{"id":22765,"date":"2026-10-07T04:00:06","date_gmt":"2026-10-07T04:00:06","guid":{"rendered":"https:\/\/8657085.xyz\/?p=22765"},"modified":"2026-10-07T04:00:06","modified_gmt":"2026-10-07T04:00:06","slug":"the-autonomy-industrys-biggest-architectural-bet-and-what-it-means-for-simulation","status":"publish","type":"post","link":"https:\/\/8657085.xyz\/?p=22765","title":{"rendered":"The autonomy industry&#8217;s biggest architectural bet, and what it means for simulation"},"content":{"rendered":"<p> <div style=\"display: grid; grid-template-columns: 300px 160px; gap: 2px; width: 460px; background: #eee; padding: 2px;\">\r\n\r\n  <!-- \u6574\u884c\u5bbd\u5e7f\u544a -->\r\n  <div style=\"grid-column: 1\/-1; width: 460px; height: 250px; background: #ccc; display: grid; place-items: center;\">\r\n  <script async type=\"application\/javascript\" src=\"https:\/\/a.magsrv.com\/ad-provider.js\"><\/script> \r\n <ins class=\"eas6a97888e2\" data-zoneid=\"5876674\"><\/ins> \r\n <script>(AdProvider = window.AdProvider || []).push({\"serve\": {}});<\/script>\r\n  <\/div>\r\n  <div style=\"grid-column: 1\/-1; width: 460px; height: 90px; background: #ccc; display: grid; place-items: center;\">\r\n  <script async type=\"application\/javascript\" src=\"https:\/\/a.magsrv.com\/ad-provider.js\"><\/script> \r\n <ins class=\"eas6a97888e2\" data-zoneid=\"5876676\"><\/ins> \r\n <script>(AdProvider = window.AdProvider || []).push({\"serve\": {}});<\/script>\r\n  <\/div>\r\n\r\n  <!-- \u5de6\u4fa7\u7ad6\u6392 -->\r\n  <div style=\"height: 250px; background: #ccc; display: grid; place-items: center;\">\r\n  <script async type=\"application\/javascript\" src=\"https:\/\/a.magsrv.com\/ad-provider.js\"><\/script> \r\n <ins class=\"eas6a97888e2\" data-zoneid=\"5876672\"><\/ins> \r\n <script>(AdProvider = window.AdProvider || []).push({\"serve\": {}});<\/script>\r\n  <\/div>\r\n  <div style=\"height: 500px; background: #ccc; display: grid; place-items: center;\">\r\n  <script async type=\"application\/javascript\" src=\"https:\/\/a.magsrv.com\/ad-provider.js\"><\/script> \r\n <ins class=\"eas6a97888e2\" data-zoneid=\"5876680\"><\/ins> \r\n <script>(AdProvider = window.AdProvider || []).push({\"serve\": {}});<\/script>\r\n  <\/div>\r\n\r\n  <!-- \u53f3\u4fa7\u6469\u5929\u697c\uff08\u548c\u5de6\u4fa7\u5b8c\u5168\u5bf9\u9f50\uff09 -->\r\n  <div style=\"grid-row: 3\/5; height: 750px; background: #ccc; display: grid; place-items: center;\">\r\n  <script async type=\"application\/javascript\" src=\"https:\/\/a.magsrv.com\/ad-provider.js\"><\/script> \r\n <ins class=\"eas6a97888e2\" data-zoneid=\"5876678\"><\/ins> \r\n <script>(AdProvider = window.AdProvider || []).push({\"serve\": {}});<\/script>\r\n  <\/div>\r\n  \r\n  <script async type=\"application\/javascript\" src=\"https:\/\/a.magsrv.com\/ad-provider.js\"><\/script> \r\n <ins class=\"eas6a97888e6\" data-zoneid=\"5876682\"><\/ins> \r\n <script>(AdProvider = window.AdProvider || []).push({\"serve\": {}});<\/script>\r\n<\/div><br \/>\n<\/p>\n<div style=\"padding-right:0;padding-left:0\">\n<p class=\"wp-block-paragraph\"><em><em>Opinions expressed by\u00a0Digital Journal\u00a0contributors are their own.<\/em><\/em><\/p>\n<p class=\"wp-block-paragraph\">Autonomy programs are collapsing the driving stack into a single neural network. The bet isn\u2019t whether it can drive. It\u2019s whether anyone can prove it.<\/p>\n<p class=\"wp-block-paragraph\">Two or three years ago, joining an autonomy team meant owning a specific piece of the puzzle: perception, prediction, planning, or controls. Each team owned a distinct box on an architecture diagram, handing data off using clean, pre-agreed formats. It wasn\u2019t always elegant, but it was legible. You could point to a box, state its exact job, and check whether it was doing it.<\/p>\n<p class=\"wp-block-paragraph\">Most of those boxes are now disappearing, replaced by a single end-to-end model taking raw sensor data in and outputting driving commands. The engineering argument for this shift is strong and getting stronger. What often gets overlooked, though, is what it does to evidence.<\/p>\n<p class=\"wp-block-paragraph\">As technical program manager for Applied Intuition\u2019s simulation business, Akshat Gattani works directly with global automakers, Level 4 startups, and industrial autonomy teams in mining and agriculture. The pattern he keeps seeing is that teams treat this shift purely as an AI modeling decision, when most of the actual cost and complexity land somewhere else. A team can swap out a neural architecture in a few months. Building the machinery to train it, test it, and convince a regulator that it belongs on a public road takes much longer.<\/p>\n<h2 id=\"h-the-safety-challenge-why-end-to-end-ai-is-harder-to-validate\" class=\"wp-block-heading\">The safety challenge: Why end-to-end AI is harder to validate<\/h2>\n<p class=\"wp-block-paragraph\">The old modular stack lasted for a decade because it made intuitive sense. Perception fed prediction, prediction fed planning, planning fed controls, and every module had clear metrics to track performance. When something went wrong on a test drive, engineers knew roughly where to look.<\/p>\n<p class=\"wp-block-paragraph\">\u201cTwo to three years ago, almost everyone in autonomy was building modular stacks,\u201d Gattani says. \u201cSince then, rapid breakthroughs in AI have pushed the whole industry toward end-to-end systems.\u201d<\/p>\n<p class=\"wp-block-paragraph\">What teams give up in that trade is usually labeled \u201cinterpretability,\u201d but the concrete loss is the ability to break a massive problem down into smaller, verifiable chunks, which was also how teams broke down their safety proofs. Few developers are going completely end-to-end for that exact reason. Waymo states plainly that you can\u2019t build trust on a black box, running an independent onboard validation layer to verify every trajectory its neural network proposes.<\/p>\n<p class=\"wp-block-paragraph\">Gattani, who spent three years at Cruise working on driverless deployments before joining Applied Intuition, notes how deeply modularity was tied to safety. \u201cWith a modular setup, you could validate the safety case piece by piece,\u201d he says. \u201cPerception had its benchmark tests, planning had its metrics, and if a vehicle misbehaved, you knew which team needed to fix it. Now, there\u2019s nothing to evaluate except the vehicle\u2019s final behavior. Component metrics don\u2019t disappear, but they stop being your upfront proof: they become your post-hoc explanation.\u201d<\/p>\n<p class=\"wp-block-paragraph\">A safety case is an argument built out of smaller claims. Remove those individual claims and you\u2019re left with just one: here is how the vehicle handled this set of situations, and here is why you should trust that these situations reflect the real world. In Gattani\u2019s view, both halves of that claim now depend entirely on simulation, quietly turning simulation from a testing tool into the safety argument itself.<\/p>\n<p class=\"wp-block-paragraph\">For years, simulation was the last step in the pipeline. Engineers wrote code, ran a test suite, counted the passes, and pushed software to the fleet. That worked for hand-written code, but it stops making sense when testing a neural network whose behavior depends entirely on training data, much of which now comes from simulation.<\/p>\n<p class=\"wp-block-paragraph\">Simple math forced this shift. RAND\u2019s landmark 2016 study showed that proving an autonomous car is safer than a human driver through real-world driving alone would require hundreds of millions (or even billions) of miles. Real-world data backs that up: Waymo has logged over 200 million real-world autonomous miles, but tens of billions in simulation.<\/p>\n<p class=\"wp-block-paragraph\">Real-world fleets spend almost all their time logging routine driving. Federal crash data shows that a life-threatening crash occurs roughly once every 10 million human driving miles, and a fatality once every 100 million. Real fleets rarely capture the extreme edge cases safety cases depend on. As Gattani sees it, the long tail of rare events has to be actively generated, not waited for.<\/p>\n<h2 id=\"h-upgrading-the-simulator-using-ai-and-data-to-generate-edge-cases\" class=\"wp-block-heading\">Upgrading the simulator: using AI and data to generate edge cases<\/h2>\n<p class=\"wp-block-paragraph\">Earlier simulators relied on hand-crafted 3D models and manual coding rules. That worked fine for validating deterministic rules, but it falls short for training deep networks because human teams can\u2019t build scenes fast enough.<\/p>\n<p class=\"wp-block-paragraph\">\u201cWe\u2019re shifting from traditional physics engines to data-driven AI tools,\u201d Gattani says. \u201cInstead of hand-crafting scenarios from scratch, simulation is becoming deeply grounded in real-world sensor logs.\u201d<\/p>\n<p class=\"wp-block-paragraph\">This shift opens up two powerful capabilities:<\/p>\n<p class=\"wp-block-paragraph\">First, smart \u201creactive\u201d AI agents can be dropped into real-world logs to create sudden hazards: an aggressive driver cutting in, a pedestrian stepping off a curb late, or a vehicle ignoring a right-of-way. Because these agents react live to the vehicle, testing becomes dynamic and measurable rather than scripted.<\/p>\n<p class=\"wp-block-paragraph\">Second, modern generative world models can take real sensor logs and re-render the scene under entirely new conditions.<\/p>\n<p class=\"wp-block-paragraph\">\u201cYou can take data recorded on a clear, sunny morning and re-render it as a night scene, or add heavy fog and rain,\u201d Gattani explains. \u201cNow you have rich synthetic training data that feeds straight back into the driving model. This lets teams stress-test models in conditions they never physically drove through, like blinding sun glare or sudden downpours.\u201d<\/p>\n<p>In one instance, an industrial equipment manufacturer needed to test how its autonomous machines handled sudden, blinding dust clouds thrown up by heavy haul trucks in an open-pit mine, a scenario far too dangerous to recreate with human drivers. Synthetic simulation allowed them to generate and test those extreme conditions repeatedly without risking lives or machinery.<\/p>\n<h2 id=\"h-the-blind-spot-managing-risks-when-simulators-are-driven-by-ai\" class=\"wp-block-heading\">The blind spot: Managing risks when simulators are driven by AI<\/h2>\n<p class=\"wp-block-paragraph\">How far companies should trust AI-generated environments remains debated. UK-based Wayve uses its GAIA-4 model to generate realistic camera and radar inputs while keeping the surrounding world fixed (\u201cworld-on-rails\u201d). Waymo uses broad generative models to construct entirely novel scenes the real fleet never saw. One prioritizes grounding in real logs; the other prioritizes maximum exposure to new situations.<\/p>\n<p class=\"wp-block-paragraph\">Neither approach removes risk; it changes where the risk lives. A traditional simulator fails when an engineer writes a bad rule, which you can audit in code. A generative simulator fails when pushed outside its training data, even while its visual outputs look photorealistic.<\/p>\n<p class=\"wp-block-paragraph\">\u201cYou have to treat the simulator as a statistical model, not ground truth,\u201d Gattani warns. \u201cWhen simulated video looks photo-real, teams can get complacent. We rely on rigorous sanity checks: over short timeframes, does the physics hold together? Do other drivers behave like humans? Then you compare aggregate results against real fleet data. If synthetic runs diverge from actual roads, you\u2019ve stepped outside what you can trust.\u201d<\/p>\n<h2 id=\"h-testing-real-behavior-why-gattani-believes-interactive-closed-loop-simulation-is-mandatory\" class=\"wp-block-heading\">Testing real behavior: Why Gattani believes interactive closed-loop simulation is mandatory<\/h2>\n<p class=\"wp-block-paragraph\">Better synthetic data still doesn\u2019t tell you how a vehicle will actually drive. For that, Gattani argues, the simulated world has to respond to the vehicle\u2019s actions.<\/p>\n<p class=\"wp-block-paragraph\">Open-loop testing replays a recorded drive and checks what the neural model would have done at any given frame. It\u2019s fast and cheap, but it completely ignores the model\u2019s choices. Waymo compares open-loop testing to stepping inside a movie replay: the world moves, but nothing reacts to you.<\/p>\n<p class=\"wp-block-paragraph\">Closed-loop testing forces the world to react. If the model steers or brakes, the surrounding scene changes, and the next sensor frame reflects that decision. You can put an end-to-end network in the exact same scenario twice and observe how its driving changes.<\/p>\n<p class=\"wp-block-paragraph\">The trade-off is drift. The instant a vehicle strays from the original log, the simulator has to invent how the rest of the scene responds, compounding errors over time. Wayve\u2019s \u201cworld-on-rails\u201d limits this by locking the background scene to the log, letting only the main vehicle move freely.<\/p>\n<p class=\"wp-block-paragraph\">Open-loop testing holds the world still so engineers can figure out why a model made a decision; closed-loop lets the world move so they can see what the vehicle actually does. Relying on only one leaves a team either debugging blind or approving road deployments based on behavior they can\u2019t explain.<\/p>\n<h2 id=\"h-defining-simulation-realism-measuring-the-sim-to-real-gap\" class=\"wp-block-heading\">Defining simulation realism: Measuring the \u201csim-to-real\u201d gap<\/h2>\n<p class=\"wp-block-paragraph\">No matter how advanced simulators get, none are perfectly real. \u201cWill simulation ever completely replace road testing?\u201d Gattani asks. \u201cNo. The short answer is simply no.\u201d<\/p>\n<p class=\"wp-block-paragraph\">The real work lies in measuring the gap between simulation and reality. A precise, measurable gap carries far more weight in a safety case than vague claims of realism. Frameworks like Wayve\u2019s evaluate outcome fidelity, closed-loop trajectory fidelity, and sensor component fidelity. Waabi\u2019s \u201cpair-setting\u201d benchmark builds digital twins of real logs to score spatial distance between simulated and real trajectories, reporting a 99.7% realism score.<\/p>\n<p class=\"wp-block-paragraph\">Gattani urges caution regarding isolated metrics. A realism score is only as good as the underlying scenario dataset, and the industry currently lacks shared benchmark scenarios or independent auditing. Furthermore, errors are rarely obvious to the eye: a simulated wall might look real to a human reviewer while returning an inaccurate radar reflection.<\/p>\n<p class=\"wp-block-paragraph\">Beyond physical sensor fidelity, Gattani highlights system fidelity: verifying whether the offboard simulation pipeline feeds the neural model the exact data structure that onboard vehicle hardware receives. If offboard timing, deskewing, or hardware latencies feed the model data in a format the real car never sees, the test is invalid.<\/p>\n<h2 id=\"h-industrial-autonomy-why-mining-and-agriculture-rely-even-more-on-synthetic-data\" class=\"wp-block-heading\">Industrial autonomy: Why mining and agriculture rely even more on synthetic data<\/h2>\n<p class=\"wp-block-paragraph\">Mining, agriculture, and construction are making the same pivot to end-to-end AI, facing identical core validation questions.<\/p>\n<p class=\"wp-block-paragraph\">\u201cWhat surprised me most is how identical the questions are,\u201d Gattani says. \u201cA haul truck and a passenger car are completely different machines, but the questions match: Can we recreate what the sensors saw? Can we test how the machine reacts when the world pushes back? And does any of this predict what happens in the field?\u201d<\/p>\n<p class=\"wp-block-paragraph\">The big difference is data volume. Urban robotaxis generate petabytes daily, whereas a mining company might operate 15 trucks in a remote pit, and agriculture is limited by harvest windows. Sectors leaning hardest on synthetic data often have the least real-world data to validate their simulators against.<\/p>\n<h2 id=\"h-the-road-ahead-what-the-autonomy-industry-must-decide-next\" class=\"wp-block-heading\">The road ahead: What the autonomy industry must decide next<\/h2>\n<p class=\"wp-block-paragraph\">Simulation software is evolving faster than regulatory frameworks. The industry still lacks clear agreement on what makes a synthetic scenario legally valid, how to benchmark closed-loop accuracy, or how much synthetic evidence regulators should accept.<\/p>\n<p class=\"wp-block-paragraph\">Existing technical standards like ISO 21448 (SOTIF) and ASAM OpenSCENARIO offer starting points for scenario description and functional safety. However, major regulatory authorities (including NHTSA in the US and UNECE in Europe) have yet to establish formal rules converting closed-loop simulation metrics into official safety certification.<\/p>\n<p class=\"wp-block-paragraph\">Over the next two to three years, three key questions will settle out: which simulation methodologies regulators actually trust, which testing platforms deliver sensor-accurate closed-loop evaluation at scale, and which teams consistently measure their sim-to-real gap instead of assuming it away.<\/p>\n<p class=\"wp-block-paragraph\">The central question in autonomy was never really whether a deep neural network could learn to steer. It was whether the industry could build the evidence to prove that it should.<\/p>\n<\/div>\n<p><!-- \u603b\u5bb9\u5668\uff1a\u6700\u5927\u5bbd908px Grid\u7d27\u51d1\u5e03\u5c40 -->\r\n<div style=\"display: grid; grid-template-columns: 728px 160px; gap:2px; width:908px; background:#eee; padding:2px;\">\r\n\r\n  <!-- \u901a\u680f\u9876\u90e8\uff1a\u6700\u5927\u6a2a\u5e45 908x258 \u8de8\u6574\u884c -->\r\n  <div style=\"grid-column:1\/-1; height:258px; background:#ff6b6b; display:grid; place-items:center;\">\r\n    <!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114307\" data-width=\"908\" data-height=\"258\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114307});<\/script>\r\n<!--JuicyAds END-->\r\n  <\/div>\r\n\r\n  <!-- \u7b2c\u4e8c\u901a\u680f\uff1a728\u00d790 \u901a\u680f -->\r\n  <div style=\"grid-column:1\/-1; height:90px; background:#4ecdc4; display:grid; place-items:center;\">\r\n    <!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114300\" data-width=\"728\" data-height=\"90\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114300});<\/script>\r\n<!--JuicyAds END-->\r\n  <\/div>\r\n\r\n  <!-- \u5de6\u4fa7\u4e3b\u680f\uff1a\u591a\u5e7f\u544a\u5806\u53e0 -->\r\n  <div style=\"display:grid; gap:2px;\">\r\n    <div style=\"height:60px; background:#45b7d1; display:grid; place-items:center;\">\r\n\t<!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114308\" data-width=\"468\" data-height=\"60\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114308});<\/script>\r\n<!--JuicyAds END-->\r\n\t<\/div>\r\n    <div style=\"height:250px; background:#ffe066; display:grid; place-items:center;\">\r\n\t<!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114299\" data-width=\"300\" data-height=\"250\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114299});<\/script>\r\n<!--JuicyAds END-->\r\n\t<\/div>\r\n    <div style=\"height:250px; background:#ff9ecd; display:grid; place-items:center;\">\r\n\t<!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114305\" data-width=\"250\" data-height=\"250\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114305});<\/script>\r\n<!--JuicyAds END-->\r\n\t<\/div>\r\n    <div style=\"height:139px; background:#c792ea; display:grid; place-items:center;\">\r\n\t<!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114302\" data-width=\"133\" data-height=\"139\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114302});<\/script>\r\n<!--JuicyAds END-->\r\n\t<\/div>\r\n    <div style=\"height:125px; background:#91e7ac; display:grid; place-items:center;\">\r\n\t\r\n<!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114303\" data-width=\"125\" data-height=\"125\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114303});<\/script>\r\n<!--JuicyAds END-->\r\n\t<\/div>\r\n  <\/div>\r\n\r\n  <!-- \u53f3\u4fa7\u7ad6\u680f\uff1a160\u00d7600 \u6574\u5217\u9ad8\u5e7f\u544a -->\r\n  <div style=\"grid-row:3\/8; height:600px;  display:grid; place-items:center;\">\r\n    <!-- JuicyAds v3.0 -->\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async src=\"https:\/\/poweredby.jads.co\/js\/jads.js\"><\/script>\r\n<ins id=\"1114301\" data-width=\"160\" data-height=\"600\"><\/ins>\r\n<script type=\"text\/javascript\" data-cfasync=\"false\" async>(adsbyjuicy = window.adsbyjuicy || []).push({'adzone':1114301});<\/script>\r\n<!--JuicyAds END-->\r\n  <\/div>\r\n\r\n<\/div><br \/>\n<br \/> The autonomy industry&#8217;s biggest architectural bet, and what it means for simulation<br \/>\n<br \/>#autonomy #industrys #biggest #architectural #bet #means #simulation<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Opinions expressed by\u00a0Digital Journal\u00a0contributors are their own. Autonomy programs are collapsing the driving stack into&#8230;<\/p>\n","protected":false},"author":1,"featured_media":22766,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[7],"tags":[11639,2571,1982,2593,15438,692,13509],"class_list":["post-22765","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-stories","tag-architectural","tag-autonomy","tag-bet","tag-biggest","tag-industrys","tag-means","tag-simulation"],"featured_image_urls":{"full":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/TechTO-11-9.png",1600,900,false],"thumbnail":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/TechTO-11-9-150x150.png",150,150,true],"medium":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/TechTO-11-9-300x169.png",300,169,true],"medium_large":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/TechTO-11-9-768x432.png",640,360,true],"large":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/TechTO-11-9-1024x576.png",640,360,true],"1536x1536":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/TechTO-11-9-1536x864.png",1536,864,true],"2048x2048":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/TechTO-11-9.png",1600,900,false],"covernews-slider-full":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/TechTO-11-9-1115x715.png",1115,715,true],"covernews-slider-center":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/TechTO-11-9-800x500.png",800,500,true],"covernews-featured":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/TechTO-11-9-1024x576.png",1024,576,true],"covernews-medium":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/TechTO-11-9-540x340.png",540,340,true],"covernews-medium-square":["https:\/\/8657085.xyz\/wp-content\/uploads\/2026\/10\/TechTO-11-9-400x250.png",400,250,true]},"author_info":{"display_name":"admin","author_link":"https:\/\/8657085.xyz\/?author=1"},"category_info":"<a href=\"https:\/\/8657085.xyz\/?cat=7\" rel=\"category\">Stories<\/a>","tag_info":"Stories","comment_count":"0","_links":{"self":[{"href":"https:\/\/8657085.xyz\/index.php?rest_route=\/wp\/v2\/posts\/22765","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/8657085.xyz\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/8657085.xyz\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/8657085.xyz\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/8657085.xyz\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=22765"}],"version-history":[{"count":0,"href":"https:\/\/8657085.xyz\/index.php?rest_route=\/wp\/v2\/posts\/22765\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/8657085.xyz\/index.php?rest_route=\/wp\/v2\/media\/22766"}],"wp:attachment":[{"href":"https:\/\/8657085.xyz\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=22765"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/8657085.xyz\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=22765"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/8657085.xyz\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=22765"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}