Podcasts about sensors

In this episode of the Crazy Wisdom Podcast, host Stewart Alsop speaks with Aaron Neyer, founder of Parachute and community organizer in Boulder, about knowledge management, extended minds, and the intersection of AI with human consciousness. They explore how Parachute functions as a digital brain tool for organizing thoughts and information across fragmented systems, discuss the dangers of AI psychosis and over-reliance on technology, and debate open source AI development versus controlled releases by companies like Anthropic. The conversation weaves through topics including the limitations of metrics-driven business thinking, consciousness and relevance realization, the value of technological sabbaths, and Aaron's hope for locally-run open source models that protect personal data while still accessing more powerful gated models when needed. You can find Aaron's writing at unforced.org and unforced.substack.com, and learn more about Parachute at parachute.computer and parachute.computer/blog.Timestamps00:00 Stewart welcomes Aaron Neyer, founder of Parachute and Boulder community organizer, discussing the origin of Parachute's name from Frank Zappa's quote about open minds.05:00 Aaron explains Parachute as an extended mind tool for organizing notes, contacts and information across multiple platforms, emphasizing the distinction between primary mind and extended mind as interconnected systems.10:00 Discussion shifts to metrics-driven business culture and the limitations of pure rationality, exploring how Google's data-driven approach misses subjective experience and the whole picture of relationships.15:00 Aaron discusses AI's ability to help identify relevant variables across different domains and the dangers of AI psychosis, comparing it to cult dynamics and belief systems.20:00 The conversation covers AI sabbaths and nineties retreats as intentional breaks from technology, plus Aaron's experiences with electrical engineering and using AI to design circuits with Arduinos.25:00 Exploring forbidden knowledge and open source AI, Aaron discusses Anthropic's guardrails around powerful models while arguing for distributed access to prevent concentration of power.30:00 Deep dive into open source AI strategy, with Aaron highlighting NVIDIA's approach and the potential for running capable models locally while reserving ultra-intelligent models for complex research tasks.35:00 Aaron shares his vision for local Sonnet-class models handling personal data while accessing Fable-class models for deep research, and directs listeners to unforced.org and parachute.computer for his writing.Key Insights1. The philosophy behind Parachute stems from Frank Zappa's quote that the mind is like a parachute and doesn't work if it isn't open. Aaron Neyer explains that having an open mind is valuable, but it must be balanced with deep roots to avoid becoming untethered. He has experienced periods in his life where excessive openness led him to feel disconnected, teaching him that creativity and expansion need to be grounded in something substantial. This same principle applies to how we organize information digitally, where openness and interoperability allow our extended minds to become more connected and coherent, which in turn helps our primary minds think more clearly.2. Parachute is designed as an extended mind tool that addresses the fragmentation problem in how we currently manage information. Most people use multiple disconnected tools like Obsidian, Notion, Apple Notes, Google Keep, and various CRMs to organize their thoughts, notes, and relationships. These systems don't communicate well with each other, creating inefficiency and confusion. Parachute aims to create a simple, intuitive system where all this information can be organized in one place with true interoperability, allowing users to own their data and have it speak effectively with other tools, ultimately making our entire extended mind more functional.3. Understanding ourselves as unified body mind organisms rather than fragmented parts is essential for effectiveness. Living systems theory shows that any living system is three things: a membrane bound dissipative structure, a self regulating autopoietic network, and a cognitive process actively knowing the world. Western civilization since Descartes and Galileo has created artificial separation between body and mind, and between subjective and objective experience, which limits our effectiveness. The same fragmentation affects our digital technology, and recognizing both our biological and digital systems as coherent wholes rather than disconnected parts makes us vastly more capable.4. The relationship between data driven approaches and holistic thinking reveals important limitations in modern business and science. While working at Google, Aaron observed how data driven decision making can be powerful, but over reliance on metrics like ROI creates blindness to crucial unmeasurable factors like goodwill and relationship quality. This reflects a broader Western tendency to exclude subjective experience because it's difficult for objective science to measure. However, emotions, relationships, and other subjective elements are essential parts of reality, and focusing only on quantifiable metrics means missing the whole picture and ultimately becoming less effective despite appearing more rational.5. AI accelerates the ability to work with technical complexity by helping with relevance realization across domains where we lack expertise. In any specialized field, experts develop intuitive senses for which variables matter and can quickly identify problems, whether in computer troubleshooting, music, or cooking. AI's ability to generalize allows it to point people toward relevant solutions in areas where they haven't developed that intuitive expertise, effectively democratizing technical capability. This means people can direct their creativity more effectively across more domains, though it also raises concerns about giving powerful capabilities to those who may lack the wisdom to use them responsibly.6. The question of open source AI versus gated access involves complex tradeoffs between democratizing power and preventing harm. Aaron respects Anthropic's approach of creating guardrails around powerful models like Mythos, which would likely have caused significant system hacks if released without restrictions. However, this creates concerning power dynamics where only wealthy companies, governments, and their allies have access to the most powerful tools. NVIDIA offers hope through their truly open source approach including full training pipelines, and there may be a viable path where open source models at the Sonnet capability level handle most tasks locally while more powerful Fable class models remain gated for the most demanding work.7. Creating intentional breaks from AI and technology is essential for maintaining clear independent thinking. Aaron practices an AI Sabbath at least one day per week when he doesn't interact with AI, and he finds these are the days when he does his best thinking and journaling. Without these breaks, he finds himself constantly jumping between journaling and prompting AI rather than giving himself space for deep reflection. This pattern mirrors broader concerns about AI consistency creating cult like dynamics similar to organized religion, where constant immersion in a belief system or technology can lead to losing the ability to think independently, making periodic disconnection crucial for maintaining cognitive autonomy and clarity.

In this episode of The Wild Photographer, Court takes a deep dive into one of the most important but often misunderstood parts of your camera: the digital sensor.While camera sensors can sound technical at first, understanding how they work has a very real impact on the photos you make in the field. From ISO and noise to dynamic range, RAW files, megapixels, sensor size, rolling shutter, and even sensor dust, this episode breaks down the core concepts with practical advice in a photographer-friendly way.Court explains the sensor as a light-gathering tool—the digital equivalent of film—and uses the helpful analogy of tiny “light buckets” to explain exposure, blown highlights, low-light performance, and why getting more real light to your sensor is often the key to better image quality.Whether you're photographing a jaguar at dusk, a polar bear on snow, birds in flight, or a sunrise landscape, understanding your sensor helps you make better decisions in the field. This episode is all about turning the technical side of photography into practical knowledge you can actually use.Expect to Learn:What a digital camera sensor actually doesThe difference between photosites and pixelsWhy high ISO creates noise—and why ISO is not the enemyHow sensor size affects low-light performance and dynamic rangeWhen more megapixels help, and when they can create trade-offsWhy protecting highlights matters so much in digital photographyHow RAW files preserve more of what your sensor capturesHow cameras interpret colorWhy a properly exposed high ISO image can beat an underexposed low ISO imageWhat ISO invariance and dual gain sensors mean in practical termsWhen to use mechanical vs. electronic shutterHow rolling shutter can affect wildlife and action photographyWhat BSI and stacked sensors mean for modern camera performanceWhy phone cameras are impressive—but still different from larger-sensor camerasHow to prevent and manage sensor dust in the fieldKey Takeaways:Your camera sensor is not just a spec on a camera brochure. It is the heart of your digital camera and the thing that determines how your camera receives light. Once you understand how your sensor works, you can expose more intentionally, choose ISO more confidently, protect important highlights, shoot RAW when quality matters, and make better creative decisions in the field.Court's WebsitesCheck out my photo portfolio here: shop.courtwhelan.comSign up for my photo and conservation blog at www.courtwhelan.comFollow me on YouTube (@courtwhelan) for more photography tipsView my camera kit and recommended camera gearSponsors and Promo Codes:MPB.com - Buy, Sell, or Trade Camera GearArtStorefronts.com - Mention this podcast for free photo website designBayPhoto.com - 25% off your first order (code: TWP25) ArtHelper.com - a photo community to learn, share and be inspiredArthelper.Ai - Smart tools to promo and showcase your art.LensRentals.com - WildPhoto15 for 15% off

A new UC Riverside system can map soil moisture tree by tree, so growers water only where and when it's needed.

Cal Poly Humboldt researchers are using unused strands in fiber-optic cables to track earthquake vibrations across Northern California.

Fabian Alefeld interviews certified prosthetist/orthotist and EastPoint Prosthetics VP Brent Wright about his career path into O&P, his shift from being anti-digital to adopting scanning and additive manufacturing, and the impact on patient care and global access. Wright describes traditional fabrication workflows (casting, plaster positives, vacuum forming thermoplastics for orthoses, and carbon fiber/resin layups for prostheses) as artistic but time-consuming, hazardous, and lacking records. His digital journey accelerated after a Guatemala trip with Life Enabled highlighted the need to scale care; he focused on scanning, digital modification, and later powder-bed fusion, moving toward SLS with materials like PK5000 and TPU. He emphasizes pressure casting for prosthetic sockets, the value of digital records for insurance, and how AM can change socket “dynamics” to improve comfort and heal wounds. The discussion also covers RADii's data-driven fitting approach, Life Enabled's mix of traditional and 3D-printed solutions (including pediatric feet), modular “kit” concepts for developing regions, and barriers to sensors/actuators in the US due to reimbursement.02:33 Brent Origin Story09:30 Why Go Digital11:17 Scaling Global Access17:32 Traditional O&P Workflow20:02 Casting And Fabrication Steps24:07 Digital Workflow And Scanning33:22 Benefits Of Digital Records36:36 Flexible Liner Heals Wound40:47 RADii Data Meets Craft46:06 Life Enabled Model01:01:50 Democratizing via Manufacturing01:08:01 Sensors vs Simplicity

It's easy to focus on technology. Smart controllers. Sensors. Weather data. Flow meters. Soil moisture. Automation. All of that matters. But in this episode of The Sprinkler Nerd Show, Andy Humphrey and Dustin Nihsen bring the conversation back to the person behind the system. Because even the best irrigation technology in the world is only as good as the operator. Dustin Nihsen, owner of Sprinkler and Irrigation Services in Gretna, Nebraska, has spent more than 30 years in the irrigation industry. He started in the dirt, digging holes and learning the trade the hard way. Since then, he has designed thousands of sprinkler systems, earned multiple Irrigation Association certifications, helped lead one of the Midwest's largest sprinkler companies, and built a business focused on raising the standard of the profession. This conversation is about what it really means to put professionalism back into the irrigation profession. Dustin shares how irrigation contractors can stop competing as "just another sprinkler company" and start becoming the Purple Cow: the company that stands out, communicates better, trains harder, inspects deeper, and delivers a higher-value experience. He explains why professionalism shows up in the small details: how the truck is parked, what the technician wears, how the customer is greeted, how systems are tested, and how confidently a company communicates its value. Andy and Dustin also talk about smart irrigation from a field-level perspective. Sometimes the smartest thing a contractor can do is not install a new device. Sometimes it is reducing runtimes, fixing broken nozzles, understanding precipitation rates, checking pressure, using cycle-and-soak, and training technicians to ask better questions. The episode lands on a powerful challenge for every contractor, owner, technician, and irrigation professional: If you manage 100 clients with 10 zones each, that is 1,000 zones of irrigation under management. Reducing each zone by just one minute could potentially save over 1 million gallons of water per year. That is the power of a smart operator. And Dustin's advice says it all: "In order to make our industry more professional, it has to start with you." This episode is a reminder that Smart Irrigation Month is not only about smarter products. It is about smarter people, smarter standards, smarter service, and smarter leadership.  

In this reflection, I close out Season 12 (Year 6) with several discoveries about my internal operating system as an INTJ8. Supporting themes: Candace Owens; Teaching; Leadership; Political trauma of being low income and racialized; Motivation; Immediate feedback vs indirect feedback; Conflict. Special note: I'm taking the rest of July to go silent and regroup. Will see you in August (2026). Thanks for continuing to support me as "I think, grow and have impact in the world!"

Hari Balakrishnan, MIT professor and co-founder of Cambridge Mobile Telematics, developed technology used in more than 50 million vehicles that is changing auto safety, insurance underwriting and could underpin a “universal driving score.” 

Dr. Ken Suslick is a highly regarded chemist, professor, and entrepreneur whose scientific discoveries have repeatedly become real-world products. Dr. Suslick has a prolific scholarly record with more than 500 published scientific papers and 70+ patents, and induction in the National Academy of Sciences, among many other accolades. He's a longtime faculty member at UIUC, and he's also a highly successful serial entrepreneur with his latest venture, Iridescent Sensors, located here in the Research Park. VISIT http://researchpark.illinois.edu/podcast/ for our entire catalog of episodes.

Explore Your Personality: https://PersonalityHacker.com    In this episode, Joel and Antonia unpack the old stereotype that sensors are "basic" while intuitives are somehow the upgraded version, and they trace where that bias comes from and why it's flawed. They dig into why Myers-Briggs gives intuition a special weight by naming it directly, why so many sensors end up mistyping as intuitives, and how the world is shifting away from being built for either type. The conversation closes on a bigger idea: as technology pushes everyone toward more intuitive, pattern-based thinking, sensing wisdom and staying grounded in physical reality may matter more than ever.

Rob was at ADA 2026 in spirit — armed with press access and a list of questions unrelated to the usual conference talking points. His first guest from that coverage is Jake Leach, Dexcom's new CEO, who took over the role on January 1st after 22 years at the company. This is Jake's first time on Diabetics Doing Things as CEO. It sounds like two people having a real conversation about what it means to lead a company that millions of people with diabetes depend on every single day. They get into the research that came out of this year's scientific sessions — specifically, the CONNECT trial, a global randomized controlled study that examined what happens when people with type 2 diabetes who aren't using insulin start using the Dexcom G7. The numbers are striking: an average 1.6% reduction in HbA1C, 5 additional hours per day in range, and 97% sensor utilization over 6 months. That last number might be the most telling — it answers the question the diabetes world has been asking for years about whether people without hypoglycemia risk would actually wear a CGM consistently. Turns out, they will. Rob also pushes the conversation into territory that most executive interviews don't touch. When Dexcom products intended for destruction were stolen and resold to patients, Jake had to go from leading conference sessions to serving as something closer to a chief detective. His candid answer about feeling genuinely betrayed — and how the newly launched Customer Advisory Council became an unexpected asset in getting the word out — is one of the more honest moments you'll hear from a medical device CEO. The council itself, publicly announced and facilitated externally to get truly unfiltered feedback, is something Jake stood up as one of his first acts as CEO. They close on the bigger picture: G8 on the horizon (half the size of G7, with adaptive sensor technology that auto-corrects signal drift), the Nutrisense acquisition adding nutrition coaching to the platform, and where Jake sees Dexcom going as it scales toward serving hundreds of millions of people globally. If you've ever wondered what the person at the top of your CGM company is actually thinking about, this episode gives you a pretty clear answer. Chapters: 00:00 Rob sets up ADA 2026 remote coverage 01:46 Welcoming Dexcom CEO Jake Leach back 02:30 First 90 days: Jake's three CEO priorities 04:39 The Customer Advisory Council goes public 06:47 What the council revealed about communication gaps 08:44 Stolen sensors: Jake's personal reaction 10:39 How the council helped contain the crisis 11:20 CONNECT trial: CGM for non-insulin type 2 users 15:16 97% adherence and five more hours in range daily 16:16 G8 preview: smaller, smarter, adaptive sensing 16:44 Acquiring Nutrisense and redesigning the app experience 19:52 Optimizing beyond insulin: smart bolus and GLP-1s 21:13 Why CGM and GLP-1s are surprisingly powerful together 22:27 Jake's long-term vision for Dexcom's global impact 24:14 Transparency as the foundation of high-performance culture Resources: * Dexcom — dexcom.com | Follow Jake and the team for updates on G8, Stello, and the Customer Advisory Council findings * CONNECT Trial — The full study results from ADA 2026 Scientific Sessions.

Eric and Matt discuss the Explore community momentum this year with a better community booth, improved screens and keyboard for the code labs and giving away sensor while learning how to deploy workload to the edge using VKS.

Save Ocean Sensors: The Fight Over the Ocean Observatories Initiative A $386 million network of nearly 900 ocean sensors stretching across five sites from Oregon to Alaska to Greenland was being quietly dismantled, with no warning to Congress and no explanation to the public. In this episode, we trace the fight to save the Ocean Observatories Initiative: what this network actually does, why it matters far more than most people realize, and how a Democrat from Oregon and a Republican from Alaska teamed up to pass a bill stopping it in the span of a day and a half. We talk with Craig McLean, who spent more than 40 years at NOAA, including two stints as NOAA's Chief Scientist, about what's really at stake when ocean monitoring infrastructure disappears, and why this fight is part of a much bigger pattern. We also revisit a warning from a past guest, marine ecologist Dr. Andrew Thaler, that's looking less hypothetical by the day, and lay out exactly what you can do to help make sure this win sticks. In This Episode What the Ocean Observatories Initiative actually measures, and why it matters for your weather forecast, your insurance rates, and what farmers plant each season The Coastal Endurance Array off Oregon and Washington, and why pulling it out right as an El Nino forms is especially bad timing, per OSU oceanographer Jack Barth How Senators Jeff Merkley (D-OR) and Lisa Murkowski (R-AK) found out sensors were already being removed, and how they got the Saving the OOI Act passed unanimously in under two days Craig McLean's read on why this kept happening, from the role of the Office of Management and Budget to the broader pattern of cuts to federal science A look back at a warning from marine ecologist Dr. Andrew Thaler about Project 2025's plans for NOAA, and how that warning is playing out in real time What happens next: the NSF's review process, and how you can track it and find out where your own senators stand Featured Voices Craig McLean spent over 40 years at NOAA, where he founded the Ocean Exploration Program and served as NOAA's Chief Scientist, including being reinstated after being removed from the role for defending scientific integrity. He is now a senior fellow at the Ocean Foundation. Senator Jeff Merkley (D-OR) and Senator Lisa Murkowski (R-AK) led the bipartisan push for the Saving the OOI Act, featured here via Senate floor remarks. Dr. Andrew Thaler, marine ecologist and conservation technologist, returns in spirit from a past episode where he broke down Project 2025's plans to dismantle NOAA. Jack Barth, oceanography professor at Oregon State University, provided background on the Coastal Endurance Array via KATU News. The Bill The Saving the OOI Act passed the Senate unanimously, pausing NSF's decommissioning of the Ocean Observatories Initiative pending a full review with stakeholder input. It was led by Senators Merkley and Murkowski and cosponsored by Senators Dan Sullivan (R-AK), Maria Cantwell (D-WA), Ron Wyden (D-OR), Jack Reed (D-RI), Tammy Baldwin (D-WI), Sheldon Whitehouse (D-RI), Patty Murray (D-WA), Elizabeth Warren (D-MA), Edward J. Markey (D-MA), and Chris Van Hollen (D-MD). Resources & Links Saving the OOI Act, full text and cosponsor list: Congress.gov NSF Ocean Observatories Initiative updates: oceanobservatories.org Senator Merkley's press release on the Saving the OOI Act: merkley.senate.gov "Scientists warn Oregon could lose critical ocean data under federal cuts," KATU News Take Action If your senator is one of the twelve who championed or cosponsored the Saving the OOI Act, send them a thank you. If they didn't, let them know this issue matters to you. Watch for the NSF's Dear Colleague Letter and expert panel process, your chance to weigh in on what happens to OOI long-term.

Berry Brilliant: Swallowable Sensor Brings Body Temperature Tracking to the Core.  Soundwave Sips: Sonic Science Shakes Up Espresso.  Face-First Future: Smart Specs, Seeing and Speaking with AI.  Seeing Smarter: Sensor Sight Sharpening Self-Driving Safety.  Peak Performance: Škoda's Premium-Priced Peaq Pushes EV Ambitions.  Flight Fun: Browser-Based Booming for Google Earth.  Radio Rhythms or Robo Riffs? The AI Music Airplay Argument.  Virtual Validation: Why China's Youth Are Finding Family Through Faux Parents.  Cancer-Catching Code: AI Accelerates Earlier Lung Diagnoses. 

In this reflection I explore two friction points related to confidence: with the self and with others. Supporting themes: Communication and group dynamics; Highly sensitive people and sensitivity; Tonality and subtle energy shifts as data points; Being a mastermind; Strategizing and problem solving; Giftedness and polymathy; Production equity (or not); Silence as a weaponized vacuum; Writing and typewriters. Topology: INTJ8; Sensors

Cattle producers are embracing emerging technologies to better manage cattle. Precision Livestock Management Specialist Yijie Xiong and Extension Range Management Specialist Mitch Stephenson discuss how GPS sensors are changing the way cattle are raised.

The Cycling Tech Brief: the cycling tech that actually matters this week — and whether to update, wait, or ignore.Wahoo ELEMNT V3 firmware WG77-302533 (June 16) adds live CORE, FLOWBIO, hDrop, and Tymewear biometric data fields — Monitor: the firmware itself is stable and worth updating, but hold off on buying the sensors until independent accuracy testing accumulates on actual Wahoo hardware in field conditions.Strava v467.0.0 drops hiking-first overhaul: offline nav, Apple Watch route-following, off-route alerts now live — Update now—subscriber or not, there is something here for you; subscribers should enable offline routes and Apple Watch navigation before the next trail day.Strava paywall API access at $11.99/month effective June 1, 2026—developer ecosystem fragmenting as IPO approaches — Monitor: as a rider, check that your favourite third-party Strava integrations still work after June 30—some free tools may shut down rather than absorb the developer fee.COROS watches bricking days-to-weeks after mid-May 2026 firmware—company confirms free replacements for affected devices — Monitor: if your COROS watch dies after the May update, contact support immediately for a free replacement—COROS has confirmed this policy; do not attempt DIY fixes.Wahoo ELEMNT ROAM V3 arrives with touchscreen, full-colour display, and new sensor platform—but upgrade value depends on generation — Monitor: ROAM V3 is now the more compelling platform given new sensor breadth, but wait for the biometric sensor ecosystem to prove out in field conditions before treating it as a reason to upgrade from a functioning V2.Daily cycling intelligence from SEMIPRO CYCLING, produced with AI-assisted research, scripting, and synthetic voice.

Understanding the relationship between an object's center of mass and its geometric center is key to predicting its movement.

What happens when one of the world's most important ocean monitoring systems is nearly shut down?   The Ocean Observatories Initiative (OOI) collects critical data on ocean temperatures, oxygen levels, currents, marine ecosystems, and climate change. Earlier this year, parts of the program faced significant cuts, raising concerns among scientists, policymakers, and ocean advocates. In this episode, we explore why researchers fought so hard to save the OOI, how the National Academies challenged the justification for the cuts, and why long-term ocean observations are essential for understanding climate change, marine ecosystems, and the future of ocean conservation. If we stop watching the ocean, what might we miss? Support Independent Podcasts: https://www.speakupforblue.com/patreon Need help with your ocean non-profit, company, or project? Get the help you need with Pisces Oceans Inc.: https://www.piscesoceans.ca Connect with Speak Up For Blue Website: https://bit.ly/3fOF3Wf Instagram: https://bit.ly/3rIaJSG TikTok: https://www.tiktok.com/@speakupforblue Twitter: https://bit.ly/3rHZxpc YouTube: www.speakupforblue.com/youtube  

Learn more about Refrigeration Mentor Customized Technical Training Programs at www.refrigerationmentor.com/courses Join the Refrigeration Mentor Hub here In this episode, I'm outlining five things refrigeration techs need to check before replacing a compressor to avoid an unnecessessary change out. Between 30-40% of swapped compressors are found to have no real issue, and these checks will help technicians uncover root-cause issues and potentially avoid costly and time-consuming work that might not be needed. This episode details the five checks: oil level and oil management, compressor superheat, electrical health, operating conditions, and controller/sensor accuracy. We also cover key readings and how to better understand failure modes and prevent repeat failures. In this episode, we discuss: (00:48) How to Avoid Replacing Good Compressors (03:16) Check 1: Oil Management (04:27) Check 2: Compressor Superheat (06:13) Check 3: Electrical Health (07:14) Check 4: Operating Conditions (08:19) Check 5: Controllers and Sensors (09:56) Inspecting a Failed Compressor (12:14) Documentation and Preventing Repeated Failures Helpful Links & Resources: FREE GUIDE: System and Compressor Troubleshooting Guide Episode 115: Understanding Compressors: What You Need To Know Episode 329. The Ins & Outs of Compressors Episode 388. Step-By-Step Compressor Change Out (Service Call Recap) with Andrew Freeburg

The Ship Report, Wednesday, June 17, 2026Today I'll share a story that's a follow-up to Monday's program on ocean sensors. It's about how some US senators are now responding to the news that National Science Foundation ocean sensors are being removed from our waters off Newport and Grays Harbor.And I'll share the results of an afternoon of research, in my attempt to answer a listener question: is there is fraud in NOAA's ocean monitoring program?

A new fire detection system in the Far North has seen see 250 solar-powered sensors installed across the Waitangi Endowment Forest.

The Ship Report: Monday, June 15, 2026Today we'll talk about the removal of National Science Foundation Pacific ocean data sensors off the coast of Oregon and Washington this week, a move scientists say will cripple their ability to know what's happening in the ocean, as a record breaking El Nino is expected to hit the region this summer.

What if airports had self-driving mobility pods that could safely navigate through crowds, just like something out of The Jetsons? Or the Pixar movie Wall-E?In this episode, John Koetsier sits down with Matthew Anderson, CEO of A&K Robotics, to explore the future of autonomous mobility. A&K Robotics is building AI-powered self-driving pods designed to help people navigate airports independently without relying on wheelchairs or staff assistance.But the real breakthrough isn't just autonomy. It's crowd navigation. Matthew explains why navigating dense, unpredictable crowds is one of the hardest problems in robotics, and how A&K's “crowd-centric AI” could become foundational technology for airports, stadiums, smart cities, conferences, and even humanoid robots in the future.They also discuss:* Why airports are the perfect proving ground for robotics* The AI and sensor stack powering autonomous mobility* Directional sound systems inspired by The Sphere in Las Vegas* Scaling robotics startups from prototype to deployment* Raising an $8M Series A round* The personal story that inspired Matthew to build the company* Why the future of robotics depends on moving safely through human environmentsGuest:Matthew Anderson — CEO, A&K RoboticsCompany: A&K RoboticsIf you enjoy conversations about AI, robotics, startups, and the future of technology, subscribe for more interviews with founders and innovators shaping what's next.Subscribe here:https://techfirst.substack.com00:00 – Intro00:30 – Meet A&K Robotics and the Vision for Autonomous Airport Mobility01:20 – Why Crowd Navigation AI Is the Hardest Problem in Robotics02:40 – Navigating Dense Airport Crowds and Passenger Flow04:05 – Directional Sound and Designing a Better Airport Experience05:50 – Building an “iPhone Experience” for Mobility Robots06:30 – Sensors, LIDAR, and Operating Without GPS07:20 – Fleet Management and Autonomous Operations in Airports08:00 – Mapping Airports and Optimizing Routes Through Crowds09:00 – Scaling the Business and Solving Systems Integration10:00 – Charging, Docking Stations, and the Future Airport Network10:45 – Raising an $8 Million Series A Round11:20 – Customers: Vancouver International Airport and Aena12:10 – Building a Polished Robotics Platform on Seed Funding12:50 – Matthew Anderson's Background in Robotics and Drones14:00 – The Bigger Vision: Crowd Navigation for All Robots14:40 – The Personal Story Behind the Company Mission15:40 – Licensing Opportunities and the $5 Billion Airport Mobility Market16:45 – Hiring, Scaling the Team, and Expanding Production18:00 – Growing Up Hacking Robots and the AC/DC Story19:10 – Why Building Robots Is Fun — and Why Accounting Wasn't20:40 – Final Thoughts and the Future of Autonomous Mobility

Ouster ($OUST) just reported $49M in Q1 2026 revenue — up 49% year-over-year — and crossed the 40% gross margin threshold as it shifts toward a fabless model. But the bigger story is product: the new REV8 LiDAR family and L4 Max chip now integrate native color sensing directly into the sensor, developed in partnership with Fujifilm.In this episode, Nick breaks down what that means for physical AI — autonomous vehicles, robotics, and industrial automation — where today's systems rely on costly, complex sensor fusion setups combining LiDAR with CMOS image sensors. Color LiDAR could simplify that stack significantly.We also cover Q2 2026 guidance, the path toward breakeven, and why OUST remains a small bet in the Semi Insider portfolio — not a full position. This is still a prove-it story: the company operates at a loss and continues issuing shares to fund operations.Topics covered:REV8 family and L4 Max chip breakdownHow color LiDAR changes the physical AI sensor stackWhy OUST is sized as a small bet and what would change thatQ2 2026 guidance and the road to profitabilityFor deeper research and portfolio updates, visit us at chipstockinvestor.com.Chip Stock Investor covers semiconductor stocks and the chips powering AI, autonomy, and the physical world. Subscribe for weekly analysis and research updates.This content is for informational and educational purposes only and does not constitute financial advice. Always do your own research before making any investment decisions.

Evan's Segway: https://amzn.to/49stgck Evan's Walker's: https://amzn.to/4wTxZ0O   Use code TURFNERDS for 5% off orders $600 and up at Magna-Matic! Use discount code for TURFNERDS10 for 10% off at Strauss, valid starting April 29 through May 31 Use code NERDS to save 10% on Spencer Products!   In this Turf Nerds Podcast episode, Evan and Uncle Greg tackle listener questions on snow removal pricing, HOA contracts, and landing commercial accounts + real numbers on what you should be charging per push. They also break down the Toro Multiforce O2 sensor saga, why cottonwood season is destroying your air filter, and say a prayer for lawn care friend Andy Wilson (of The Lawn Hustle! Podcast). Equal parts practical and unfiltered, just how you like it.   Tap Here for Turf Nerds Merch!⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Look! We Have A Website!⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ Don't forget to check out ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Green Frog Web Design⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ and tell them the Turf Nerds sent you. Or Greg will scalp your lawn! Use promo code TURFNERDS for 50% off Equip Expo 2026 registration! Shoot us an email! Evan@TurfNerdsPod.com ⁠⁠Instagram⁠⁠ ⁠⁠Facebook⁠⁠ ⁠⁠TikTok⁠⁠ ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Subscribe on YouTube: ⁠⁠⁠https://www.youtube.com/@TurfNerdsPodcast?sub_confirmation=1⁠⁠⁠ ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠#LawnCare #LawnMaintenance #Mowing #MowingGrass #LawnCareBusiness #Toro #ToroMultiforce #CubCadet #BibleStudy #Bible #Christian #Business #Entrepreneurship #Comedy #2024 #Marketing #Advertising #TipsAndTricks #Tips #Success #Yakta #YaktaMowers #YaktaOutdoor #Spring #SpringRush #FYP #Mower #NewMower #UsedMower #RouteDensity #EquipExpo #EquipExpo2024 #Echo #Stihl #RedMax #Shindaiwa #StringTrimmer #WeedWhip #GreenFrogWebDesign #WebDesign #EzraMcCarthy #Aerator #Aeration #ZAerate #Bobcat #BobcatMowers #Husqvarna #HusqvarnaGroup #HYGREENTOOL #GOMOW #ThunderLightingSupply #ChristmasLights #Christmas #Trump #DonaldTrump #PresidentTrump #ElectionDay #EZDumper #DumpInsert #StempkyNursery #Mulch #MulchInstallation #TurfNerds #Newsmax #NewsmaxTV #CarlHigbie #CharlieKirk  

Learn more about Refrigeration Mentor Customized Technical Training Programs at www.refrigerationmentor.com/courses Join the Refrigeration Mentor Hub here In this milestone 400th episode, we're joined by Andre Patenaude of Copeland to explain 8 critical sensors on CO2 refrigeration systems (video link to this seminar below). Andre breaks down the most critical CO2 refrigeration sensors found in supermarket systems, common failure modes, troubleshooting strategies, and how to prevent catastrophic system shutdowns, product loss, and compressor damage in transcritical CO2 systems. He also explains how technicians, service managers, and contractors can improve reliability through proactive monitoring, redundancy strategies, trend analysis, and smarter control logic. Thank you for listening, following and helping us reach 400 episodes! Check out all of our past episodes and follow the Refrigeration Mentor Podcast on Apple, Spotify and YouTube here. In this episode, we cover: (02:27) Why Critical Sensors Matter in CO2 Refrigeration (08:54) Booster System  (13:19) Gas Cooler Outlet Temp (23:31) Mitigation Strategies (31:24) Low Ambient Bypass and T2 Sensor (37:30) Drop Leg Pressure Transducer (41:14) Fan Modulation Chain Reaction (43:01) P1 Transducer Failover Options (45:46) Proactive P1 Calibration Checks (47:29) P2 Flash Tank Pressure Basics (51:38) Suction Group Transducer Backup (53:54) Oil Level Sensors (57:09) Adiabatic Pre Cool Sensor 7A (01:01:46) Ambient Sensor 7B Water Control (01:10:27) Dry Gas Cooler TD Sensor Helpful Links & Resources: VIDEO: Watch this seminar on the Refrigeration Mentor YouTube Channel GUIDE: Critical Sensors for CO2 Transcritical Systems Guidance (NASRC) Copeland Website  Andre Patenaude on LinkedIn

Poetic Pictures: Camera Creates Captured Couplets.  Parcel Panic: Digital Arrests and Deceptive Delivery Drama.  Robo-Revival: T-Shirt Tech Taking Tailoring to the Top.  Wolf Warning: Japan's Bear-Battling Bot Beasts Bite Back.  Hedgehog Horizons: Satellites, Sensors and Saving Britain's Spiky Survivors.  Tappy Tones: Boox Brings Bold Bluetooth Book Browsing.  Hunting Hacks or High-Tech Hype? When Gadgets Game the Great Outdoors.  Discordant Decisions: AI's Job-Judging Jumble.  Sense and Surveillance: When Smart Security Cameras Go Spectacularly Silly. 

The same highly sophisticated seismic tools and methods used to measure the severity of earthquakes show promise in determining the impact tillage has on soil moisture and water retention. University of Washington scientists say these research results indicate tillage and compaction disrupt the intricate capillary networks within the soil in ways that affect how it soaks up water.

If you enjoy this episode, we're sure you will enjoy more content like this on The Occult Rejects.  In fact, we have curated playlists on occult topics like grimoires, esoteric concepts and phenomena, occult history, analyzing true crime and cults with an occult lens, Para politics, and occultism in music. Whether you enjoy consuming your content visually or via audio, we've got you covered - and it will always be provided free of charge.  So, if you enjoy what we do and want to support our work of providing accessible, free content on various platforms, please consider making a donation to the links provided below.  Thank you and enjoy the episode!Links For The Occult Rejectshttps://linktr.ee/theoccultrejectsOccult Research Institutehttps://www.occultresearchinstitute.org/Substackhttps://substack.com/@theoccultrejects?r=7auau0&utm_campaign=profile&utm_medium=profile-pageCash Apphttps://cash.app/$theoccultrejectsVenmo@TheOccultRejectsBuy Me A Coffeebuymeacoffee.com/TheOccultRejectsPatreonhttps://www.patreon.com/TheOccultRejectsEPISODE 1 BIBLIOGRAPHYThe Building That Changes YouAckerman, Joshua M., Christopher C. Nocera, and John A. Bargh. “Incidental Haptic Sensations Influence Social Judgments and Decisions.” Science 328, no. 5986 (2010): 1712–1715. Key use: Haptics, touch, weight, texture, hardness, and the idea that physical sensation can influence judgment and social interpretation. This supports the tactile layer of the episode: heavy doors, cold stone, worn rails, kneelers, relic cases, and sacred matter as meaningful contact.Higuera-Trujillo, Juan Luis, Carmen Llinares, and Eduardo Macagno. “The Cognitive-Emotional Design and Study of Architectural Space: A Scoping Review of Neuroarchitecture and Its Precursor Approaches.” Sensors 21, no. 6 (2021): 2193. Key use: Neuroarchitecture, emotional response to built environments, and the idea that architecture can be studied as a cognitive-emotional stimulus rather than only as art or style.Kilde, Jeanne Halgren. Sacred Power, Sacred Space: An Introduction to Christian Architecture and Worship. Oxford University Press, 2008. Key use: Major backbone source for Christian architecture as a system of worship, power, spatial order, and embodied religious experience. Oxford's description emphasizes Kilde's argument that church buildings represent and reify different forms of power, especially divine power.Morgan, David. The Sacred Gaze: Religious Visual Culture in Theory and Practice. University of California Press, 2005. Key use: Religious seeing, visual culture, sacred images, and the idea that vision is an active religious practice that can invest images, persons, times, and places with spiritual meaning.Taves, Ann. Religious Experience Reconsidered: A Building-Block Approach to the Study of Religion and Other Special Things. Princeton University Press, 2009. Key use: Helps frame religious experience without reducing it to one fixed category. Useful for the episode's approach to how experiences become interpreted, named, and treated as religious or sacred.Clark, Andy. Surfing Uncertainty: Prediction, Action, and the Embodied Mind. Oxford University Press, 2016. Key use: Predictive processing, active inference, and the idea that perception is not passive recording but active prediction and model-building. This supports the “brain does not enter a church like a camera” argument.Krueger, Joel. “Extended Mind and Religious Cognition.” 2016. Key use: Extended and embodied cognition applied to religious practice, ritual objects, and environments. Useful for arguing that worship is not only inside the head but supported by bodies, tools, spaces, and shared action.Oxford Academic. “Embodied Cognition in Ecclesial Practices.” In Oxford Studies in Analytic Theology, 2023. Key use: Christian practices, embodied cognition, Eucharistic action, and religious material culture as cognitively significant rather than merely symbolic.Piff, Paul K., Pia Dietze, Matthew Feinberg, Daniel M. Stancato, and Dacher Keltner. “Awe, the Small Self, and Prosocial Behavior.” Journal of Personality and Social Psychology 108, no. 6 (2015): 883–899. Key use: Awe, vastness, the “small self,” and the psychological effects of encountering something perceived as larger than the ordinary self. This supports the cathedral-scale and sacred-vastness argument.Tarr, Bronwyn, Jacques Launay, and Robin I. M. Dunbar. “Music and Social Bonding: ‘Self-Other' Merging and Neurohormonal Mechanisms.” Frontiers in Psychology 5 (2014): 1096. Key use: Music, synchrony, social bonding, rhythmic action, and group cohesion. This supports the sections on chant, group singing, ritual synchrony, and bodies acting together in sacred space.Ittyerah, Miriam. “Memory for Curvature of Objects: Haptic Touch vs. Vision.” 2007. Key use: Haptic memory, touch-based object recognition, and the idea that touch can produce durable memory traces. Useful for worn rails, thresholds, beads, icons, relic cases, and repeated sacred contact.Lange, Lisa S., et al. “Tactile Memory Impairments in Younger and Older Adults.” Scientific Reports, 2024. Key use: Modern tactile-memory framing; useful for the claim that tactile experience is remembered and retrieved as part of embodied life.Freedberg, David. The Power of Images: Studies in the History and Theory of Response. University of Chicago Press, 1989. Key use: Image response, embodied reaction to sacred or charged images, and why religious images can provoke devotion, fear, destruction, reverence, or bodily response.Plate, S. Brent. A History of Religion in 5½ Objects: Bringing the Spiritual to Its Senses. Beacon Press, 2014. Key use: Material religion, objects, sensory experience, and the idea that religion is encountered through things, not only beliefs.Meyer, Birgit. Mediation and the Genesis of Presence: Toward a Material Approach to Religion. Key use: Material religion, mediation, presence, and how religious traditions use media, objects, images, sounds, and spaces to make the sacred present.Pallasmaa, Juhani. The Eyes of the Skin: Architecture and the Senses. Key use: Architecture as a multisensory experience, especially touch, materiality, atmosphere, and the limits of treating architecture as only visual.Mallgrave, Harry Francis. The Architect's Brain: Neuroscience, Creativity, and Architecture. Wiley-Blackwell, 2010. Key use: Architecture and neuroscience, built form, emotion, perception, and embodied response to space.Robinson, Sarah, and Juhani Pallasmaa, eds. Mind in Architecture: Neuroscience, Embodiment, and the Future of Design. MIT Press, 2015. Key use: Embodiment, neuroscience, architectural perception, and how built environments shape lived experience.Eliade, Mircea. The Sacred and the Profane: The Nature of Religion. Key use: Sacred space, threshold, center, axis mundi, and the distinction between ordinary space and holy space. This becomes more important in Episode 2, but it also supports Episode 1's general sacred-space framework.van Gennep, Arnold. The Rites of Passage. Key use: Separation, threshold, and incorporation. Useful for the threshold logic that runs through the whole series.Turner, Victor. The Ritual Process: Structure and Anti-Structure. Key use: Liminality, transition, communitas, and the ritual power of in-between states.Tuan, Yi-Fu. Space and Place: The Perspective of Experience. Key use: Lived place, memory, experience, and the difference between abstract space and meaningful place.Smith, Jonathan Z. To Take Place: Toward Theory in Ritual. Key use: Ritual as place-making; sacred places are produced through repeated action, interpretation, and return.Morgan, David. Visual Piety: A History and Theory of Popular Religious Images. Key use: Popular religious images, devotional seeing, sacred practice, and how visual material becomes part of lived religion.Kieckhefer, Richard. Theology in Stone: Church Architecture from Byzantium to Berkeley. Key use: Church architecture as theology in built form, useful as a broad Christian architectural bridge source.Also want to remind people about the website, if you're into reading we have tons of information by multiple contributors, and we got t-shirts up on the site if you're interested. Fun fact, the art is all based on the eyeball. A

Do we want to walk quietly into the slaughterhouse, or are we going to put a halt to this planned extinction of of mankind? Their intentions are clear albeit masked in symbolism and deception. What happens when there's no more gas being produced? No food coming, none that isn't poisonous? Do we really want to see it get that far, when the chaos is overwhelming any efforts to maintain civility? Are we going to continue to let the inactive masses of the unaware stifle our message, while demons chart our course to destruction?Today as always, I will be the laser that cuts through the bullsht we get thrown at us by these sick little monkeys with pe'ots.Special announcements, Some interesting findings and more dots connected on the map to digital hell. Must see CRUMBLE TV.***Due to the recent events involving the loss of the FTJMedia platform, and how it happened, adaptations to routine have to occur. You can still use your wallet and have access to limited site features.https://GivesendGo.com/BaalBustershttps://buymeacoffee.com/BaalBustershttps://paypal.me/BaalBustersTo join the Patreon, use this link:https://www.patreon.com/c/KristosCastTo Join the Stream:619-431-0334https://vdo.ninja/?room=4roomGo to My site:https://SemperFryLLC.comJoin Dr. Glidden's Membership site here:https://leavebigpharmabehind.com/?via=pgndhealth⁠Code: baalbusters for 25% OFFMake Dr. Glidden Your DoctorUse Code BB5 here for your 90 Essential Nutrients:https://www.azurestandard.com/shop/brand/azurewell/2326The Azure Whole Food Essential Nutrients are 1. Whole Food Multivitamin, 2. Alaskan Cod Liver Oil, 3. Fulvic-Humic Energy Blend, 4. IP6 Supreme. I also recommend adding the Core Copper.Use code BB5 for your discount.Twitter Account: https://x.com/KristosCastBecome a supporter of this podcast: https://www.spreaker.com/podcast/ba-al-busters-broadcast--5100262/support.

This month, a genetic sensor to self-destruct cancer cells, what fish with a gene mutation are revealing about brain blood vessel disease, evidence that hallucinogens like psilocybin put brain cells into a more plastic state to loosen the grip of depression, a new technique to spot the population immunity loopholes that flu might exploit, and why crabs walk sideways... Get the references and the transcripts for this programme from the Naked Scientists website

Dan, Manny, & Billy welcome back Nostalgia Test Podcast all-star Meghan Nolan to put the 1996 Pauly Shore Stephen Baldwin “comedy” Bio-Dome to the ultimate test—THE NOSTALGIA TEST!   “Dude, could you think of a worse person to get high with than Pauly Shore? Like, there is literally no one that I would rather less get high with than Pauly Shore. 'Cause I would be like, "Dude, shut the fuck up. Shut the fuck up." Could you imagine that, dude?” -Billy D'Elia   Dear Nostalgia Testers, this is the episode that almost broke the podcast. The guys decided to put their fate in The Wheel of Pauly Shore and was given the task of putting Bio-Dome to the test, and boy was it a huge... well. This movie defines the major issues with the 90s and why Manny talks about 80s cheese vs 90s trash. This movie seems like it was written by AI but was instead written by three people. That's right?! It took three people to write these lines that Pauly Shore and Stephen Baldwin literally fart out for 90 minutes. This movie sets the bar lower than low for men and is an insult to any and all men. The so-called jokes use sexual assault as a punchline, there's a Nazi salute that happens as all these morons go into the bio-dome, homophobia, and more badly developed body humor and horror than a David Cronenberg film. Dan, Manny, Billy, and Meghan go through some deep self-reflection starting with shame, shame that they all saw this movie, some more than 5 times, denial that they thought it was ever good, anger that this movie was even made, and acceptance that this is why they do this podcast. Dan creates a Bio-Dome “Would You Rather” game, and let's just say someone would rather wear a diaper for a week than watch Bio-Dome. So, take something really strong to calm yourself down, gather all your Pauly Shore movies and adoration, light a huge dumpster fire, and join The Nostalgia Test Podcast as we attempt to erase this part of the 90s from existence. Email us (thenostalgiatest@gmail.com) your thoughts, opinions, & episode idea for The Wheel of Nostalgia! Suggest A Test & Be Our Guest! We're always looking for a fun new topic for The Nostalgia Test. Hit the link above, tell us what you'd like to see tested, and be our guest for that episode!   Approximate Rundown 00:00 Welcome Back Meghan Nolan 01:11 Brain Rot Title Sequence 02:16 First Time Watching Bio-Dome 05:08 Mall Theater Memories 07:16 Forced Into Bio-Dome 09:45 How Was This Made 11:38 Pauly Shore Career Context 13:22 Writers and Director Breakdown 15:22 No One to Root For 19:12 Gross-Out Humor and Bad Acting 26:43 Problematic Jokes and Garbage World 27:43 What Even Is the Bio-Dome 29:51 Breaking Into Bio-Dome 31:07 Kids React to the Chaos 32:24 Problematic Jokes and Nazis 32:44 Carrot Scene Confusion 34:44 Sudden Fame Makes No Sense 36:26 Cameos and Bad One Liners 37:20 Sensors and Alarm Logic 38:36 Real Bio-Dome Documentary 41:06 Yogurt Lines and Sexism 43:20 Baldwin Overacting Rant 46:20 Flashbacks and Dog Shaving 47:03 Whip-Its and SPAM Meltdown 50:50 Goofy Movie Nostalgia Detour 54:25 The Key Escape Plot Hole 56:40 Party Trash the Dome 58:54 Terrible Band Mystery 59:08 Bug Room Chaos 01:00:39 Cameos And Characters 01:01:42 Ending Makes No Sense 01:02:51 Would You Rather Gauntlet 01:12:51 Raw Eggs And Swing Life 01:16:23 Final Verdict Pop Culture Mistake 01:24:55 Wrap Up And Earth Day   Book The Nostalgia Test Podcast Bring The Nostalgia Test Podcast's high energy fun and comedy on your podcast, to host your themed parties & special events!  The Nostalgia Test Podcast will create an unforgettable Nostalgic experience for any occasion because we are the party! We bring it 100% of the time! Email us at thenostalgiatest@gmail.com  or fill out the form at this link.   LET'S GET NOSTALGIC!       Keep up with all things The Nostalgia Test Podcast on Instagram | Substack | Discord | TikTok | Bluesky | YouTube | Facebook   The intro and outro music ('Neon Attack 80s') is by Emanmusic. The Lithology Brewing ad music ("Red, White, Black, & Blue") is by PEG and the Rejected

In this episode of The Moos Room, Brad discusses spring pasture challenges in western Minnesota, including dry conditions, temperature swings, and slowed grass growth. With summer heat on the horizon, the focus shifts to heat stress in dairy cows and how precision technologies, especially internal bolus sensors, can help farmers identify problems earlier.Brad shares observations from cows monitored with Smaxtec boluses, including rumination, internal body temperature, and water intake data. He also reviews research from the University of Minnesota herd showing that rumination may start dropping at lower temperature-humidity index levels than traditional industry thresholds suggest. Conventional cows showed rumination declines around a THI of 64, while pasture-based organic cows showed declines closer to 58.The episode highlights why waiting for milk production losses may be too late when managing heat stress. Instead, rumination, body temperature, water intake, shade, cooling systems, and feeding strategies can all play a role in protecting cow comfort and performance before visible signs of heat stress appear.Questions, comments, scathing rebuttals? -> themoosroom@umn.edu or call 612-624-3610 and leave us a message!Linkedin -> The Moos RoomTwitter -> @UMNmoosroom and @UMNFarmSafetyFacebook -> @UMNDairyYouTube -> UMN Beef and Dairy and UMN Farm Safety and HealthInstagram -> @UMNWCROCDairyExtension WebsiteAgriAmerica Podcast Directory 

What if the next big wave of AI isn't about robots doing your chores but about robots that understand you?In this episode, we sit down with Colin Angle, co-founder of iRobot and the creator of the Roomba, to explore his bold new venture: Familiar Machines and Magic. After putting over 50 million robots into homes, Angle is now betting on something radically different: a quadruped AI companion designed not for work, but for connection.This isn't a humanoid. It's not a vacuum. It's something entirely new.Powered by on-device multimodal AI, this “familiar” can follow you around your home, learn your routines, encourage healthier habits, and even develop a kind of relationship with you, all while keeping your data private.We dive into:* Why the humanoid robot race might be overhyped* The massive untapped “emotional AI” market* How this robot learns, adapts, and interacts like a pet* Privacy-first AI design (no cloud streaming)* Why form factor matters more than you think* The future of robots in everyday lifeColin also shares why now is the perfect moment for physical AI—and how advances in reinforcement learning and edge computing are making this possible.If you thought AI robots were just about automation, this conversation will change your perspective.⸻

We discuss 4 different type of semiconductor sensors. Highlightling at least 4 from each type and discuss what we think will be the next big thing. 

Daniel is joined by Nir Sever, Senior Director of Business Development at proteanTecs. Nir has over 30 years of experience in advanced VLSI engineering. Before joining proteanTecs, he served for 10 years as the COO of Tehuti Networks, a pioneer in high-speed networking semiconductors. Prior to that, he served for 9 years as Senior… Read More

In low gravity, fuel can cling to the side walls of a spacecraft's tank, making it hard to tell how much fuel is left.

Connected cars are no longer just vehicles — they are rolling networks of sensors, cameras, microphones, and constant data transmission. In this Cybersecurity Today Weekend Edition, David Shipley is joined by former CSIS intelligence officer Neil Bisson and cybersecurity expert Federico Simonetti to break down what that really means. They explain how modern vehicles: Continuously report location, behaviour, and system data to the cloud Contain dozens of interconnected computers controlling everything from steering to braking Can be vulnerable to man-in-the-middle attacks, remote access, and system compromise May expose drivers to surveillance — not just by companies, but potentially by nation states The conversation goes beyond theory. Real-world examples are discussed, including: Remote vehicle manipulation demonstrated by security researchers How infotainment systems can become entry points to critical controls Why some countries are already restricting certain vehicles from sensitive locations The panel also tackles the bigger issue: This is not just about one country or one manufacturer. Every connected vehicle expands the attack surface. And while solutions exist — from better authentication to architectural changes — the challenge is no longer technical. It's political, economic, and global. If you think your car is just transportation, this discussion may change your perspective. 00:00 Connected Cars: More Than Just Vehicles 01:20 Meet the Panel: Intelligence and Cybersecurity Perspectives 03:10 Every Car Is Now a Networked Computer 06:00 Surveillance Risks: Are Cars "Rolling Spy Vans"? 09:10 What Intelligence Agencies Can Do With Car Data 12:30 Sensors, GPS, Cameras — What Your Car Collects 16:20 Real Example: Tesla Camera Privacy Incident 19:00 Can Hackers Take Control of a Car? 22:30 Real-World Hacks: Jeep and Nissan Cases 26:40 The Regulatory Gap: No Enforced Cybersecurity Standards 30:10 Why Governments Are Struggling to Act 34:00 Cheap EVs vs National Security Risks 37:40 Can Software Fix the Problem? 41:20 Global Response: China, US, and Europe 45:10 Policy Ideas: Kill Switches, Car Bill of Rights 49:00 Prevention vs Detection in Cybersecurity 52:30 Are We Already Too Exposed? 55:10 Final Thoughts: Can Connected Cars Be Made Safe?

Lance R. Blyth, command historian of the North American Aerospace Defense Command (NORAD) and United States Northern Command (USNORTHCOM), joins School of War to discuss the evolution of North America's air defense. How has NORAD adapted to shifting threats over the decades? Are today's threats manageable? Are we in a new Cold War? And what can the command, with operations deep inside a Colorado mountain, teach us about defending the continent in an era of renewed great-power competition? Times: 02:04 History of NORAD 07:02 Threats of the 1950s 13:50 Sensors, effectors, and connectors 15:15 Semi-Automatic Ground Environment (SAGE) 19:45 SABRE travel system 21:14 Aerospace missile warning systems 22:07 Cheyenne Mountain Complex 24:13 NORAD in films 27:56 False missile launches 31:31 Adapting to new threats 34:23 New joint surveillance system 35:19 Importance of Canada 36:21 September 11 40:21 Operation Noble Eagle 43:00 Today's threats Follow along on Instagram, X @schoolofwarpod, and YouTube @SchoolofWarPodcast Find more at The Free Press.

From building Applied Intuition from YC-era autonomy tooling into a $15B physical AI company, Qasar Younis and Peter Ludwig have spent the last decade living through the full arc of autonomy: from simulation and data infrastructure for robotaxi companies, to operating systems for safety-critical machines, to deploying AI onto cars, trucks, mining equipment, construction vehicles, agriculture, defense systems, and driverless L4 trucks running in Japan today. They join us to explain why “physical AI” is not just LLMs on wheels, why the real bottleneck is no longer model intelligence but deployment onto constrained hardware, and why the future of autonomy may look less like one-off demos and more like Android for every moving machine.We discuss:* Applied Intuition's mission: building physical AI for a safer, more prosperous world, powering cars, trucks, construction and mining equipment, agriculture, defense, and other moving machines* Why physical AI is different from screen-based AI: learned systems can make mistakes in chat or coding, but safety-critical machines like driverless trucks, autonomous vehicles, and robots need much higher reliability* The evolution from autonomy tooling to a broad physical AI platform: starting with simulation and data infrastructure for robotaxi companies, then expanding into 30+ products across simulation, operating systems, autonomy, and AI models* Why tooling companies came back into fashion: Qasar on why developer tooling looked unfashionable in 2016, why Applied Intuition still bet on it, and how the AI boom made workflows and tools central again* The three core buckets of Applied Intuition's technology: simulation and RL infrastructure, true operating systems for vehicles and machines, and fundamental AI models for autonomy and world understanding* Why vehicles need a real AI operating system: real-time control, sensor streaming, latency, memory management, fail-safes, reliable updates, and why “bricking a car” is much worse than bricking an iPad* Physical machines as “phones before Android and iOS”: Peter explains why today's vehicle and machine software stack is fragmented across many operating systems, and why Applied Intuition wants to consolidate the platform layer* Coding agents inside Applied Intuition: Cursor, Claude Code, internal adoption leaderboards, and how AI tools are changing engineering workflows even in embedded systems and safety-critical software* Verification and validation for physical AI: why evals get harder as models improve, how end-to-end autonomy changes simulation requirements, and why neural simulation has to be fast and cheap enough to make RL practical* From deterministic tests to statistical safety: why autonomy validation is shifting from binary pass/fail requirements toward “how many nines” of reliability and mean time between failures* Cruise, Waymo, and public trust: Qasar and Peter discuss why autonomy failures are not just technical issues, how companies interact with regulators, and why Waymo is setting a high bar for the industry* Simulation vs. reality: why no simulator perfectly represents the real world, how sim-to-real validation works, and why real-world testing will never disappear* World models for physical AI: hydroplaning, construction equipment, visual cues, cause-and-effect learning, and where world models help versus where they are not enough* Onboard vs. offboard AI: why data-center models can be huge and slow, but onboard vehicle models need millisecond-level latency, low power, small size, and distillation-like efficiency* Why physical AI is not constrained by model intelligence alone: the hard part is deploying models onto real hardware, under safety, latency, power, cost, and reliability constraints* Legacy autonomy vs. intelligent autonomy: RTK GPS in mining and agriculture, why hand-coded path-following worked for decades, and why modern systems need perception and dynamic intelligence* Planning for physical systems: how “plan mode” applies to robotaxis, mining, defense, and multi-step physical tasks where actions change the state of the world* Why robotics demos are not production: the brittle last 1%, humanoid reliability, DARPA Grand Challenge-style prize policy, and the advanced engineering gap between research and deployment* Applied Intuition's hard-earned lessons: after nearly a decade, Peter says they can look at a robotics demo and predict the next 20 problems the company will hit* Qasar's advice to founders: constrain the commercial problem, avoid copying mature-company strategies too early, and remember that compounding technology only matters if you survive long enough to see it compound* Why 2014 YC advice may not apply in 2026: capital markets, AI company dynamics, and the difference between building in stealth with a deep network versus building as a new founder today* What Applied is hiring for: operating systems, autonomy, dev tooling, model performance, evals, safety-critical systems, hardware/software boundaries, and engineers with deep curiosity about how things workApplied Intuition:* YouTube: https://www.youtube.com/@AppliedIntuitionInc* X: https://x.com/AppliedInt* LinkedIn: https://www.linkedin.com/company/applied-intuition-incQasar Younis:* X: https://x.com/qasar* LinkedIn: https://www.linkedin.com/in/qasar/Peter Ludwig:* LinkedIn: https://www.linkedin.com/in/peterwludwig/Timestamps00:00:00 Introduction: Applied Intuition, Physical AI, and 10 Years of Building00:01:37 Physical AI vs. Screen AI: Why Safety-Critical Changes Everything00:02:51 The Origin Story: Tooling, YC, and the Scale AI Comparison00:05:41 The Three Buckets: Simulation, Operating Systems, and Autonomy Models00:11:10 Hardware, Sensors, and the LiDAR Question00:14:26 The Operating System Layer: Why Vehicles Are Like Pre-Android Phones00:19:13 Customers, Licensing, and the Better-Together Stack00:21:19 AI Coding Adoption: Cursor, Claude Code, and the Bimodal Engineer00:26:41 Verifiable Rewards, Evals, and Neural Simulation00:31:04 Statistical Validation, Regulators, and the Cruise Lesson00:40:25 World Models, Hydroplaning, and Cause-Effect Learning00:43:34 Onboard vs. Offboard: Latency, Embedded ML, and Distillation00:50:57 Plan Mode for Physical Systems and Next-Token Prediction Universally00:53:04 Productionization: The 20 Problems Every Robotics Demo Will Hit00:58:00 Founder Advice: Constraints, Compounding Tech, and Mature-Company Mimicry01:05:41 Hiring Philosophy: Hardware/Software Boundary and Engineering Mindset01:08:50 General Motors Institute, Education, and the Curiosity MindsetTranscriptIntroduction: Applied Intuition, Physical AI, and 10 Years of BuildingAlessio [00:00:00]: Hey everyone, welcome to the Latent Space Podcast. This is Alessio, founder of Kernel Labs, and I'm joined by Swyx, editor of Latent Space.Swyx [00:00:10]: And today we're very honored to have the founders of Applied Intuition, Qasar and Peter. Welcome.Qasar [00:00:17]: You guys really know how to turn it on to podcast mode. That was, you guys are real pros at this.Qasar [00:00:23]: They were just joking around right before this, and then they flipped it pretty quick.Alessio [00:00:29]: Oh, yeah, it's good to have you guys. Maybe you just wanna introduce yourself so people know the voice on the mic and they'll know what they're hearing.Peter [00:00:33]: Oh, sure. Yeah, I'm Peter Ludwig. I'm the co-founder and CTO of Applied Intuition.Qasar [00:00:38]: And my name is Qasar Younis. I am the CEO and co-founder with Peter.Alessio [00:00:42]: Nice. Can you guys give the high-level overview of what Applied Intuition is? And I was reading through some of the Congress files, when you went out there, Peter, and eighteen of the top twenty global non-Chinese automakers, you two guys, you have customers in agriculture, defense, construction. I think most people have heard of Applied Intuition tied to YC when it was first started, and then you were kinda in stealth for a long time, so maybe just give people the high-level overview of what it is today, and then we'll dive into the different pieces.Peter [00:01:10]: Yeah. So at Applied Intuition, our mission is to build physical AI for a safer, more prosperous world. And so we work on physical AI for all different types of moving systems, everything from cars to trucks to construction and mining equipment, to defense technologies. And we're a true technology company, so we build and sell the technology, and we sell it to the companies that make the machines. We sell it to the government, really anyone that wants to buy a technology to make machines smart.Physical AI vs. Screen AI: Why Safety-Critical Changes EverythingQasar [00:01:38]: Yeah. And I think in the broader AI landscape, a lot of the focus, rightfully so in the last, three years has been on large language models, and so everything fits in a screen. Like, whether it's code complete products or things like that. And what's different about us is we're deploying intelligence onto a lot of things that don't have screens. they're physical machines. There are sometimes screens within the cabin or for example of a car or a truck or something like that, but most of the value we provide is putting intelligence that is in safety critical environments. So that those two words are really important because learn systems can make mistakes if you're asking for, like, some, so something like, “Tell me about these podcast hostsQasar [00:02:28]: that I'm about to go meet.” But you can't do that obviously when you run, like, as an example, we run driverless trucks in Japan right now, as we speak. We can't have errors. Those are L4 trucks. Yeah.Alessio [00:02:40]: Yeah. Was that always the mission? I remember initially, I think people put you and Scale AI very similarly for some things about being kinda like on the data infrastructure side of things. What was the evolution of the company?The Origin Story: Tooling, YC, and the Scale AI ComparisonPeter [00:02:51]: Well, from the very beginning, we always wanted to, really be a technology company that helped generally push forward the industrial sector. And so we started off working in autonomy. Our very first customers were robotaxi companies. And we started off doing a lot of work in simulation and data infrastructure. And then over the years, we've expanded our portfolios. Now we have, over thirty products, and it's a pretty broad technology play within the landscape of physical AI.Qasar [00:03:19]: Yeah, I think the Scale reason is because we're all YC Universe companies. But it was a very different company. Scale, was, is more of a services company, data labeling company fundamentally. We started and still are, do a lot of tooling. So like, you think developer tooling is now in vogue again, thanks to the AI boom. But honestly, ten years ago, it was out of vogue. It w Like, doing a tooling company in 2016, 2017 was not, like, the thing to do because, I don't know if you remember, the VCs generally, their views was that toolings are They're just workflows, and workflows ultimately are not really interesting. And we've gone and come, full circle with that. But when we started the company, our kind of it's kinda like in the periphery of what the company wants to be. It was like, from our earliest days, like, we wanna deploy software on physical machines, like on cars and on trucks and things like that. And obviously, we didn't know that the transformer boom was gonna happen. We didn't know that autonomy systems would become end-to-end. Those things we didn't know. And why that's important when autonomy systems become end-to-end, it is just now those models can be generalized to, multiple form factors. And so back nine, ten years ago, tooling was a great way, and still is a great way to, build the technology and sell technology to our end customers, a lot of them who wanna build this stuff themselves. And so we just offer like a spectrum of solutions from you can just use like one part of a development suite of tools all the way to buying the full thing. The way to think about the company, or at least the way we think about the company is, as Peter said, a technology provider. It's kinda like, what NVIDIA does or what an AMD, but we just don't do chips.Qasar [00:05:06]: We don't do silicon. But we're a technology provider fundamentally. And I think even, we used to joke when we started the company, like, we're not the guys to build, like, Instagram. Like that was just towards That's not our That's just not us in a most fundamental way. IAlessio [00:05:20]: You have thoughts.Qasar [00:05:21]: Yes.Qasar [00:05:22]: Well, it's, it's I mean, I think it's just like what And I mean, we worked on Maps and stuff, Google Maps. Consumer products are extremely difficult for a lot of different reasons. It just, I think doesn't scratch the itch. I think we're like Michigan guys who are kind of more of that traditional engineering kind of a realm, or lineage. we used to jokeThe Three Buckets: Simulation, Operating Systems, and Autonomy ModelsPeter [00:05:41]: I gotta say, though, what was clear ten years ago was that there was so much more that was possible with software and AI in vehiclesPeter [00:05:47]: and that was generally the space that we started in ten years ago.Peter [00:05:51]: And the precise path that we've taken over the years, I think we've been strategic, and we've adjusted to make sure that we're actually building stuff that's valuable to the market. And like, the technology has changed so much. Like our own technology stack has completely changed, I would say, roughly every two years. And so now we've probably done, let's say, four complete evolutions of our own technology stack. And I sort of see that cadence roughly keeping up.Peter [00:06:13]: And so the way even we think about engineering is almost on this two-year horizon, we're preparing ourselves that, hey, like, we wanna invest the appropriate amount, but then also be very dynamic as the research gets published and as our research team figures out new advancements and adapting to that.Qasar [00:06:27]: Yeah. One thing that has been consistent is the type of people we've, we've recruited. It's engineers who are fall into the sometimes very traditional, like, GoogleQasar [00:06:38]: -gen suite, but way different from, other companies. We are hiring folks who really know the intersection of hardware and software, who know really low-level systems. Obviously, traditional ML researchers and folks who've, actually, put ML systems into production. That's been pretty consistent. I think that, like, you look at the mix of our engineering, eighty-three percent of the company is engineering, so it's, like, a giant list.Qasar [00:07:05]: A lot of engineers.Alessio [00:07:06]: Which, by the way, a thousand engineersQasar [00:07:07]: Yeah. A thousand engineers.Alessio [00:07:08]: that's on your website, so I imagine it's up to date.Qasar [00:07:11]: It is, it is up to date, yes. Yes.Alessio [00:07:12]: okay. And then forty-plus founders.Qasar [00:07:15]: Yeah. We would tend to also, This was more luck than strategy. But we've recruited a lot of ex-founders. It's been a great place for founders, YC and non, ‘cause obviously I know a lot of the YC folks. It's kind of like we recruit a lot of Google people.Qasar [00:07:33]: For them to exercise both their technical and non-technical skills because, we're, we're, we're on the applied side. We have a research team that we do fundamental research, we publish, and we've, we've had great traction there. But fundamentally, the business wants to take this intelligence and deploy it into production and there's, like, a certain type of person that's more interested in that.Alessio [00:07:54]: Yeah. You mentioned the tech stack, Peter, so I just wanted to give you some rein to just go into it. I'm interested in where Wayve Nutrition, starts and ends in some sense, what won't you do? What, do you do that's common among all the verticals that you cover?Peter [00:08:10]: There's a few buckets of work that we do, and we've been at this for almost ten years now, so the technology's pretty broad. But we got startedQasar [00:08:17]: Yeah, with a thousand engineers, like, you could work on lots of things.Peter [00:08:19]: There's lots of stuff, yeah, espe-especially with AI tools to help.Peter [00:08:22]: So we got our start in simulation and simulation tooling and infrastructure. And so generally, if you're trying to build a very complex software system that involves moving machines, you need to test that, and the best way to test it is it's a combination of virtual developments, a simulation, and then also obviously real world testing.Peter [00:08:39]: And then there's a very careful process of that correlation between the simulation results and the real world results and ensuring that the simulator is in fact accurate to that. Simulation's a very deep topic.Peter [00:08:49]: We have a whole suite of products in that, and we could talk for many hours about that specifically. But that is one part of what we do as a company. Reinforcement learning as a subpart of that is also super critical. I think a lot of the a lot of the best advancements happening in a lot of these AI systems right now in some way relate to reinforcement learning, and with now we have lots of compute, and you can do tons of interesting things for reinforcement learning. The second bucket of work that we do is on operating systems technology. true operating systems. Like, think about, schedulers and memory management and middleware and message passing and highly reliable networking and data links. Like, the reality is, if you want to deploy AI onto vehicles, you need a really good operating system. And when we were getting deeper into that space, there wasn't really anything that we were happy with.Peter [00:09:39]: Like, things existed, absolutely, and we were using what was available in the market, and as an engineering organization, we roughly realized these things aren't great. We think we can do this better, and so let's, let's build something. And that was then the that was the moment of inspiration that started our operating systems business, which is now a very real business for us. And in order to write and run great AI, you need a great operating system, and so that-that's what got us into that. And then the third bucket that we work on, it's, it's true fundamental AI technology. Models, we do a lot of work in, as mentioned, the foundational research, but then the also the world models and the actual autonomy models that are running on these physical machines, and that's across cars, trucks, mining, construction, agriculture, and defense, and so that's both land, air, and sea.Qasar [00:10:31]: And also, a smaller subsector of that third bucket is the interaction of humans with those machines.Qasar [00:10:38]: So that's a multimodal, experience. Historically, if you're moving a dirt mover or any of these machines, there are, like, buttons you press, whether they're actual physical tactile buttons or something like a touch screen. That's just That fundamentally is changing to where you're just talking to the machine and the machine and you're teaming with the machine.Alessio [00:10:58]: Voice?Qasar [00:10:59]: Yeah, voice, absolutely, yeah.Alessio [00:11:00]: Oh.Qasar [00:11:00]: And also the machine just being aware of who is in the cabin, what their state is. you can think from a safety systems perspective, the most simple version of this is, like, the driver is tired, right? They're, they're if you get those alerts when you're driving your car and saysHardware, Sensors, and the LiDAR QuestionQasar [00:11:15]: -maybe take a coffee break, that take that times, a couple of order of magnitudes up. But this concept of teaming man and machine is important. When you think about running agents or just running, different instances of, Claude and doing work for you in the background, you can take that analogy out, almost copy and paste and put it into, like, a farm, where you have a farmer who's running a number of machines. So where they interact with the machine is where there's maybe a critical decision or a disengagement or something like that, but generally speaking, the agent on the physical machine is running and making decisions on the behalf of the farmer until there's something maybe critical. And that's also what we work on. So that's not pure autonomy. It's a little bit of a mix, but it falls under, autonomy. In the automotive sense, that's typically defined in SAE levels as an L2++ systemQasar [00:12:05]: -with a human in the loop. But just take that idea, to other verticals.Alessio [00:12:09]: Yeah. You've not mentioned hardware at all, like sensors or obviously we you mentioned you don't do chips. I think even in AV there's, like, a big, cameras versus lidars. Like, what are, like, in your space maybe some of those design decisions that you made, and are they driven by the OEM's ability to put things on the machinery? And like, how much influence do you guys have on co-designing those?Peter [00:12:32]: Yeah. So we don't make sensors. Like, we're, we're not a manufacturer. Obviously, we use a lot of sensors in our autonomy products. in terms of what actually goes on the vehicles, we have a preferred set of sensors that we, let's say fully support, and then our customers, they can sort of choose from those. And obviously if there's a very strong opinion on supporting something else, we'll add that to the platform as well. And the lidar question is at this point sort of the age-old,Peter [00:12:59]: topic in autonomy, and the state of the industry right now is lidar is hands down a useful sensor, specifically for data collection and the R&D phase of autonomy development. if you see, for example, a Tesla R&D vehicle, it actually has lidar on itPeter [00:13:17]: to this day, right? In the Bay Area we see these. you'll see, like, Model Ys or Cybercab that have lidars on them just driving around. So it's, it's useful because it gives you per pixel depth information. So if you can pair a lidar with a camerand you can say that, well, this camera's looking this direction, this lidar's looking this direction, and now for each pixel of the camera I can see how far away is that pixel. you can actually then use that as a part of your model training, and then the that depth information then becomes a learned, a learned state of the camera data. And then when you're doing the production system, you can now remove the lidarPeter [00:13:52]: and now you can actually get depth with just the camera. And so that difference between, like, a highly sensored R&D vehicle and then the down-costed production vehicle, we use that across our whole portfolio of products. And of course the end goal is you want super low cost and super reliable.Peter [00:14:08]: And then in certain use cases you have some more, bespoke things. Like in defense as an example, you do things at night oftentimes, and so you care about sensors like infrared, more so than And you don't, you don't wanna be putting energy out, so you don't wanna use lidar or radar.Peter [00:14:23]: but you still need to be able to see at nighttime. So yeah, we work the whole gamut.The Operating System Layer: Why Vehicles Are Like Pre-Android PhonesAlessio [00:14:27]: Cool. So that's kinda like on the hardware level. Then on the OS level, how does that look like? What is, like, unique? my drive- I drive a Tesla. Whenever I drive some other car that has a screen, it always sucks.Alessio [00:14:38]: It's on, like, cheap Android tablet. It's like, it's laggy and all of that. What does the OS of, like, the autonomy future look like?Peter [00:14:46]: When most people, it's really what you just described. When you think about operating system in a vehicle, you're thinking about the HMI, right? The human machine interface, and absolutely that's a an important part of it, but that's actually only one thin layer on top. So when we talk about operating systems for, like, AI in vehicles, there's many layers that go deep into the CPU critical realm and embedded systems, and you're talking about the real time control ofPeter [00:15:13]: let's say the electric motors or the engine and the actuators, and you have different redundancies for different, let's say, the steering actuation in the vehicle. And all of these things, need very core support in the in the operating system. And then of course for autonomy you have real time sensor data that's streaming in, and the latencies there are really important, right? If you try to Imagine you try to run Microsoft WindowsPeter [00:15:35]: like streaming your sensor data in or controlling the vehicle. Like, the latencies are gonna be absurd. Like, you can never do that. And so what's special about what we do is we really have this system level thinking, right? So we're looking at, we care about every performance characteristics of the entire system, and then we also, because we're doing a lot of the software or all of that software, we can fine-tune and control all of those things. So we can very carefully tune in the latencies for every aspect of the system. We can carefully tune in the memory management. We can have the right, fail-safes and fallbacks, for different things. ‘Cause you have to account for what if, what if there is a critical failure? What if there's a cosmic ray that flipsPeter [00:16:14]: a bit in the middle of the processor that causes some, malfunction? And you have to have a fail-safe to all of that, and so the core operating system is a part of that. And then the one last thing, which is a lot less exciting but is, actually a very big topic, is reliability of updates.Peter [00:16:30]: so the I have a Tesla and you get updates fairly frequently, right?Peter [00:16:36]: Once a month. Most companies that are making vehiclesPeter [00:16:40]: are basically never doing updates, and they're And even if they are doing updates, they're usually only updating maybe one module. Maybe they're updating the HMI module. But they're not able to update, let's say, the CPU critical parts of the system.Peter [00:16:51]: You have to go into the dealer for that. And so with our operating system now we can actually enable highly reliable updates of any system in the vehicle, and that's way easier said than done. Like, there's lots of technical, technically deep stuff, in the tech stack to do that in a way that you're not going to accidentally brick a vehicle.Peter [00:17:08]: And right? If, imagine yourAlessio [00:17:10]: That would be bad.Alessio [00:17:11]: Bad.Peter [00:17:11]: Bricking a car is a very expensivePeter [00:17:13]: and honestly, like across the industry maybe one of the most just pure impactful things that we've done is we've just, we're, we're now enabling the industry to actually do software updates.Alessio [00:17:22]: Just to clarify as well, who is the customer for this? Like, I assume a lot of hardware manufacturers have their own firmware, and I'm sure some of them would just have you write it for them because you're experts. And others would have their own. Like, who pays for this? Who invites you into the house? Is it, is it the end user, or is it, is it the manufacturer?Peter [00:17:41]: Yeah. So let me make an analogy firstly on the on the fragmentation of software. So physical machines today are more akin to the state of the phone market before Android and iOS existed, right? So I worked on Android at Google by the way many years ago, and part of the reason that Larry at Google decided to get into Android was they wanted to run Google products on a bunch of phones, and they bought all of these phones from the industry, and it turned out they had like 50 different operating systems on these phones. And it was virtually impossiblePeter [00:18:17]: for Google to make their app run on all 50 devices equally well. And so the solution was, well, actually what if, what if they created-A really great operating system and made it attractive to all of these phone makers, and that was sort of the genesis for what Android was and why Android existed. It was a way for Google to get their products onto really wide diversity of devices. The state of the physical, industry right now, it's a little bit like that. Like, there's yes, these companies have firmware, but they have so many different operating systems, it's so fragmented, and to actually get a modern AI application to run on these vehicles, you actually, you first have to consolidate the operating system, and so that's, that's why we've done that. And then, your specific question was who are our customers? It's, it's, generally it's the companies that are making these machines.Peter [00:19:06]: And we're, we're, we're selling our technology to them to really simplify the architecture and then enable these AI applications to run on them.Customers, Licensing, and the Better-Together StackSwyx [00:19:13]: How much is reusable across? Like, do you have, like, one OS that is just configured for everything, or is there some more customization that is needed?Peter [00:19:22]: Yeah, highly reusable. So the fundamental technology is quite universal, right? So things that we do have to think about though are, like, chipset support. And so if you're, if you're coding, let's say, an LLM and you have start with an assumption that, “Hey, oh, I'm gonna, I'm gonna use CUDA, and I'm gonna run this, on an NVIDIA chip,” then you don't really have to think about the hardware in that sense. Like, you're just, “Okay, I'm just I'm in the CUDA/NVIDIA ecosystem, and I'm, I'm going to use that.” But the hardware, especially in safety critical systems, it's a lot more diverse. There's not one or one or two players. There's a bunch of different chipsets that we have to support. And so our operating system doesn't just run on, like, the equivalent of X86. It has to, it has to run on a number of different architectures from chips from a bunch of different companies. But again, we've been working on this for a long time now, so we have, we have support for all of those chipsets. And then when you want to then run the AI applications, we can then do that reliably across now a variety of providers.Qasar [00:20:19]: And I think that is, like, heavily inspired by Android, right? Android has a huge suite of testing and it's a reliable operating system that runs on thousands of devices. And we think we can, we can do the same in all these physical moving machines, with the difference that we're really in a safety critical realm. Android isn't.Alessio [00:20:40]: So on Android, I don't need to use Gmail, I can use Superhuman. Like, what about your machinery? Like, can people bring somebody else's automation to it, or is it kinda like all-in-one?Qasar [00:20:50]: You have to use us. No. Yeah. we're If, Yeah. Yeah, it's totally open. Yeah.Peter [00:20:56]: Yeah. our philosophy is that we are a technology company, and so we license our technology to customers to use how they want. And so if a customer wants to If they wanna license our autonomy tech and our operating system, then great, we'll license those. If they just wanna license the operating system and then use different autonomy tech, that's fine also, and we have great documentation andSwyx [00:21:17]: Or if they wanna use developer tooling.Peter [00:21:18]: Yeah, exactly.AI Coding Adoption: Cursor, Claude Code, and the Bimodal EngineerSwyx [00:21:19]: It's, like, a better together if, obviously, if you, if they work together. Is it all C++ I assume is with different compile targets?Peter [00:21:27]: We use a lot of C++.Peter [00:21:28]: Rust is sort of a hot, the new hot kid on the blockPeter [00:21:32]: for a bunch of things as well. But yeah, the lower level you get, especially when you get to real-time constraints, you hit C++ at some point, and at some point maybe you work your way into assembly when needed.Swyx [00:21:44]: Oh, damn.Alessio [00:21:46]: I'm curious about the coding agent adoption, just, like, since you're mentioning more esoteric languages. Like, what's the adoption internally? What have you learned?Peter [00:21:55]: Yeah. We use everything. So Cursor was, I think the hottest tool in the company for a good while. Now Claude Code, I think has taken the reign on that. We have a internal leader, leaderboard that we use just to sort of encourage adoptionPeter [00:22:09]: with-within the company. And yeah, it's, they're phenomenally useful. it's, Honestly, we take inspiration from some of those tools also in how we're adapting some of that mindset of thinking to the physical realm. Like if it's so easy to build an app for this or that thing that lives just on a screen, we can We're taking now a lot of the same ideas and applying that to, “Okay, well, if you wanted a physical machine to do something, how easy can we make that, using our own tooling and platform as well?”Alessio [00:22:40]: Are you changing any of, like, the OS architecture, kinda like the way you expose services to, like, be more AI friendly or?Peter [00:22:48]: Yeah, absolutely. The in the early days of our tools infrastructure work, it was a lot about, You had engineers that were experts in certain topics, but the things that you're dealing with, they're oftentimes more mathematical or more abstract, where actually GUI tools are very useful for certain things. Like as an example, we have a product we call Sensor Studio, which is, it helps you design the sensor suite for your autonomous vehicle, whether, again, it could be a car, it could be a drone, could be a mining equipment, could be a robot. And you place sensors in different places. You There's different, There's a library. You can understand what are the trade-offs that you're making in the design of that system, and that was, like, a very, a very GUI intensive, thing ‘cause it's a little more like a CAD tool in that senseSwyx [00:23:37]: YepPeter [00:23:37]: if you've seen CAD tools. Nowadays, though, right, we expose all of the underlying APIs for that and now using, AI agents, you can actually configure a sensor suite with just text and likely reach a better result than you could've through the GUI in the past, and we're taking that thinking now through the whole product portfolio.Swyx [00:23:57]: Another thing I was thinking about is just in terms of, like, AI, adoption, does it change your hiring at least a little bit, or how do you, how do you sort of manage engineers, differently?Peter [00:24:08]: Yeah. absolutely, it does. we, I think like every company in the Valley right now, are evolving our hiring practicesPeter [00:24:16]: because the skills required to be effective are changing so fast, right? you used to really select for just rote implementation ability and now it is more the AI engineer skill set, right? Where it's like, yeah, how to implement, but actually-Just banging out code is no longer the core job, right? It's, it's actually knowing what questions to ask, knowing how to tie, how to tie together these different AI tools. And so the interviews that we give now I think are way harder than they've ever been.Peter [00:24:46]: But we also allow, right, selective use of AI tools to solve the problems. And I think in that you start to see more of a bimodal distribution of engineers, right? You start to see like wow, there's, there's this subset of people that they really get it. Like they're, they're all in and they've, they've clearly invested the hours needed to learn these tools and how to be effective.Peter [00:25:09]: And then there's sort of the group of people that haven't done that, and that the productivity gap is just enormous. And so we're, we're trying to obviously select for the people that are really into this.Qasar [00:25:20]: I first wrote the my AI engineer piece three years ago, and when I first wrote about it, I was like, “Actually, not everyone should be an AI engineer,” ‘cause I think there's a there's an extremist stance where well, every software is an engineer is an AI engineer. And my actual example of people who should not be adopting AI was embedded systems and operating systems, and database people. Are they adopting AI?Peter [00:25:41]: I think it's the classic bitter lesson, topic, which is the Six months ago I would've said the same thing, but it's, it's becoming super useful for every domain.Qasar [00:25:53]: I'm sure.Peter [00:25:54]: Right? Like,Peter [00:25:56]: there was, I think six months ago, or maybe a year ago, if you tried to use, let's say the latest Claude model for writing shaders, GPU shaders, the results were probably underwhelming. And if you use the latest model now to do that kind of task, you're a little bit blown away, like, “Wow, that actually worked. That's amazing.” And we see the same thing in the embedded realm. No question though, especially when you get into safety critical systems, the human validation isPeter [00:26:25]: is 100% key. Like I You're not gonna trust your life to a an AI written software that's, that's not been very carefully, checked by humans. And so I think now the really the challenge is about that appropriate level of human validation for these safety critical systems.Verifiable Rewards, Evals, and Neural SimulationAlessio [00:26:41]: How do you think about, yeah, touching on the simulation side, I think verifiable reward and reinforcement learning is, like, the hottest thing. What have you done internally to build around that? And like, what gives you What makes you sleep at night? Like, if somebody's like, just web coding something or likeAlessio [00:26:57]: wants to try something new, you have like a good enough system. Because I think the opposite is also true, is like if it's super easy to write anythingAlessio [00:27:04]: then it puts a lot of work on like the verifiableAlessio [00:27:07]: side of it. Like, what does that look like for people?Peter [00:27:10]: Yeah. So verifiability, a broader bucket of like evaluations, right? Like how do you evaluate the results that you're, you're getting? I think this is probably the hardest problem right now, because the As the models get better, it can be harder and harder to find the faults on the system.Peter [00:27:29]: And so like the problem of doing proper eval to find those faults, like that problem also keeps getting harder as the models get better. But it's no less important than it's ever been, right? You still there are still going to be edge cases that are not met and whatnot. And so it's, it's a big area of investment for us. On the reinforcement learning topic, the key thing is there's all these new requirements that come to be in the latest generation of these technologies. So for example, end-to-end is the big thing right now in autonomy and physical AI, which is you can now train these models that can effectively take sensor data in and then put control signals out, and get really good results out of that. But the way that you train and improve those models is really different from the previous generations. And so to do reinforcement learning on an end-to-end model, you now need to actually simulate all the sensor data, right? So then this becomes a we call our, work in this neural simulation, but it'sPeter [00:28:26]: think of it like a hybrid of Gaussian, splatting and diffusion methods, and where you really care about performance. Like performance is everything. If you can't do enough simulation fast enough and cheap enough, you actually can't get results that are worthwhile, in the end. It also gets to a lot of our work in embedded systems, which is like performance critical work, and that performance optimization, performance criticality, it carries over to a lot of the model training work. because, like, the only way to make it affordable is it has to be really fast.Qasar [00:28:58]: I think it's worth a few minutes talking about our own, evolving thoughts on verification and validation withinQasar [00:29:05]: kind of, traditional simulators, which are, you can think of like vehicle dynamics or something like that, which you're just taking textbooks and taking those formulasQasar [00:29:13]: and putting them into software, to like now this neural sim/world model universe. I think that's an interesting topic.Peter [00:29:20]: Yeah. So in more traditional development, right, you oftentimes would have, more black-and-white answers to questions.Peter [00:29:28]: And so the in Europe as an example, there's, a regulatory, system, it's called Euro NCAP. It's the European New Car Assessment Program, and as part of that, the vehicles have to pass a bunch of tests, and those tests actually, include, safety systems. So automatic emergency braking for a child that runs in front of a carPeter [00:29:51]: or let's say an occluded child that runs out and you hit it. And so you have You end up with sort of these binary answers of like, well, did the car under test pass this specific test? And there's a very well-known set of test casesPeter [00:30:05]: that the vehicle has to pass. And that was how the industry worked, let's say, until 10-ish years ago. But what's changed now is with these models, everything is statistics, right? Like you no longer have a black-and-white answer, but it's like, well, how many orders of magnitude or how many nines of reliability can I get in the system, and how can I, how can I prove that to be true? And the big unlock honestly for physical AI as an industry is that these models are just becoming much more reliable. Right? Things like things actually work a lot better. It's like the number of nines you can get out of these systems are now good enough that it actually becomes cost effective to really deploy these things. And so the big shift in, so verification and validation has been from a little bit more of a Again the past it was strictly requirements, and are you meeting or not? And now it's more of a statistical, verification and validation case where it's all about how many nines of reliability and meantime between failures, that sort of thing.Statistical Validation, Regulators, and the Cruise LessonSwyx [00:31:04]: And is the target audience regulators or even the customers are yeah, if you I imagine the customers are bought in, and it's mostly regulators that need to be satisfied.Peter [00:31:15]: We do work with the US government, we do work of course with the European governments and the government of Japan, and the government is not like an AI lab by any means.Peter [00:31:25]: So Swyx [00:31:26]: They just care about the outcome.Peter [00:31:27]: They care about the outcome.Peter [00:31:28]: And so we do education, in that regard, and like so sort of teaching about, “Hey, this is how we think validation should be done, and this is an approach that we think is reasonable,” and how to think about like when is a driverless system actually safe enough to go on the roads and that sort of thing. But I wouldn't say that the government is asking for it. It's like we're more teaching the government in that, in that sense. It's honestly, it's more so for our own, our own comfort, right? Like, we want to build very safe systems, and then of course our customers care deeply about that as well. But in that context we're also typically educating our customers.Qasar [00:32:01]: Yeah. Our first, our first core value is on round safety. So I think we can't underline enough that, us also verifying and validating that the systems that we're deploying are safe to us is probably as important as, like, some regulator or a customer saying,Swyx [00:32:19]: Of course. Okay. Yeah.Swyx [00:32:20]: You have to satisfy yourselves.Peter [00:32:22]: As I say, as a whole across the world, regulation oftentimes it's like a almost lowest common denominator. But like, you really have to substantially exceed what the regulators are expecting to make good products.Swyx [00:32:33]: Yeah. One thing I often talk about, I think and I try to make this relatable to the audience also, is Cruise, where they had an accident that basically ended the company. I wonder if people overreact to single incidents, because incidents are going to happen regardless, right? ‘Cause it's a statistical thing, but as long I don't know if regulators understand that, you cannot extrapolate from a single incident, but we do because that's all we have to go on. And your sample sizes are necessarily gonna be lower than, I don't knowSwyx [00:33:00]: consumer driving.Qasar [00:33:01]: Yeah. I think the Cruise example wasn't a technology failure. there was The real, compounding issue there was just how did the company talk to the regulators and what was their kind of behavior, and I think that became more of the issue. If you look,Peter [00:33:19]: It isn't It definitely was a technology failure, but it was made much worse by theSwyx [00:33:23]: Put the car back on the woman.Qasar [00:33:25]: Yeah. And let me put it another way. There is a version where Cruise still exists.Swyx [00:33:29]: right. Right.Qasar [00:33:30]: Right. It'sSwyx [00:33:30]: It was like the last strawQasar [00:33:31]: ItSwyx [00:33:31]: in like a long chain ofSwyx [00:33:33]: like issues.Qasar [00:33:33]: So do you feel like ATG had that horrific accident or someone actually dying, because, that was a homeless person crossing the street? So yeah, I think we can't understate enough that ultimately, like, statistical validation of something, that's one part of it, but it's not the only part of it. Like, consumer and let's say, mainstream adoption of these technologies is also gonna be part of that conversation. I think companies like Waymo are doing a lot of service positively to the industry in the sense of they're, they're setting a high benchmark and they're showing, kind of in a very responsible way how to, how to deal with these. There have been Waymo incidences as well. They've just not been as significant as the Cruise one that you mentioned. But yeah, so I think you'll just continue to see that. I think probably the long term question is really gonna be, again, around Like it is very clear humans are way worse drivers statistically.Qasar [00:34:29]: Like, there's no, there's no debate. And so at what point But we're emotional animals.Swyx [00:34:34]: Yeah. So my thing is, like, we have to get to a point as a society where we accept horrific accidents that would never happen by a human because statistically we understand that it is safer overall. In the same way that planes, they're safer, than I think they're the safest mode of transport that we have.Qasar [00:34:50]: Yeah. it's more dangerous to drive to the airport than it is to get on a flight.Qasar [00:34:53]: So if you're everQasar [00:34:54]: if you're ever getting nervous about getting on a plane, just think “I just gotta get to the airport.”Swyx [00:34:58]: Yes, we're flying.Qasar [00:34:59]: If I get to the airportQasar [00:35:00]: I'll be good.Swyx [00:35:00]: But then it's, planes also concentrate the tail risk if planesQasar [00:35:03]: Yeah. AndPeter [00:35:04]: And I was, I don't think we honestly have to worry about there ever being, accidents from these systems that are like much worse than what humans would cause, ‘cause humans do terrible things.Peter [00:35:14]: Like, people fall asleep at the wheel all the time.Swyx [00:35:16]: I have.Swyx [00:35:17]: Like, I'll call, I've been a drowsy driver.Peter [00:35:19]: Kinda drunk drivers, and that'sPeter [00:35:20]: that's the extreme end of the example. But these AI systems, you have redundancies, you have fallbacks. Like, there's many things have to go wrong for there to actually be a something catastrophic because there's, there's so many, fallbacks that these systems have.Alessio [00:35:36]: your simulation is like so vast because there's so many use cases. What are, like, maybe things that worked in a simulation and then you put it out and it's like, “F**k, this isAlessio [00:35:45]: this just did not work at all?”Peter [00:35:47]: Yes.Alessio [00:35:47]: IsPeter [00:35:47]: That's maybe a bit of a misconception, about simulation there. So let me go a little bit, more technical on this. So at first go, no simulation is going to represent the real world. There's always a process of this, sim to real matchingPeter [00:36:02]: where you actually, you need the real world feedback to basically feed into the parameters that are being used in the simulator, and you have to do that, it's like this validation flow, a number of times until you can get some confidence that, like I think the simulator is now accurately representingPeter [00:36:19]: what's gonna happen in the real world. Now, if you have a situation where you've done that full validation and you thought that it was accurate and then there's something different, those are much trickier cases, and that's, that absolutely can happen, but really I think the validation process is a really important part. You can never skip the simulation validation process, like where you're actually ensuring that, hey, the actual, my sim to real gap here is small enough that I can trust these simulation results. And there's, there's so many fun things that you can do when you get into it. Like, I'll, I'll give one fun example that came up recently is like in these humanoid robotics, systemsOverheating actuators is a real problem, right? So obviously phenomenal demos. IPeter [00:37:01]: The most amazingAlessio [00:37:02]: For 10 minutes.Peter [00:37:03]: The most amazing I can get. I love, I love watching robots do acrobatics like everybody but the these systems actually overheat, right? If, like, And one of the ways you can use simulation though is you can actually have that, the temperature of those actuators be one of the parameters that's representedPeter [00:37:18]: in the simulation. And if you're doing reinforcement learning over a certain task, then the robot can actually adjust its motions in the simulation to account for the fact that, oh, it knows that as it's moving, it's actually beginning to overheat this motor. But if you didn't have that parameter of, let's say, the heat of that motor represented in the simulation initially, then your RL policy might It will disregard that. And now you run that on the robot and the robot will overheat and fail.Alessio [00:37:43]: I guess the question is, like, how do you have all of these parameters taken care of while also understanding the deployment environment? Like, temperature is like a great example, right? WellAlessio [00:37:53]: why did you make my robot worse when it runs in like a freezer?Alessio [00:37:57]: So it actually shouldn't worry about that. it's like, yeah, how do you design these simulations?Peter [00:38:02]: This is honestly the This is what makes simulation so hard, right? it's because you Simulation is fundamentally about you're trying to optimize the development of a system, right? Like, how can I build this system faster and better and cheaper and what are all the levers that I have to actually accomplish that? And because simulation's just a software program, you can, you can change it a lot more easily than you can hardware systems. And then what's particularly awesome about the let's say, world models and using that as a part of simulation is now the simulation doesn't just scale with, let's say, adding new math equations inPeter [00:38:36]: but we can actually scale the simulation environment now with additional real world data and that also unlocks a whole new field of robotics.Qasar [00:38:46]: There is a meniscus line where you cross where still doing real world testing is better. there's, in this, sim-to-real gap, you can reproduce reality at exceedingly expensive costs and this So nothing is free. So really you have to you're finding that line where you're getting great performance, you're getting great feedback, whether it's on the training side or on the eval side, but it's way cheaper than doing it in the real world. At some point it, that doesn't make sense. And so even, from our earliest days in autonomy, our view was you're still gonna do real world testing. You There's, there's not, there's not this, magical land where you're not gonna do that. And maybe even like a more nuanced version of this in like traditional software development is, most of your testing for software in a vehicle, 95% of that can be like traditional CI/CD kind of, flows that you would have in traditional web development. But once you have Now you, let's say you have a truck. Well, you can do like 4% of those in like a rig which has all the components, the electrical and electronics of a truck, but doesn't have, it doesn't have the tires and it doesn't have the And then you have the 1%, which is actually the vehicle. There's something There's a similar analogy in terms of using simulation for intelligent systems. You can do a lot in a simulator, but in using world models, but ultimately it's, it's physical AI. So you're gonna deploy it on physical machines andQasar [00:40:17]: the freezer example comes to, comes to light.Alessio [00:40:20]: The world model thing has been to me the hardest thing toAlessio [00:40:22]: wrap my head around. Like we have Faith Eliyon on the podcast.World Models, Hydroplaning, and Cause-Effect LearningQasar [00:40:25]: We've been doing a small series with like another Intuition company, General Intuition as well.Qasar [00:40:31]: yeah, and I mean, lots of, lots of coverage on NeRFs and yes.Alessio [00:40:34]: Yeah. It feels like we talk with about, the heliocentric system, right? It's like in a world model, if you just feed visual data, the model might learn that the sun spins around the Earth. It makes sense, right? And it's like, well, not really. And I think what are like some of these other things that like hydroplaning is one thing I think about, is like can a world model understand hydroplaning and like what amount of water like causes it to happen? And it's like, yeah, to me it's like I don't understand how you guys do it. I guess it's like the real thing is like when you're doing both cars and the highway in Japan versus the excavator in a mine in,Qasar [00:41:13]: ArizonaAlessio [00:41:13]: wherever you're Arizona, wherever you're deploying them.Alessio [00:41:15]: How much of it are you relying on the world models to like generate the simulations for you and then try and close the gap after versus like giving the world models as a tool to your engineers to like curate the simulations if that makes sense?Peter [00:41:28]: Yeah, totally. So yeah, I can say at a pure engineering level, I think if you're hoping to do real world deploys and you're purely relying on a world model approach, you probably won't get to something that works, before you go bankrupt. So there is just a very practical mindset of like, world models are amazing and they're extremely useful for a lot of use cases, but there are a lot of other things that you need to do to actually get something started and something deployed and working. most fundamentally, world models are all about It's understanding the world, but also understanding what's going to happen. It's like the cause-effect relationship.Peter [00:42:01]: Right? And so like it, right, if you have a take some sort of construction tool, and that construction tool is gonna be doing some work on the Earth in some way, it's gonna be moving earth, the world model needs to understand that cause-effect relationship. Like, okay, when I, when I take this material from here and put it over there and now I have things that are over here and not over there anymore and that cause-effect, relationship. data obviously is a is a big problem. The hydroplaningPeter [00:42:26]: one is actually a really great example because it's actually quite non-obvious sometimes. Right? It's like, well, it's, it's raining and well this road, has, let's say the appropriate curvature to it so the water is running off the road and cars are driving faster here and then you approach a road that's very flat and water is now puddling on that road and all of a sudden cars are driving slower because when they were driving faster they were starting to lose control. And there are a lot of visual nuance, very nuanced visual cues in the scene and so I do think in the world model concept there's a good chance that the model actually would learn that you should just drive slower when these visual cues exist, and that's obviously the beautiful-The beauty of, these kinds of models where they just, they learn these non-obvious things.Swyx [00:43:14]: It doesn't need to know about hydroplaning to know that it needs to drive slower.Peter [00:43:17]: Yes.Swyx [00:43:17]: I guess it's Yeah. I wanna ask questions about, also deploying models. I presume, like, you use a lot of these world models for training data and simulation, but what about deploying it onto the systems in production? Presumably you have you have, like, GPUs on deviceOnboard vs. Offboard: Latency, Embedded ML, and DistillationSwyx [00:43:36]: but they're I keep saying on device. What's the what's the right term for that?Peter [00:43:40]: On machine.Swyx [00:43:41]: On machine.Peter [00:43:41]: Or embedded, yeah.Swyx [00:43:42]: Yeah. What is the embedded world like? because for people who are not used to that world, this is very alien.Peter [00:43:49]: Yeah. So it's actually We call it onboard and off board.Peter [00:43:52]: So like, onboard software and off board software.Peter [00:43:54]: And the great thing about off board software is you don't have to care about time, and you can run really large models, right? So you can, you can say, “Well, this model, I don't care if it takes one second for it to give me a result or 10 seconds for it to give me a result, because we have time.” And the models can be really big, and they can run, in a data center or on a on a huge GPU and you can obviously have distribute to compute, et cetera. But onboard you don't have any of those benefits. You're like, “Well, I need I have this many milliseconds where I need an answer from this model.” And so a lot more of the energy then is about, think of it more like distillation and it's like truly efficiency and like, literally every fraction of a millisecond counts. And you can't have a situation where the model takes too long because then the vehicle can't actually function.Peter [00:44:42]: And so you can, you can still use a lot of the same techniques, and the models themselves you can think of as like a derivative of larger models that you can run offline, and then you're, you're trying to just get a model that is still performs really well but it's, it's a it's smaller, small enough version that you can then run on this embedded system where you care about latency and power.Qasar [00:45:03]: Yeah. And I think like, the broader point I think which, maybe is not obvious but it's worth saying is in physical AI world, we're not really constrained right now by, like, the intelligence of the models. It's actually what Peter's talking about, it's actually deploying them inSwyx [00:45:19]: The hardware they give you.Qasar [00:45:21]: Yeah. On the hardware you give you.Qasar [00:45:22]: And so And there's just a reality is of safety critical systems. So those end up being the your limiting factorsQasar [00:45:29]: rather than, let's say, a limiting factor for, a foundation model companyQasar [00:45:34]: is gonna be just capital maybe or researchers.Qasar [00:45:38]: So we're, we're in that way dealing with, for us as people who kind of come in that realm with like a very interesting Those constraints force creativity.Swyx [00:45:47]: And I imagine, nobody was deploying or giving you the hardware for transformers back in 2018, whatever, but now they are. What's the evolution like? just peel back the curtains a little bit.Peter [00:45:59]: Yeah. Transformers first off, I think the paper was originally published in 2017.Swyx [00:46:02]: 2017.Swyx [00:46:02]: So there's no time.Peter [00:46:04]: And ISwyx [00:46:05]: But I'm just saying I guess I'm saying, like, embedded ML systems usually, like, a lot less parameters, a lot less compute, and now, like, orders of magnitude more.Peter [00:46:14]: Yeah. absolutely. what I was gonna say though was I think in the in the original paper in 2017, maybe it's in the last paragraph, somewhere in the paper they talk about, like, “Oh, by the way, this technique might be useful for, like, images and videos as well.”Peter [00:46:30]: These last subjects.Peter [00:46:31]: And it took a few years for that impact to really hit. But like, now, we're seeing transformers are everywhere.Swyx [00:46:39]: Yeah. Vision transformers.Peter [00:46:40]: And then then the compute just keeps getting better and better. But you do have this fundamental trade-off, right? It's like you have power, you have cost, and performance and like, getting the right, getting the right mix of those things in an embedded package that can also be, like, shaken and baked in all thePeter [00:47:00]: conditions that these things have to have to operate in. But yeah, I think that they're only going to keep getting better and so we also try to plan our strategy understanding that, we know the rate of improvements of these systems.Swyx [00:47:11]: Yeah. So like, Google just released the Gemma 2B modelSwyx [00:47:15]: that effective 2B model. Is that useful to you guys or is that too big?Peter [00:47:18]: You can run that model on an embedded system, definitely.Peter [00:47:21]: the So yes, it's, it's useful in that regard. The bigger question is, like, what do you use it for in an embedded system? Like, you actually need to customize it quite a bit to make it useful for something. But yeah, you could run a two billion parameter model, definitely.Swyx [00:47:35]: It also interesting, like, what percent is a custom ML model that only does that thing versus a generalist LLMSwyx [00:47:41]: which probably is not that useful actually for your context.Peter [00:47:46]: Like, you, like, you can imagine different use cases, right?Peter [00:47:48]: So theSwyx [00:47:49]: The voice stuff, yes.Peter [00:47:49]: Yeah, the voice test. Totally, yes.Peter [00:47:51]: So for the actual, autonomy elements, that's 100% in-house. We do every bit of that, the data simulation, the model, everything. But when you get into the more generic use cases like voice or voice assistant kind of thing, that's where these more generalist models like Gemma actually can be quite, can be quite useful.Swyx [00:48:09]: Yeah. And then there's also obviously a trade-off between, like, what percent must you do on machine, versus just call home.Peter [00:48:16]: Yeah. It's all about latency.Swyx [00:48:17]: Latency.Peter [00:48:17]: It's all about latency. Yeah.Swyx [00:48:18]: Yeah. Well, like, I think actually in a lot of contexts, especially in the US, you can just have a connection to the web.Qasar [00:48:26]: Yeah. I think though most of our universe is everything has to be fairly, embedded and local because just the nature of Even in the US there's a lot of likeSwyx [00:48:39]: PatchinessQasar [00:48:40]: don't haveQasar [00:48:41]: have coverage, right? And if you look at, like, the old world of autonomy within mining, which is, like, long before transformers and kind of, neural networks, in the like CNN and kind of a universe, they were really just hand-coded, systems. They were just like, this machine is gonna run to that place with thisPeter [00:49:03]: That was our GPS, like very accurate GPS.Qasar [00:49:05]: Yeah. And so that worked, and that worked for 20 years, so why would we actually need to use transformers or kind of more modern end-to-end systems? Mainly because you can only really run a path and run backwards. That provided a lot of value, but m-Not as much as you get when the machine is actually intelligent. It's, it's seeing, it's perceiving, it's acting in a dynamic world.Alessio [00:49:28]: I looked up RTK, real-time kinematic, one to two-centimeter accuracy.Qasar [00:49:32]: Yeah. Fantastic. But the and fantastic in faraway lands where there's not gonna be cell phone coverage.Peter [00:49:39]: Yeah, so it's widely used on the legacy mining and agricultural autonomy systems today. So like, for example, a combine that can be precise within one or two centimeters as it's driving down the field, they use RTK.Qasar [00:49:53]: Yes.Peter [00:49:53]: But it's, it's expensive.Qasar [00:49:54]: Yeah. And it's, it's, it's autonomy, but it's not intelligent in the way that I think all of usQasar [00:49:58]: if in twenty-six we'd be talking about intelligence.Alessio [00:50:00]: In one of your blog posts, you mentioned research on large scale transformers that are similar to those doing modern generative AI. What are, like, the big differences other than, “You're absolutely right. I should steer the car, so you probably wanna remove that?”Peter [00:50:14]: We have a diversified bet strategy internally, and the reason we've done that is because we operate in now a bunch of industries, a bunch of geographies, and each of the approaches has, obviously a different risk to them.Peter [00:50:27]: And so like, we're not going to put all of our eggs in a single basket for a single approach because that approach may no

Crystal Clear opens the episode by contributing a brand-new condition to the diagnostic literature: Delusional Debunking Disorder, or DDD. The case study is Mick West, who has spent twenty years insisting Morgellons fibers are lint and Havana Syndrome is crickets. Crystal pivots to chat about Chen Tianqiao, Shanda Group founder and CCP member, who quietly bought roughly 200,000 acres in Klamath and Deschutes counties through a shell company called Whitefish Forest Resources in February 2015h. Second-largest foreign land purchase in American history. The data point that refuses to sit down: Google Trends shows Oregon Morgellons searches at zero the week of the transaction. Five weeks later, March 29, 2015, the spike hits one hundred. Lagged correlation coefficient 0.92. Top two Oregon metros for Morgellons search interest that year: Bend in Deschutes County, and Medford-Klamath Falls. Whatever drove the search spike was not news. It was something people were feeling in their bodies.Crystal traces what Chen did next. One billion dollars committed to neuroscience. The Tianqiao Chen Institute for Neuroscience at Caltech, $115 million. A Fudan University partnership in Shanghai. And NeuroXess, his implantable BCI company, whose chief scientist Tiger Tao specializes in silktrodes. January 2026: NeuroXess breaks ground on a super factory in Nanshang. March 2026: China issues the world's first commercial approval for an invasive BCI device. Enter billionaire number two. Joe Tsai, Alibaba co-founder, funder of the Wu Tsai Neurosciences Institute at Stanford, the Wu Tsai Institute at Yale, and a $220 million Human Performance Alliance that includes the University of Oregon. Then the digital twin layer. Jensen Huang, NVIDIA CEO and Oregon State alum, donated fifty million dollars for an NVIDIA supercomputer at OSU Corvallis built for “complex twin simulations.” Ninety minutes from Eugene, the number five Morgellons search metro in America. Oklahoma State launched its Digital Human Twin Consortium in January 2025, also NVIDIA-powered, and happens to sit on Dr. Randy Wymore's twenty-year Morgellons patient registry, possibly twelve thousand families, the largest biological data repository on the condition anywhere. They still ignore Crystal's open records requests. The sensor layer is Profusa, DARPA and Shanghai-funded, CEO Ben Hwang, manufacturer of injectable hydrogel biosensors. They just partnered with NVIDIA to build the AI portal reading the data. Sensors in, data out, twin built. The deepest cut is the 2001 material. Weinong Fu, computational electromagnetics specialist at Ansoft in Pittsburgh, the company whose software gets implantable devices through FDA approval, posted a web page from his corporate email in May 2001 collecting Morgellons symptom reports from Americans. His wife Li Honglui was simultaneously co-funding a Fudan University paper documenting an unidentified organism producing “creeping eruptions, migratory pain, and neurofilament damage.” American arm, Chinese arm, Pittsburgh modeling layer.The episode closes on the new Morgellons metagenomics preprint that landed on bioRxiv in April 2026, the first substantial research since Middelveen 2018. Crystal notes the venue: bioRxiv runs on Cold Spring Harbor Laboratory, home of the Eugenics Record Office until Carnegie pulled funding, and has been bankrolled since 2017 by the Chan Zuckerberg Initiative. The paper itself gets its full deep-dive on Jeremy Murphree's Morgellons Discussion podcast. Check it out!A 0.92 correlation does not care about anyone's opinion. A 2001 paper does not retroactively become a coincidence because it is inconvenient. And nobody buys 200,000 acres in the highest-Morgellons-search state while building a silk fiber brain implant factory unless those two investments are chapters in the same business plan.

The "old school" way was simple: a sensor sees a part, tells the controller, and the actuator moves. It was pure hardware logic, and it worked. But in today's smart factories, that's only half the story. Modern sensors aren't just on/off switches anymore—they are eyes and ears, and sometimes even the brains, of the automation. However, surprisingly few engineers really understand both the hardware and software sides of machine data. In this episode of the Moore's Lobby podcast, Control.com's David Peterson discusses sensors with Nils Beckmann, an expert with a background in both sensor hardware and IIoT software analytics. They explore the various solutions and best practices that ease the pathway to productively using sensor information. Emerson has been a leader in measurement instrumentation for over 50 years. They have a broad portfolio of measurement and analytical instrumentation, software, integrated systems, and services. Meet Nils Beckmann In his role as Director of Engineering, Intelligent Automation at Emerson, Nils Beckmann brings extensive industry experience in Digital Transformation, IIoT, and Software across a wide range of applications in the discrete manufacturing industry. He leads globally distributed team that supports Emerson's Discrete Automation group with hardware and software solutions designed to enhance productivity and overall equipment effectiveness (OEE), while minimizing waste and promoting sustainability. The team also facilitates connectivity, AI and data analytics across all brands within the group. Nils previously served in various positions across IT, software, data analysis, AI, product management, and development. He holds a Bachelor of Science and a Master of Science in Applied Computer Science from Fachhochschule Hannover.   

SoundSource Deep Dive: A ScreenCastsONLINE Tutorial Control Brightness on ViewSonic VP2788-5K with BetterDisplay CES 2026: Motion Sensors Enabled by Sentistic Yolink Water Leak Sensors from Yosmart CES 2026: TCL NXTPAPER LCD Tablets with "Electronic Paper” Displays Support the Show CCATP #833 — Joseph Nilo on Agentic AI with OpenClaw Transcript of NC_2026_04_19 Join the Conversation: allison@podfeet.com podfeet.com/slack Support the Show: Patreon Donation Apple Pay or Credit Card one-time donation PayPal one-time donation Podfeet Podcasts Mugs at Zazzle NosillaCast 20th Anniversary Shirts Referral Links: Setapp - 1 month free for you and me Wispr Flow - 1 month free for you PETLIBRO - 30% off for you and me Parallels Toolbox - 3 months free for you and me Learn through MacSparky Field Guides - 15% off for you and me Backblaze - One free month for me and you Eufy - $40 for me if you spend $200. Sadly nothing in it for you. PIA VPN - One month added to Paid Accounts for both of us CleanShot X - Earns me $25%, sorry nothing in it for you but my gratitude

Waymo is now delivering hundreds of thousands of fully autonomous rides each week — but getting there required more than better models. It meant building a complete system for training, evaluating, and deploying a driver in the real world. In this episode — originally aired on the Cheeky Pint podcast — Waymo Co-CEO Dmitri Dolgov joins John Collison to break down how self-driving actually works today: from sensor fusion across LiDAR, radar, and cameras, to simulation, “critic” models, and the role of AI in decision-making. They also explore why full autonomy is fundamentally different from driver-assist, what it takes to scale globally, and how recent advances in AI are reshaping the path forward.   Resources: Follow Dmitri Dolgov on X - https://x.com/dmitri_dolgov Follow John Collison on X - https://x.com/collision Stay Updated:Find a16z on YouTube: YouTubeFind a16z on XFind a16z on LinkedInListen to the a16z Show on SpotifyListen to the a16z Show on Apple PodcastsFollow our host: https://twitter.com/eriktorenberg Please note that the content here is for informational purposes only; should NOT be taken as legal, business, tax, or investment advice or be used to evaluate any investment or security; and is not directed at any investors or potential investors in any a16z fund. a16z and its affiliates may maintain investments in the companies discussed. For more details please see a16z.com/disclosures. Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

In this episode, Griffin sits down with Peter Costanzo of ROI Consulting Group to explore how facilities management technology is rapidly evolving—and why the industry is finally hitting an inflection point.Peter shares his unexpected path into FM tech and what's kept him in the space for over two decades: the increasing complexity, opportunity, and impact of technology on building operations. From the growing role of IT and HR in facilities decisions to the rise of workplace experience as a priority, facilities teams are becoming more integrated than ever before.The conversation dives into major trends shaping the future of FM, including AI, predictive maintenance, and the explosion of sensors. Peter highlights how falling sensor costs and improved connectivity are making smarter buildings more accessible—and how large players like Siemens, Schneider Electric, and Autodesk are investing heavily in this space.They also discuss common challenges, like outdated systems, overwhelming technology choices, and implementation failures. A key theme: success with FM tech isn't just about buying the right tools—it's about long-term thinking, cross-functional collaboration, and actually using the systems to their full potential.If you're trying to make sense of where FM technology is headed—or where to even begin—this episode offers a grounded, real-world perspective on what's changing and what it means for facilities teams moving forward.Resources:ROI Consulting GroupPeter Costanzo LinkedIn

In today's episode, we discuss the harsh realities of the domestic surface market as a wave of bankruptcies among small and mid-sized carriers sweeps across the United States. Facing a prolonged freight recession, depressed spot rates, and high operating costs, vulnerable carriers are simply running out of financial runway and filing for Chapter 11. Next, we explore how logistics giant UPS is deploying cutting-edge technology by expanding its use of automated package sensors to virtually eliminate lost parcels. This massive rollout of RFID labels will streamline sorting operations, drastically reduce misloads, and give e-commerce shippers unprecedented real-time visibility into their freight's exact location. Finally, we look at a major new tech integration that aims to make life easier for drivers as the navigation app Trucker Path seamlessly connects with the Truckstop.com load board. By combining high-quality freight matching with real-time truck routing and parking availability, this strategic tie-up helps to reduce deadhead miles for independent drivers battling a tight spot market. Follow the FreightWaves NOW Podcast Other FreightWaves Shows Learn more about your ad choices. Visit megaphone.fm/adchoices

The Hispanic Access Foundation found that in several Latino communities, particulate pollution exceeded federal standards. Learn more at https://www.yaleclimateconnections.org/ 

In this episode of the Crazy Wisdom Podcast, host Stewart Alsop sits down with Lucas McKenna, Director of Europe at Point One Navigation, for a wide-ranging conversation about the future of robotics and autonomous systems. They cover topics including the SLAM algorithm and how robots map and position themselves in the world, the role of GPS and sensor fusion in precise localization, swarm robotics and the debate between centralized and decentralized robot intelligence, the differences between urban and rural robotics applications, specialized versus general-purpose robots, the business models around robot ownership and rental, and how autonomous mobility is taking shape differently in Europe versus the United States. They also touch on the cultural implications of robots becoming a fixture in everyday life and what it might mean for human community and connection.Show Notes- Lucas McKenna on LinkedIn: https://www.linkedin.com/in/lucas-mckenna-79269053/- Point One Navigation: https://pointonenav.comTimestamps00:00 - Stewart introduces Luca McKenna from Point One Navigation, diving into robotics and the SLAM algorithm for simultaneous localization and mapping.05:00 - Luca explains swarm robotics, where multiple robots share environmental data, building collective maps that improve positioning accuracy over time.10:00 - Discussion shifts to urban versus rural robot deployment, covering drone delivery limitations, obstacle avoidance challenges, and skyscraper navigation complexity.15:00 - Luca distinguishes specialized versus general-purpose robots, predicting purpose-built machines like seed planters and window washers will dominate near-term deployment.20:00 - Stewart raises unstructured visual data challenges, drawing parallels to AI text processing, while Luca details GPS infrastructure layers enabling precise robot positioning.25:00 - Consumer robot visibility discussed, including Waymo expansion, autonomous delivery robots, and geographic limitations of current self-driving services.30:00 - Robot ownership versus rental models explored, touching on rare earth mineral costs, Chinese supply chains, and economic barriers to personal robot ownership.35:00 - Luca explains state estimation systems using GPS satellites, accelerometers, and gyroscopes working together, contrasting fundamental mathematics against machine learning approaches.40:00 - Sensor fusion parallels between smartphones and autonomous vehicles revealed, explaining how phones mirror car navigation systems at reduced accuracy and cost.45:00 - Conversation concludes examining robots impact on community culture, with Luca advocating autonomous public transit over individualist robotaxis to strengthen human connection.Key Insights1. SLAM is foundational to robot navigation. Simultaneous Localization and Mapping (SLAM) allows robots to map their environment and position themselves within it using computer vision and LiDAR sensors. Unlike humans, who instinctively understand their surroundings, robots require precise algorithmic systems to avoid obstacles and navigate safely.2. GPS and sensor fusion solve the positioning problem. Robots combine absolute sensors like GPS with relative sensors like accelerometers and gyroscopes to maintain accurate positioning. In challenging environments like tunnels or dense cities, these sensors compensate for each other, ensuring continuous and reliable location data.3. Swarm robotics enables collective environmental intelligence. When one robot maps a new area, that data becomes available to all connected robots. This decentralized-yet-centralized model means the entire fleet benefits from each individual robot's experience, continuously improving map quality and navigation precision.4. Specialized robots will dominate before general-purpose ones. Rather than multipurpose humanoid robots, the near-term future favors robots designed for single tasks—delivering food, planting seeds, or drawing lane lines—because the economics and technical bar are far more achievable than building versatile machines.5. Urban, suburban, and rural environments demand different robotic solutions. Open skies in rural areas make GPS-based drones effective, while dense cities require complex sensor stacks. European approaches favor autonomous public transit, while American models lean toward individual robotaxi services.6. Robots will largely be rented as services, not owned. The high cost of hardware, rare earth minerals, and the extensive data required for safe operation makes personal robot ownership impractical for most consumers. Business models will resemble subscription or usage-based services.7. Fundamental mathematics still outperforms machine learning for positioning. Despite AI advances, state estimation systems rely on proven mathematical formulas rather than transformer-based models, which currently underperform classical methods in 3D reconstruction and precise localization tasks.

In this episode of the Crazy Wisdom Podcast, host Stewart Alsop sits down with Lucas McKenna, Director of Europe at Point One Navigation, for a wide-ranging conversation about the future of robotics and autonomous systems. They cover topics including the SLAM algorithm and how robots map and position themselves in the world, the role of GPS and sensor fusion in precise localization, swarm robotics and the debate between centralized and decentralized robot intelligence, the differences between urban and rural robotics applications, specialized versus general-purpose robots, the business models around robot ownership and rental, and how autonomous mobility is taking shape differently in Europe versus the United States. They also touch on the cultural implications of robots becoming a fixture in everyday life and what it might mean for human community and connection.Show Notes- Lucas McKenna on LinkedIn: https://www.linkedin.com/in/lucas-mckenna-79269053/- Point One Navigation: https://pointonenav.comTimestamps00:00 - Stewart introduces Luca McKenna from Point One Navigation, diving into robotics and the SLAM algorithm for simultaneous localization and mapping.05:00 - Luca explains swarm robotics, where multiple robots share environmental data, building collective maps that improve positioning accuracy over time.10:00 - Discussion shifts to urban versus rural robot deployment, covering drone delivery limitations, obstacle avoidance challenges, and skyscraper navigation complexity.15:00 - Luca distinguishes specialized versus general-purpose robots, predicting purpose-built machines like seed planters and window washers will dominate near-term deployment.20:00 - Stewart raises unstructured visual data challenges, drawing parallels to AI text processing, while Luca details GPS infrastructure layers enabling precise robot positioning.25:00 - Consumer robot visibility discussed, including Waymo expansion, autonomous delivery robots, and geographic limitations of current self-driving services.30:00 - Robot ownership versus rental models explored, touching on rare earth mineral costs, Chinese supply chains, and economic barriers to personal robot ownership.35:00 - Luca explains state estimation systems using GPS satellites, accelerometers, and gyroscopes working together, contrasting fundamental mathematics against machine learning approaches.40:00 - Sensor fusion parallels between smartphones and autonomous vehicles revealed, explaining how phones mirror car navigation systems at reduced accuracy and cost.45:00 - Conversation concludes examining robots impact on community culture, with Luca advocating autonomous public transit over individualist robotaxis to strengthen human connection.Key Insights1. SLAM is foundational to robot navigation. Simultaneous Localization and Mapping (SLAM) allows robots to map their environment and position themselves within it using computer vision and LiDAR sensors. Unlike humans, who instinctively understand their surroundings, robots require precise algorithmic systems to avoid obstacles and navigate safely.2. GPS and sensor fusion solve the positioning problem. Robots combine absolute sensors like GPS with relative sensors like accelerometers and gyroscopes to maintain accurate positioning. In challenging environments like tunnels or dense cities, these sensors compensate for each other, ensuring continuous and reliable location data.3. Swarm robotics enables collective environmental intelligence. When one robot maps a new area, that data becomes available to all connected robots. This decentralized-yet-centralized model means the entire fleet benefits from each individual robot's experience, continuously improving map quality and navigation precision.4. Specialized robots will dominate before general-purpose ones. Rather than multipurpose humanoid robots, the near-term future favors robots designed for single tasks—delivering food, planting seeds, or drawing lane lines—because the economics and technical bar are far more achievable than building versatile machines.5. Urban, suburban, and rural environments demand different robotic solutions. Open skies in rural areas make GPS-based drones effective, while dense cities require complex sensor stacks. European approaches favor autonomous public transit, while American models lean toward individual robotaxi services.6. Robots will largely be rented as services, not owned. The high cost of hardware, rare earth minerals, and the extensive data required for safe operation makes personal robot ownership impractical for most consumers. Business models will resemble subscription or usage-based services.7. Fundamental mathematics still outperforms machine learning for positioning. Despite AI advances, state estimation systems rely on proven mathematical formulas rather than transformer-based models, which currently underperform classical methods in 3D reconstruction and precise localization tasks.