-heavy.pdf" }, { "metric": "Terbium oxide average price", "unit": "USD/kg", "value": 1010, "canon_target": 50, "as_of": "2026-02-01", "source": "https://pubs.usgs.gov/periodicals/mcs2026/mcs2026-rare-earths-heavy.pdf" }, { "metric": "Domestic content of the most-localised Western humanoid", "unit": "% of parts", "value": 75, "canon_target": 100, "as_of": "2026-06-24", "source": "https://www.sec.gov/Archives/edgar/data/0002074973/000121390026071287/ea029548401ex99-1.htm" } ], "sources": [ { "date": "2026-06-24", "org": "U.S. SECURITIES AND EXCHANGE COMMISSION", "text": "Agility Robotics sources approximately 75% of Digit's parts within the United States - the most-localised Western humanoid on the public record.", "kind": "STANDARD", "url": "https://www.sec.gov/Archives/edgar/data/0002074973/000121390026071287/ea029548401ex99-1.htm", "submitter": null }, { "date": "2026-05-05", "org": "INTERNATIONAL FEDERATION OF ROBOTICS", "text": "Chinese domestic robot suppliers took 57% of their home market in 2024, up from 30% in 2020, and 85% in metal and machinery applications.", "kind": "STANDARD", "url": "https://ifr.org/ifr-press-releases/news/china-makes-ai-powered-robots-core-of-national-strategy", "submitter": null }, { "date": "2026-02-01", "org": "U.S. GEOLOGICAL SURVEY", "text": "China produced 270,000 of 390,000 tonnes of world rare-earth-oxide mine output in 2025 (69%); U.S. net import reliance for rare-earth compounds and metals was 67%, with 71% of 2021-24 imports from China.", "kind": "STANDARD", "url": "https://pubs.usgs.gov/periodicals/mcs2026/mcs2026-rare-earths.pdf", "submitter": null }, { "date": "2026-02-01", "org": "U.S. GEOLOGICAL SURVEY", "text": "U.S. net import reliance for heavy rare-earth compounds and metals is 100%; terbium, holmium and lutetium came 100% from China; terbium oxide averaged $1,010/kg and dysprosium oxide $239/kg in 2025.", "kind": "STANDARD", "url": "https://pubs.usgs.gov/periodicals/mcs2026/mcs2026-rare-earths-heavy.pdf", "submitter": null }, { "date": "2026-02-01", "org": "U.S. GEOLOGICAL SURVEY", "text": "China's April 2025 export controls on samarium, gadolinium, terbium, dysprosium, lutetium, scandium and yttrium remain in force; the October 2025 expansion to all heavy rare earths was suspended in November 2025 for one year.", "kind": "STANDARD", "url": "https://pubs.usgs.gov/periodicals/mcs2026/mcs2026-rare-earths-heavy.pdf", "submitter": null } ], "movers": [ "China Ministry of Commerce", "U.S. Geological Survey", "MP Materials (Mountain Pass)", "Harmonic Drive Systems / Nabtesco", "Agility Robotics", "International Federation of Robotics" ], "commentary": "The metal is the easy part, which is the uncomfortable finding. China mined 69 per cent of the world's rare earths last year, and American reliance on imported heavy rare earths, the dysprosium and terbium that stop an actuator magnet demagnetising when it gets hot, is exactly 100 per cent, with terbium sourced entirely from China at $1,010 a kilogram. Beijing's April 2025 export controls remain in force; the wider October regime is merely suspended, until November. The best-localised Western humanoid is 75 per cent domestic by part count, a metric in which the magnets conveniently hide.", "weight": 6, "progress": 0.2667 }, { "id": "automated-factories", "pres": "leaf", "name": "Automated factories", "reading": 0.071, "scale": 1, "state": "MORE EFFORTS", "moved": "2 MONTHS AGO", "rec": "mid", "factor": 121.66666666666667, "short": "122× short", "canon": "Lights-out factories producing complete autonomous combat platforms end-to-end - sited, supplied, operated and maintained with ZERO human involvement - in an environment with no functioning civilian industry.", "real": "Assembly is machine work and has been for two decades. What is not automated anywhere is the ends of the chain: extraction, refining, tooling changeover, exception handling, and maintenance of the factory itself. All of those are dexterity problems, so the factory that builds humanoids cannot yet be staffed by them.", "realVal": "30 days", "canonVal": "3650 days", "footMeta": "TRL 8 · WEIGHT 7 OF 10\nREVIEWED EVERY 30 DAYS\n4 INDICATORS · 5 SOURCES", "indicators": [ { "metric": "Longest documented unattended run of a lights-out plant", "unit": "days", "value": 30, "canon_target": 3650, "as_of": "2003-06-01", "source": "https://en.wikipedia.org/wiki/Lights_out_(manufacturing)" }, { "metric": "Automation share of the best-in-class consumer-electronics plant", "unit": "%", "value": 81, "canon_target": 100, "as_of": "2024-07-10", "source": "https://newatlas.com/robotics/xiaomi-dark-robotic-factory" }, { "metric": "Humanoids produced per hour off the fastest humanoid line", "unit": "units/h", "value": 1, "canon_target": 100, "as_of": "2026-04-29", "source": "https://www.figure.ai/news/ramping-figure-03-production" }, { "metric": "Global industrial robot density", "unit": "units per 10,000 employees", "value": 132, "canon_target": 10000, "as_of": "2026-04-08", "source": "https://ifr.org/ifr-press-releases/news/robot-density-surges-in-europe-asia-and-americas" } ], "sources": [ { "date": "2026-06-24", "org": "U.S. SECURITIES AND EXCHANGE COMMISSION", "text": "Agility's RoboFab is designed to support production of up to 10,000 humanoid units annually.", "kind": "STANDARD", "url": "https://www.sec.gov/Archives/edgar/data/0002074973/000121390026071287/ea029548401ex99-1.htm", "submitter": null }, { "date": "2026-04-29", "org": "FIGURE AI", "text": "BotQ reached one Figure 03 per hour, a 24x throughput gain in under 120 days, with over 350 units delivered, over 9,000 actuators produced, over 80% end-of-line first-pass yield and 99.3% battery-line yield; line capacity 12,000 units a year.", "kind": "PRIMARY", "url": "https://www.figure.ai/news/ramping-figure-03-production", "submitter": null }, { "date": "2026-04-08", "org": "INTERNATIONAL FEDERATION OF ROBOTICS", "text": "Global industrial robot density reached 132 units per 10,000 employees; China holds roughly two million installed robots and took 54% of world installations in 2024.", "kind": "STANDARD", "url": "https://ifr.org/ifr-press-releases/news/robot-density-surges-in-europe-asia-and-americas", "submitter": null }, { "date": "2024-07-10", "org": "NEW ATLAS", "text": "Xiaomi's Changping dark factory runs eleven automated lines producing over ten million phones a year, with a platform the company says independently diagnoses equipment problems and improves process flows.", "kind": "PRIMARY", "url": "https://newatlas.com/robotics/xiaomi-dark-robotic-factory", "submitter": null }, { "date": "2003-06-01", "org": "WIKIPEDIA, CITING CNN MONEY", "text": "FANUC's Oshino plant has robots building robots at about 50 per 24-hour shift and runs unsupervised for as long as 30 days at a time - the most-cited and least-re-measured figure in lights-out manufacturing.", "kind": "PRIMARY", "url": "https://en.wikipedia.org/wiki/Lights_out_(manufacturing)", "submitter": null } ], "movers": [ "FANUC", "Xiaomi", "Figure AI", "Agility Robotics", "International Federation of Robotics", "ASE Group" ], "commentary": "Robots have been building robots, unsupervised for thirty days at a stretch, since 2001, a fact whose most-cited source is a magazine article from 2003 that nobody has re-measured. The modern showcase, Xiaomi's dark factory, ships ten million phones a year at 81 per cent automation, with people retained for the maintenance. Figure's humanoid line went from one robot a day to one an hour in under four months, which is genuine and is also 12,000 a year. What remains stubbornly human is the non-repeatable work: changing tooling, fixing machines, handling exceptions. All of it is the manipulation problem, wearing overalls.", "weight": 7, "progress": 0.0711 }, { "id": "humanoid-robot-mass-production", "pres": "leaf", "name": "Humanoid robot mass production", "reading": 0.044, "scale": 1, "state": "MORE EFFORTS", "moved": "3 WEEKS AGO", "rec": "warm", "factor": 26.17801047120419, "short": "26× short", "canon": "Series production of a humanoid combat android at a rate sufficient to field it as LINE INFANTRY across a planet, with generational model turnover implying an iterated production programme and a concurrent prototype pipeline.", "real": "Shipments are real and growing fast - 19,100 units in the first half of 2026, up 272% - but the units are research, education and light-industrial machines with 2-4 hour endurance. Announced capacity already far exceeds demand: Tesla targeted 50,000-100,000 units in 2026 and had produced none on a line as of its second-quarter update, Figure's 12,000/year line had delivered over 350, and Agility's 10,000/year factory supports about 100 deployed robots.", "realVal": "19100 units", "canonVal": "500000 units", "footMeta": "TRL 8 · WEIGHT 8 OF 10\nREVIEWED EVERY 30 DAYS\n4 INDICATORS · 7 SOURCES", "indicators": [ { "metric": "Global humanoid robot shipments per half-year", "unit": "units", "value": 19100, "canon_target": 500000, "as_of": "2026-08-10", "source": "https://smartanalyticsglobal.com/global-humanoid-robot-shipments-2026-agibot-unitree/" }, { "metric": "Optimus units produced on a production line against a 50,000-100,000 unit 2026 target", "unit": "units", "value": 0, "canon_target": 50000, "as_of": "2026-07-22", "source": "https://electrek.co/2026/07/02/musk-shuts-down-optimus-4d-chess-theory/" }, { "metric": "Cheapest commercially listed humanoid robot", "unit": "USD", "value": 13500, "canon_target": 1000, "as_of": "2026-06-09", "source": "https://fortune.com/2026/06/09/china-builds-85-percent-worlds-humanoids-robots-cheap/" }, { "metric": "Humanoid billing rate in commercial deployment", "unit": "USD per robot-hour", "value": 25, "canon_target": 1, "as_of": "2026-06-09", "source": "https://fortune.com/2026/06/09/china-builds-85-percent-worlds-humanoids-robots-cheap/" } ], "sources": [ { "date": "2026-08-10", "org": "SMART ANALYTICS GLOBAL", "text": "Global humanoid shipments reached 19,100 units in the first half of 2026, up 272% year on year, with AGIBOT at 8,400 and Unitree at 5,900; full-year 2026 is forecast at roughly 60,000 units and $1.6bn of revenue.", "kind": "PRIMARY", "url": "https://smartanalyticsglobal.com/global-humanoid-robot-shipments-2026-agibot-unitree/", "submitter": null }, { "date": "2026-07-02", "org": "ELECTREK", "text": "Tesla has produced zero Optimus units on a production line against a stated 2026 target of 50,000-100,000, with Musk stating production 'will be extremely slow at first'.", "kind": "PRIMARY", "url": "https://electrek.co/2026/07/02/musk-shuts-down-optimus-4d-chess-theory/", "submitter": null }, { "date": "2026-06-24", "org": "U.S. SECURITIES AND EXCHANGE COMMISSION", "text": "Agility has around 100 Digits with paying customers and over $300m of multi-year Digit v5 orders explicitly subject to contractual milestones, against a factory rated at 10,000 units a year.", "kind": "STANDARD", "url": "https://www.sec.gov/Archives/edgar/data/0002074973/000121390026071287/ea029548401ex99-1.htm", "submitter": null }, { "date": "2026-06-10", "org": "CAIXIN GLOBAL", "text": "China's MIIT and SASAC jointly directed local governments and state-owned enterprises to put more than 10,000 humanoid robots into commercial use by the end of 2026.", "kind": "STANDARD", "url": "https://www.caixinglobal.com/2026-06-10/china-targets-10000-humanoid-robots-in-commercial-use-by-end-2026-102452656.html", "submitter": null }, { "date": "2026-06-09", "org": "FORTUNE", "text": "Chinese firms built roughly 85% of the world's humanoids in 2025 at an average price of about $46,000, and deployment lags production capacity because use cases remain limited.", "kind": "PRIMARY", "url": "https://fortune.com/2026/06/09/china-builds-85-percent-worlds-humanoids-robots-cheap/", "submitter": null }, { "date": "2026-04-29", "org": "FIGURE AI", "text": "Figure has delivered more than 350 Figure 03 units against a first-generation line capacity of 12,000 per year.", "kind": "PRIMARY", "url": "https://www.figure.ai/news/ramping-figure-03-production", "submitter": null }, { "date": "2026-01-12", "org": "PR NEWSWIRE", "text": "Unitree shipped more than 5,500 humanoid robots in 2025, ranking first globally.", "kind": "PRIMARY", "url": "https://www.prnewswire.com/news-releases/unitree-ranks-no1-globally-in-humanoid-robot-shipments-exceeding-5-500-units-in-2025--302674729.html", "submitter": null } ], "movers": [ "AgiBot (Zhiyuan Robotics)", "Unitree Robotics", "Tesla", "Figure AI", "Agility Robotics", "UBTECH Robotics", "MIIT and SASAC" ], "commentary": "Nineteen thousand one hundred humanoids shipped in the first half of 2026, up 272 per cent, three-quarters of them from two Chinese firms. Against that, the announcements: Tesla's 2026 target of 50,000 to 100,000 units, a Fremont line meant to reach a million a year, and, as of the second-quarter update, zero robots produced. Agility's factory is rated for 10,000 a year and supports about a hundred machines with paying customers. The gating item is not the line. It is that a humanoid bills at twenty-five dollars an hour and cannot yet finish a shift on one charge.", "weight": 8, "progress": 0.0444 } ] } ] }, { "id": "physics", "pres": "hero", "pal": "physics", "name": "PHYSICS", "mission": "Marking the point where engineering ends.", "reading": 1.1, "scale": 600, "state": "NO PATH", "moved": "1 MONTH AGO", "rec": "mid", "kicker": "PHYSICS", "big": "1.1", "bigLabel": "FAMILY READING", "plate": "PLATE 08", "worstComponent": { "id": "temporal-displacement-equipment", "name": "Temporal displacement equipment", "factor": 1.2916666666666667e+87 }, "componentCount": 3, "weight": 8, "kids": [ { "id": "cat-time-displacement", "pres": "card", "name": "Time displacement", "meta": "3 COMPONENTS", "reading": 1.1, "scale": 600, "state": "MORE EFFORTS", "moved": "1 MONTH AGO", "rec": "mid", "blurb": "Whether the past is reachable at all. General relativity says maybe; quantum field theory says no. The machine, and its energy budget. The shortfall runs to eighty-seven orders of magnitude.", "factLeft": "3 COMPONENTS", "factMid": "10 INDICATORS", "factRight": "WEIGHT 8 OF 313", "footMeta": "3 COMPONENTS · 10 INDICATORS\nWEIGHT 8 OF 313", "weight": 8, "progress": 0.0010500000000000002, "kids": [ { "id": "closed-timelike-curves", "pres": "leaf", "name": "Closed timelike curves", "reading": 0.002, "scale": 1, "state": "NOT ON TRACK", "moved": "1 MONTH AGO", "rec": "mid", "factor": 454.5454545454545, "short": "455× short", "canon": "Physically realisable closed timelike curves permitting MACROSCOPIC matter to reach its own past light cone - and, in the strong form the franchise requires, an ENGINEERED AND CONTROLLABLE one, aimed at a chosen coordinate in space and time. The films assert it works and never once gesture at how.", "real": "Every known CTC-permitting solution requires either exotic matter violating the null and weak energy conditions, or infinite structures (Tipler's infinitely long rotating cylinder, Gott's infinite cosmic strings), or global cosmological conditions our universe does not have (Godel's rotating dust with negative cosmological constant). The Kerr interior contains CTCs but sits behind an event horizon and inside a Cauchy horizon that is generically unstable.", "realVal": "0 count", "canonVal": "1 count", "footMeta": "TRL 2 · WEIGHT 3 OF 10\nREVIEWED EVERY 90 DAYS\n3 INDICATORS · 9 SOURCES", "indicators": [ { "metric": "Physically realised closed timelike curves", "unit": "count", "value": 0, "canon_target": 1, "as_of": "2026-08-29", "source": "https://arxiv.org/abs/gr-qc/0204022" }, { "metric": "Exact GR solutions containing CTCs that require neither exotic matter nor infinite structures, peer-reviewed", "unit": "solutions", "value": 0, "canon_target": 1, "as_of": "2026-08-29", "source": "https://arxiv.org/abs/2607.00788" }, { "metric": "Status of the chronology protection conjecture", "unit": "proven(1)/unproven(0)", "value": 0, "canon_target": 0, "as_of": "2026-08-29", "source": "https://arxiv.org/abs/gr-qc/0204022" } ], "sources": [ { "date": "2026-07-29", "org": "ARXIV", "text": "Deutsch-CTC consistency conditions were implemented as post-selected decoder circuits on IBM quantum hardware, quantifying decoder fidelity, post-selection overhead and routing-dependent noise. As with all such work, this simulates D-CTC mathematics on ordinary hardware and involves no chronology violation.", "kind": "PRIMARY", "url": "https://arxiv.org/abs/2607.27473", "submitter": null }, { "date": "2026-07-01", "org": "ARXIV", "text": "An unrefereed single-author preprint constructs an exact vacuum spacetime that develops closed timelike curves from regular, asymptotically flat initial data respecting the weak, dominant and strong energy conditions, with the chronology horizon reaching a degenerate configuration whose generating closed null geodesic has vanishing boost and optical scalars. If it survives peer review this would be a CTC-forming spacetime requiring no exotic matter, which is the most robust standing objection in the field. No journal reference and no independent verification as of 2026-08-29.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2607.00788", "submitter": null }, { "date": "2022-03-23", "org": "PHYSICAL REVIEW D (ARXIV:2105.03079)", "text": "Santiago, Schuster and Visser refuted three contemporaneous claims of positive-energy warp drives, showing the claims established only that co-moving Eulerian observers see positive energy density whereas the weak energy condition requires all timelike observers to. All physically reasonable warp drives violate the null energy condition, and in modified gravity the violation moves to the geometric null convergence condition rather than disappearing.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2105.03079", "submitter": null }, { "date": "2014-06-19", "org": "NATURE COMMUNICATIONS", "text": "A photonic experiment simulated the nonlinear behaviour of a qubit interacting unitarily with an older version of itself, reproducing predicted CTC effects including perfect discrimination of non-orthogonal quantum states. No chronology violation occurred: the experiment used ordinary forward-in-time optics.", "kind": "PRIMARY", "url": "https://doi.org/10.1038/ncomms5145", "submitter": null }, { "date": "2009-02-08", "org": "PROCEEDINGS OF THE ROYAL SOCIETY A (ARXIV:0808.2669)", "text": "Aaronson and Watrous proved that computers with access to Deutsch-model closed timelike curves solve exactly the complexity class PSPACE, and that classical and quantum CTC computers have identical power — meaning a CTC would collapse the polynomial hierarchy and eliminate the quantum computing advantage entirely.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/0808.2669", "submitter": null }, { "date": "1996-05-15", "org": "PHYSICAL REVIEW D (ARXIV:GR-QC/9510071)", "text": "Ford and Roman applied quantum-inequality bounds on negative energy density to static traversable wormholes and concluded that either the wormhole must be only a little larger than Planck size, or the negative energy must be concentrated in a band many orders of magnitude smaller than the throat — making macroscopic traversable wormholes very improbable.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/gr-qc/9510071", "submitter": null }, { "date": "1992-07-15", "org": "PHYSICAL REVIEW D", "text": "Hawking proposed the chronology protection conjecture — that the laws of physics prevent the appearance of closed timelike curves, via divergence of the renormalised stress-energy tensor as the chronology horizon forms. It remains unproven in general and requires a quantum theory of gravity to settle.", "kind": "PEER REVIEWED", "url": "https://doi.org/10.1103/PhysRevD.46.603", "submitter": null }, { "date": "1988-09-26", "org": "PHYSICAL REVIEW LETTERS", "text": "Morris, Thorne and Yurtsever showed that a traversable wormhole held open by exotic matter can be converted into a time machine by moving one mouth relativistically, and that this necessarily requires violation of the weak energy condition.", "kind": "PEER REVIEWED", "url": "https://doi.org/10.1103/PhysRevLett.61.1446", "submitter": null }, { "date": "1949-07-01", "org": "REVIEWS OF MODERN PHYSICS", "text": "Godel published the first exact cosmological solution of the Einstein field equations containing closed timelike curves — a rotating, pressureless-dust universe with a negative cosmological constant, establishing that general relativity does not forbid time travel.", "kind": "PEER REVIEWED", "url": "https://doi.org/10.1103/RevModPhys.21.447", "submitter": null } ], "movers": [ "Matt Visser, Victoria University of Wellington", "L. H. Ford and Thomas A. Roman", "Scott Aaronson and John Watrous", "Andrew White group, University of Queensland", "Applied Physics (Bobrick, Martire, Fuchs, Helmerich et al.)" ], "commentary": "General relativity has permitted closed timelike curves since 1949, which is the least useful fact in physics. Every solution demands exotic matter, an infinitely long rotating cylinder, or a universe that rotates and ours does not. Quantum field theory then bounds the negative energy required so tightly that Ford and Roman confined macroscopic wormholes to Planck scale or to an exotic band many orders of magnitude thinner than the throat. Hawking's chronology protection remains a conjecture rather than a theorem, so the honest score is theoretical and not blocked. The best result in the field is Aaronson and Watrous: a working time machine would make quantum computers pointless.", "weight": 3, "progress": 0.0022 }, { "id": "temporal-displacement-equipment", "pres": "leaf", "name": "Temporal displacement equipment", "reading": 0.001, "scale": 1, "state": "BLOCKED", "moved": "2 YEARS AGO", "rec": "cool", "factor": 1.2916666666666667e+87, "short": "87 orders of magnitude short", "canon": "The machine itself: a device occupying a room in a Skynet laboratory complex, generating a spherical displacement field around a single living passenger and sending them one-way to a chosen past coordinate, with violent local electromagnetic and mechanical side effects at both ends. CANON GIVES NO ENERGY FIGURE.", "real": "There is no device concept. Two routes exist in the literature and both fail on the same number. Build and stabilise a traversable wormhole, then move one mouth relativistically — needing order 1.35e27 kg of negative mass for a one-metre throat, held in a configuration the quantum inequalities forbid. Or engineer a global spacetime with pre-existing CTCs — needing infinite cosmic strings or an infinitely long rotating cylinder. No third proposal exists, which is more telling than the failure of the first two.", "realVal": "51 log10 ratio", "canonVal": "0 log10 ratio", "footMeta": "TRL 1 · WEIGHT 3 OF 10\nREVIEWED EVERY 90 DAYS\n6 INDICATORS · 6 SOURCES", "indicators": [ { "metric": "Orders of magnitude between laboratory negative energy and the least demanding requirement", "unit": "log10 ratio", "value": 51, "canon_target": 0, "as_of": "2026-08-29", "source": "https://arxiv.org/abs/gr-qc/9510071" }, { "metric": "Orders of magnitude shortfall for a 100 m warp bubble respecting quantum inequalities", "unit": "log10 ratio", "value": 87, "canon_target": 0, "as_of": "2026-08-29", "source": "https://arxiv.org/abs/gr-qc/9702026" }, { "metric": "Largest negative mass-energy ever assembled in a laboratory", "unit": "kg", "value": -4.8e-25, "canon_target": -1.35e+27, "as_of": "2026-08-29", "source": "https://arxiv.org/abs/gr-qc/9510071" }, { "metric": "Negative mass-energy required for a one-metre traversable wormhole throat", "unit": "kg", "value": -1.35e+27, "canon_target": -4.8e-25, "as_of": "2026-08-29", "source": "https://arxiv.org/abs/gr-qc/9510071" }, { "metric": "Negative mass-energy required for a 100 m warp bubble, quantum-inequality respecting", "unit": "kg", "value": -6.2e+62, "canon_target": -4.8e-25, "as_of": "2026-08-29", "source": "https://arxiv.org/abs/gr-qc/9702026" }, { "metric": "For scale: ratio of the observable universe's diameter to the Planck length", "unit": "log10 ratio", "value": 62, "canon_target": 87, "as_of": "2026-08-29", "source": "https://arxiv.org/abs/gr-qc/9702026" } ], "sources": [ { "date": "2024-04-29", "org": "CLASSICAL AND QUANTUM GRAVITY (ARXIV:2405.02709)", "text": "A constant-velocity subluminal warp drive solution satisfying all energy conditions was constructed by combining a stable positive-ADM-mass matter shell with an Alcubierre-like shift vector distribution, generated numerically and verified not to reduce to a coordinate transformation. Being subluminal, it produces no closed timelike curves and is not a time machine.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/2405.02709", "submitter": null }, { "date": "2011-11-17", "org": "NATURE", "text": "The dynamical Casimir effect was observed in a superconducting circuit with a rapidly modulated boundary condition, generating real photons from vacuum fluctuations — the strongest demonstration that vacuum energy can be engineered, at magnitudes of order 1e-8 J in a laboratory cavity.", "kind": "PEER REVIEWED", "url": "https://doi.org/10.1038/nature10561", "submitter": null }, { "date": "1999-12-01", "org": "CLASSICAL AND QUANTUM GRAVITY (ARXIV:GR-QC/9905084)", "text": "Van Den Broeck showed a geometric modification of the Alcubierre metric — a small bubble neck enclosing a large internal volume — reduces the required negative mass to the order of a few solar masses with a comparable amount of positive energy, satisfying the quantum inequality on weak-energy-condition violations. This is an improvement of roughly 63 orders of magnitude and remains unattainable.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/gr-qc/9905084", "submitter": null }, { "date": "1997-07-01", "org": "CLASSICAL AND QUANTUM GRAVITY (ARXIV:GR-QC/9702026)", "text": "Pfenning and Ford applied quantum inequalities to the Alcubierre metric, finding the bubble wall must be only a few hundred Planck lengths thick and that a 100 m radius bubble requires total negative energy of at most -6.2e65 grams, equivalent to -3e20 galaxy masses, which they describe as roughly ten orders of magnitude greater than the total mass of the entire visible universe. Relaxing the quantum inequality to allow a one-metre wall still requires about a quarter of a solar mass; an electron-Compton-wavelength bubble requires about -400 solar masses.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/gr-qc/9702026", "submitter": null }, { "date": "1997-01-06", "org": "PHYSICAL REVIEW LETTERS", "text": "Lamoreaux measured the Casimir force between conducting surfaces over the 0.6 to 6 micrometre range, establishing experimentally that the quantum vacuum can be manipulated to produce regions of negative energy density.", "kind": "PEER REVIEWED", "url": "https://doi.org/10.1103/PhysRevLett.78.5", "submitter": null }, { "date": "1996-05-15", "org": "PHYSICAL REVIEW D (ARXIV:GR-QC/9510071)", "text": "Quantum energy inequalities place an uncertainty-principle-type constraint on the magnitude and duration of negative energy density seen by a timelike geodesic observer, and applying them to traversable wormholes makes macroscopic examples very improbable. These are derived theorems in quantum field theory, not conjectures.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/gr-qc/9510071", "submitter": null } ], "movers": [ "Michael Pfenning and L. H. Ford", "Chris Van Den Broeck", "Applied Physics (Bobrick, Martire, Fuchs, Helmerich, Sellers, Melcher)", "Steve K. Lamoreaux", "Chalmers University (Wilson, Johansson et al.)" ], "commentary": "The arithmetic is worth stating once, plainly. Pfenning and Ford costed a hundred-metre warp bubble with a quantum-inequality-respecting wall at minus 6.2 times ten to the sixty-fifth grams of negative energy — roughly ten orders of magnitude more than the mass of the visible universe. The best negative energy humanity has ever assembled is a Casimir cavity holding about minus four times ten to the minus eighth joules. The shortfall is fifty-one orders of magnitude against the most forgiving requirement and eighty-seven against the honest one. For scale, the observable universe spans about sixty-two orders of magnitude from end to end in Planck lengths.", "weight": 3, "progress": 0.0006 }, { "id": "organic-only-constraint", "pres": "leaf", "name": "Organic-only constraint", "reading": 0, "scale": 1, "state": "BLOCKED", "moved": "24 YEARS AGO", "rec": "cold", "factor": 1000000, "short": "1,000,000× short", "canon": "The displacement field transports ONLY living organic matter, and whatever is entirely enclosed by it. Nothing dead, nothing inorganic, nothing worn. This single rule is why the T-800 has skin at all - the infiltration disguise and the transit requirement are the SAME engineering constraint. The T-1000 violates it and no film ever addresses that.", "real": "The entire mechanism. Nothing in general relativity or the Standard Model couples to whether a thing is alive.", "realVal": "0 count", "canonVal": "1 count", "footMeta": "TRL 1 · WEIGHT 2 OF 10\nREVIEWED EVERY 180 DAYS\n1 INDICATOR · 2 SOURCES", "indicators": [ { "metric": "Known physical couplings that discriminate by biological status", "unit": "count", "value": 0, "canon_target": 1, "as_of": "2026-08-29", "source": "https://arxiv.org/abs/gr-qc/0204022" } ], "sources": [ { "date": "2002-04-05", "org": "ARXIV", "text": "The standing survey of chronology protection catalogues the peculiarities that arise in spacetimes containing closed causal curves. None of the pathologies, constraints or proposed protection mechanisms discriminates between living and non-living matter; all are expressed in terms of stress-energy and causal structure.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/gr-qc/0204022", "submitter": null }, { "date": "1996-05-15", "org": "PHYSICAL REVIEW D (ARXIV:GR-QC/9510071)", "text": "The constraints that quantum field theory places on any spacetime-manipulating process are expressed entirely in terms of the stress-energy tensor. No formulation of these bounds contains any term sensitive to the biological status of the matter involved.", "kind": "PEER REVIEWED", "url": "https://arxiv.org/abs/gr-qc/9510071", "submitter": null } ], "movers": [], "commentary": "The franchise's load-bearing rule is also its least defensible. Physics sorts matter by conserved quantities: mass-energy, charge, spin, baryon number. Being alive is not among them, and cannot be, because it is a property of a trajectory rather than a state. A cell and the same cell a second after death are, to any achievable precision, identical objects. Cameron appears to have known: Reese answers the question with \"I didn't build the fucking thing.\" The T-1000 then walks through the same field as solid mimetic polyalloy, converting a law of nature into a detector that can be spoofed. Scored at zero, and the score is the point.", "weight": 2, "progress": 0 } ] } ] } ] }