Podcasts about installed

Selling the equipment is the easy part. The real revenue shows up after the sale.Sam Neva, Vice President of Sales for Service Lifecycle Management at PTC, joined the show to talk servitization - what it means, and why it's becoming the difference between OEMs who scrape by on hardware margins and ones who build real recurring revenue. Chris caught up with him live at PTC's headquarters.Manufacturing folks, we didn't forget about you! This episode is geared squarely toward people building equipment. If you want to tighten up your sales process and make your customer relationships stickier, this one is for you.Sam and Chris get into what's holding most OEMs back from servitization, how AI is starting to change what proactive service looks like, and the math behind why the money shows up years after the original sale.In this episode, find out:Why the smartest OEMs are lowering the price of the original sale, and what they're betting on insteadThe three levels standing between a traditional OEM and a full servitization modelWhy ‘tribal knowledge' is the hidden gap between engineering and service teamsHow AI is helping teams triage service issues before they need a technicianThe Harvard Business Review stat that shows just how much revenue gets left on the table post-saleWhat Schneider Electric did to grow revenue, win rates, and improve customer satisfaction at the same timeThe first question every OEM should ask before attempting servitizationEnjoying the show? Please leave us a review here. Even one sentence helps. It's feedback from Manufacturing All-Stars like you that keeps us going!Tweetable Quotes:“You're reacting to a problem, instead of doing your best to extend and plan that time horizon to prepare for that problem." - Sam Neva, Vice President of Sales for Service Lifecycle Management at PTC“Step 1 is what do customers expect from us, why do they expect that, and how can we give them that?" - Sam Neva, Vice President of Sales for Service Lifecycle Management at PTC“The goal is how do I make money as the OEM, not just by selling you that box, but selling you the outcome of what that box provides.” - Sam Neva, Vice President of Sales for Service Lifecycle Management at PTCLinks & mentions:Benchmark your servitization strategy, a complimentary assessment where ServiceMax experts will evaluate your current service organization and identify opportunities to improve performance, profitability, and customer outcomes.ServiceMax, a PTC Technology, is on a mission to help customers keep the world running with asset-centric field service management software. As a recognized leader in this space, our cloud-based software and mobile apps provide a complete view of assets to field service teams.Make sure to visit https://manufacturinghappyhour.com for detailed show notes and a full list of resources mentioned in this episode. Stay Innovative, Stay Thirsty.

WBZ NewsRadio’s James Rojas reports. See omnystudio.com/listener for privacy information.

Just before the show started at 2pm today, we all (unfortunately not our very own Mia Tracina) received an AusAlert on our phones. For some who have heard it before like Chrissie in Japan, we just went on about our day. However for others, it’s sparked a conversation about what it really was for, so we opened up the hotlines to see what you all made of it. Plus, a man has impaled himself on a hike in the US and still walked 10km whilst impaled?!See omnystudio.com/listener for privacy information.

Water meters register the volume passing through them, but what happens when that volume contains both water and entrained air? Anthony Giudice, president of AquaFlow, explains how turbulent flow can influence meter readings and how AquaFlow's calibrated valve is designed to help meters reflect what he describes as true water consumption.    Why Flow Conditions Matter at the Meter  Anthony connects entrained air to the pressure required to move municipal water and the turbulence created as water travels through piping, changes direction, and encounters shifting demand. Because a conventional meter cannot distinguish between water and air within that volume, he says the resulting air-water mixture can contribute to overreading.  The valve addresses the condition from the customer's side of the property. Installed immediately after the meter, it creates a slight backpressure intended to establish laminar flow upstream while compressing the entrained air rather than removing it from the system.    Calibration, Placement, and System Conditions  Each valve is calibrated for its specific meter and operating environment. Anthony explains why valves cannot simply be exchanged between meters of the same size and describes a dual-spring design that responds to changing pressure throughout the day.  Available sizes range from three-quarter inch to 32 inches, supporting applications from residential service to power plants, data centers, manufacturing facilities, and cooling tower systems. Trace and Anthony also examine an important secondary-metering question: where should a valve be installed when cooling tower makeup and bleed meters affect water and sewer billing credits?  The answer depends on the measurement objective. Teams must first identify which meter they want to optimize and how any downstream reading affects utility calculations or sewer credits.    Measuring Results Beyond the Utility Bill  A lower invoice alone does not prove that a valve is performing. Facility activity may change substantially from one billing period to another.  Anthony recommends a measurement and verification reconciliation using 12 clean pre-installation months, the installation month, and at least three clean post-installation months. Consumption should then be normalized against an operating unit such as cars washed, hotel guests, or stadium attendance.  A car wash example demonstrates the distinction. Recorded consumption changed from 16.03 gallons per car before installation to 13.13 gallons per car afterward. That per-unit comparison provided a clearer performance indicator than the total bill, which could rise or fall with the number of vehicles served.  Careful meter selection, operating data, and normalized analysis help water professionals evaluate this technology without confusing reduced recorded consumption with changes in production or occupancy.  Listen to the full conversation above. Explore related episodes below. Stay engaged, keep learning, and continue scaling up your knowledge!    Timestamps  02:20 — Trace Blackmore Shares: Reflections on Episode 485's listener-submitted questions, ways to suggest future topics and guests, and learning resources available at ScalingUpH2O.com.  05:00 — Words of Water with James: James McDonald challenges listeners to identify the term for the distribution ratio of a volatile substance between the steam and liquid phases.  07:20 — Upcoming Events for Water Treatment Professionals: Trace previews the 2026 AWT Convention and Expo, the American Chemical Society Expo, and August's Legionella Awareness Month programming.  10:40 — Interview with Anthony Giudice, President of AquaFlow: Anthony introduces water-meter optimization and explains how entrained air can affect recorded water consumption.  12:50 — Anthony explains how municipal pressure, pipe length, changing demand, and directional changes contribute to turbulent flow and entrained air.  14:00 — Trace raises a practical question about secondary metering for cooling-tower makeup and bleed water.  16:00 — Anthony explains the valve's placement on the customer's side of the meter and connects its operation to Bernoulli's principle, the Venturi effect, and Boyle's law.  18:20 — Anthony distinguishes AquaFlow's dynamic, meter-specific valve from conventional pressure-reducing and check valves.  20:00 — Anthony clarifies that the device compresses entrained air—not water—and describes what happens after the mixture passes through the valve.  21:00 — Anthony discusses reported payback periods, 316L stainless-steel construction, certifications, installation time, trial terms, valve sizes, and industrial applications.  23:50 — Anthony connects water-meter optimization with property value, water-hammer reduction, booster-pump protection, and possible carbon-credit opportunities.  28:30 — Anthony explains how visual demonstrations and measurement and verification reconciliation can document performance more reliably than invoice comparisons alone.  30:50 — A car-wash example demonstrates why gallons per vehicle provide a clearer performance measure than total monthly consumption.  32:50 — Trace and Anthony revisit cooling-tower submetering to determine valve placement when sewer credits are involved.  36:10 — Anthony outlines the site survey, meter-specific calibration, recommended valve location, and typical installation process.  38:50 — The conversation explores possible applications for creating laminar flow in blood, eggs, oil, gas, and other fluid-handling systems.  41:20 — Anthony directs listeners to AquaFlow's website and homepage demonstration for more information.  42:20 — Trace explains AquaFlow's 90-day trial offer for the Scaling Up Nation, including discount code H2O750 and the additional money-back guarantee.    Quotes  "Meters, unfortunately, people don't like to hear this, but they're designed to register volume. Volume is anything that passes underneath the meter."  "Each one is specific to that meter. You can't just start, even if they're the same size, you can't just start switching them around."  "We're not compressing water. We're compressing the entrained air in the water."  "It was 16.03 gallons of air and water. When the valve was installed, it forces a true water consumption reading of 13.13 gallons."    Connect with Anthony Giudice  Phone: 19544156973  Email: tony@aquaflow.com   Website: AquaFlow – Reduce Water Bills with Smart Water Valves   LinkedIn: https://www.linkedin.com/in/mbe750/     Guest Resources Mentioned   AquaFlow – Reduce Water Bills with Smart Water Valves  International Performance Measurement and Verification Protocol  Bernoulli's Equation  Venturi Theory  Boyle's Law  NSF/ANSI/CAN 61 Testing and Certification   IAPMO R&T Water Systems Certification  Kiwa NSF/ANSI/CAN 61 Certification  Siemens Process Instrumentation  Honeywell Flow Meters    Scaling UP! H2O Resources Mentioned  AWT (Association of Water Technologies)  Scaling UP! H2O Academy video courses  Submit a Show Idea  The Rising Tide Mastermind      Words of Water with James McDonald  Today's definition is a measure of the tendency of a volatile substance, such as a neutralizing amine, to remain in the steam phase. It is defined as the ratio of the concentration of the substance in the steam phase to its concentration in the liquid phase. Can you guess the word or phrase?    2026 Events for Water Professionals  Check out our Scaling UP! H2O Events Calendar where we've listed every event Water Treaters should be aware of by clicking HERE.    This episode made possible through our valued partners at:   

The hosts for the 2026 Wisconsin Farm Technology Days, No Joke Dairy in Stratford, are examples of what a partnership with Focus on Energy can accomplish. Pam Jahnke visits with Matt Redetzke, one of the brothers farming, about their fifth-generation family farm in Marathon County. Through careful planning with Focus on Energy, the farm has achieved considerable savings on several projects around the farm. Focus on Energy Advisor, Kevin Weiler, explains the amount of energy saved - and the money that was kept in the farm families pocket! Energy Efficiency Upgrades with Focus on EnergyNo Joke Dairy has implemented a series of energy-saving improvements in partnership with Focuson Energy:• Livestock Waterers (Installed in 2022 and 2023)o Installed new waterers that use less electricity and keep water from freezing in winter.The cows always have clean water to drink, even during the colder months. Thesewaterers save money on energy bills and keep the animals comfortable. • LED Exterior Lighting (2023)o Replaced exterior lights with LED lights. LEDs make outdoor areas safer for everyoneand last longer, reducing the need to replace them as often.• Refrigeration Heat Recovery (RHR) System (2020)o Installed an RHR system that takes heat from the milk-cooling process and uses it towarm water for the farm. The farm needs less electricity or fuel to make hot waterfor cleaning. • Variable Frequency Drive (VFD) Vacuum Pump (2019)o Upgraded to a vacuum pump with a VFD to allow the milking system to run at the powerneeded, instead of at full power all the time. This reduces electricity use and extendsequipment life. • High-Bay LED Fixtures (2019)o Improved lighting inside the barn with high-bay LED fixtures to create a brighter, saferworkspace while using less energy than traditional high-intensity lamps.See omnystudio.com/listener for privacy information.

See omnystudio.com/listener for privacy information.

See omnystudio.com/listener for privacy information.

Morning Sermon from 12 July

You can't rewrite a blueprint you've never let yourself look at, and that goes for your relationships too.Buckle up, because we're kicking off the High Self-Worth Summer series with the foundational piece nobody wants to touch: the relational trauma you carry from your relationship with your parents. And before you say "but Dr. Morgan, my parents and I are great now", that's exactly why you need this one. This isn't about blame. There are ways your parents failed you, and they were doing the best they could with what they had. Both are true. In this episode I'm walking you through why avoiding this work quietly runs your love life, your friendships, and even your career and how to finally examine, process, and release what you've been carrying so you can stop recreating that familiar (not safe) emotional home.Inside the episode:The Mother & Father Wounds: Explores how early caregiving shapes self-worth ("Am I too much?") and external relationship patterns (trusting steady love, proving worth).Repetition compulsion in plain terms — why your nervous system chases familiar over healthy, and how that keeps you dating the same emotionally unavailable person in a new outfit until you look at the blueprint.Becoming the love scientist — the exact practice for noticing your patterns in real time: who you're attracted to, what triggers you, what you tolerate, and how you talk to yourself.Ready to do the work?The pattern isn't your fault, but the healing is your responsibility, and I've made it easy. Grab the Identity Reset ($47), my go-to course with a daily journal, rewiring prompts, and self-soothing strategies. It's 10 minutes a day and it's the one thing over a thousand people tell me changed everything.

A new law in Virginia will put a device limiting the speed of cars of frequent or outrageous speeders to the posted limit. Do you like the idea? Chad opens Swift Takes! with that topic before moving to a couple more.

With temperatures soaring across Europe in recent weeks, the debate about the necessity of air conditioning in homes has sparked in France once again.Is this an inevitable conclusion as the continent experiences high temperatures, and what would the environmental impact of the move be?Commentator John Gibbons joins Matt for The Last Word on the Environment.Hit the ‘Play' button on this page to hear the piece.

Hello and welcome to Handgun Radio! I'm your host Ryan Michad, Weerd Beard & Co from the wild woods of Central Maine and this is your home for all the news, information and discussion in the handgunning world!   This week we talk Developmental Dead Ends!   Please check out the Patriot Patch Company for their awesome patches and other high quality  items! Visit www.patriotpatch.co for more information! Cool artist “proof” rendition come along with the latest patch of the month patches!    Thank you to all our patreons! Visit us at https://www.patreon.com/handgunradio    Week In Review:   Ryan: -Back from a short hiatus; been a busy few weeks. In the space of a week, water heater died out, that same day, the fridge died out. So new fridge delivered and installed, new water heater installed. -Installing a new 1TB SSD for my PS5. Installed an external hard drive but you can't play PS5 games directly from it, only archive them.  -Been doing some fishing with Connor! Actually going to go after we record. Haven't had much luck but hoping to change that. Done rivers mostly but theve been fast and high. -Cut the hell of out my thumb. Nice meat cleaver action! -October Road Trip!   Weerd: MOVING!   Drink Segment:  Moving….so too much   Main Topic: Developmental Dead Ends   From Listener G: I have an idea for a show topic. Guns of the future that wasn't/or has yet to come. I think this is great, because yall can dive into the developmental dead ends of the firearms industry. I think this could act as a platform to talk about what yall think was truly a dead end and what may be brought forward into future development.   I took a day to think this over and compiled a list of examples that I think are fitting:   The Dardick (trounds and revolving “cylinder”) Calico (helical magazine) Stuff and Things Mars automatic (desert eagle part 1)   Frommer Stop (my personal favorite)(long recoil handguns) Jo.Lo.Ar and others (single hand chambering firearms) Webley-Fosbury/Mataeba Unica 6 (recoil operated revolvers) Beretta 92 (this is just D.Od bait) Last is a big list with all of the attempts at caseless ammunition: HK G11 Daisy V/L (the only ‘successful' one in my opinion) Volcanic (arguably the second most successful attempt) Gyrojet   Wrap Up: Don't forget to shop Brownells using our affiliate link! Head to firearmsradio.net and click the affiliate link in the upper right hand corner! Be sure to go like Handgun Radio on facebook and share it with your friends! Leave us a review on iTunes! Listen to all the great shows on the Firearms Radio Network! Check out the Patriot Patch Company!! www.patriotpatch.co   Weerd where can people find you? Assorted Calibers Podcast,  Weer'd World   Oddball gunscarstech.com Assorted Calibers Podcast ACP and HGR Facebook Play screechingtires.wav   David Assorted Calibers Podcast ACP and HGR Facebook Blue Collar Prepping Brena Bock Author Page David Bock Author Page Team And More Xander: Assorted Calibers Podcast Here so Ryan doesn't do a bad impression of me   Until next week, have fun & safe shooting!  

Want us to look at your studio and find the quick wins then book a free 15-minute discovery call. Follow the show so you never miss an episode: Spotify Apple Podcasts YouTube Instagram Reece and Summer own a studio that's just hit 0% churn at 200-plus members, with Reece finally off the floor after 11 years and a million-dollar studio on track for their one-year anniversary. In this episode I sit down with both of them to break down exactly how they did it. Everyone says they want to work on the business instead of in it. Almost nobody does, because it was never really a time problem. It's that the whole business lives in the owners' heads, and getting it out means becoming a different kind of owner. They did it one system at a time. Killed free trials. Installed a paid intro. Learned the sales script so Reece could hand it off. Brought on a VA and got 20 hours a week back. Built a retention system the whole team runs. And somewhere in there, Reece stopped seeing himself as "just a PT" while Summer kept the vision and the systems pointed at where they're actually going. In this episode you'll hear: Why getting off the floor is an identity shift, not a scheduling fix Why we kill free trials and install a paid intro instead How to learn a sales script so someone else can run it for you The right way to bring on a VA, and the feedback loop that makes it stick The retention system holding a 200-plus member studio at 0% churn Why every member gets allocated to a named trainer The vision book, the Polaroid wall, and the "make yourself proud" standard Why looking at your numbers every week is the unlock, not the threat Reece and Summer's advice for anyone standing where they were a year ago If this one resonated, go back and listen to "The Retention Revolution: What the Top 1% of Studios Are Doing Differently". It's a perfect follow-on. And if your head's spinning and you're thinking "okay, what do I actually do now" - book a free 15-minute discovery call and we'll look at how your studio's going right now and where the quick-win opportunities are. Chapters 00:00:00 12 months in: from burnt out to back-to-back record months 00:02:01 11 years on the floor, and why getting off it isn't about the hours 00:02:40 The first change: delegation and learning to trust the team 00:04:21 Why we killed free trials and installed a paid intro 00:06:05 Learning the sales script (and why it's not about being a closer) 00:08:11 Bringing on a VA: where to start and what to hand over first 00:12:20 Training a VA with playbooks and a feedback loop 00:13:55 The retention systems: going from feel to a real system 00:18:45 The Polaroid wall and 0% churn at 200-plus members 00:20:43 Allocating every member to a trainer: the secret past 350 00:22:17 What "working on the business" actually means 00:23:54 The vision book and the three-year picture 00:28:35 The identity shift from trainer to leader 00:31:52 Leaving for the summit, and what they found on return 00:36:18 What's next: more locations, more impact 00:40:05 The advice: right people, know your numbers, lean in

 Questions? Comments? We love feedback! Email us at info@baishavaad.org Rav Yosef GreenwaldQuestion: A roofer was hired to install an attic fan. Unfortunately, he went to the wrong address and installed it in the wrong house. He sends a bill to the house where he installed the fan. Does the homeowner who never asked for the fan have to pay for it?Answer: When the Gemara speaks about cases of “nehene”, it typically is speaking about when one person takes something from someone else. In this case, the homeowner isn't taking the fan from anyone else; rather, he had it foisted on him. This is, therefore, not a case of nehene.Instead, this would be a case of “yored l'sadeh chaveiro”. This refers to a Gemara in Bava Metziah where someone goes into his friend's field and plants a tree or does any form of work that upgrades the property, without being asked to do so. The halacha in such a case is that if the homeowner wants to keep the upgrade, he would have to pay a certain amount, but he would not have to pay the full value of the service. Since he did not contract the worker to work in his field, he doesn't have to pay for the job as if he had. Instead, he only has to pay the amount that his property went up in value as a result of the upgrade, which is a relatively small amount.Additionally, he cannot be forced to accept the addition to his field, so he can tell the worker to take back the upgrade he made to his property. In this case, that would mean that he can theoretically tell the worker to take back the fan and fix the roof to be the way it was before. If he makes this request, it may not be worthwhile for the roofer to do all that extra work and he may just decide to leave it there for free.

If you've ever rounded a corner in Asheville and come face-to-face with a monumental ripple of forged steel, chances are you've stumbled across the handiwork of Rachel David of RED Metal. In a city teeming with murals and microbreweries, her abstract public sculpture “Fluvial”—a centerpiece of ArtsvilleUSA's Open // Air exhibition—refuses to be neatly filed away in the usual taxonomy of public art. Installed along the urban trail outside the old S&W Cafeteria and forged in the wake of Hurricane Helene, the piece is Rachel's meditation on how water carves, erases, and remakes everything it touches.In this episode, we explore what it takes to create art that belongs to everyone, from smashing through the old boys' club of metalsmithing to designing with a community's anxieties in mind. Along the way, Rachel recalls professors who nudged her off one path and onto another, wrestles with the realities of survival as a craftsperson, and muses on the power of public art in a city still haunted by the memory of a life-changing storm.Get Involved / Where to Find MoreExplore “Fluvial” in person in downtown Asheville or virtually in Open // Air.See Rachel's work at upcoming open studio tours: American Craft Council nationwide tour (July 18), the Haywood County Studio Tour (September, check the Haywood County Arts Council for details), and The Big Crafty (July 11 - 12).Watch for new work in the Haywood Community College Sculpture Garden later this year.Follow SIBS and SPARC to plug into inclusive metalsmithing.Contact & SocialWebsite: www.redmetal.netInstagram: @__redmetal__Facebook: @redmetal1245Episode CreditsHost: Elise Wilson, ArtsvilleUSA Executive DirectorGuest: Rachel David, Red MetalProduced by: ArtsvilleUSA / Arterial Inc.Newsletter: Subscribe to the ArtsvilleUSA Newsletter for more stories and updates on the arts and crafts scene in Western North Carolina.

Alpha Warrior and Josh Reid catch their breath after one of the wildest weeks in years. Iran's civilian government just ended the war, the Strait of Hormuz reopened, sanctions are coming off, and Trump's approval rating in Israel went from positive twenty three to negative twenty three in seven days. Save Israel for last is happening in real time. Mark Levin is having a public meltdown, the APEC lobby is in panic mode, and the MOU to Israel was never released. The bombshell of the episode comes when the guys catch what Trump quietly admitted at the G7. He installed Jolani in Syria with Erdogan before he was even back in office. That confirms the takedown of Assad and the dismantling of the Iran to Hezbollah land bridge were Trump's moves, not Bibi's, and it completely shreds the controlled by Israel narrative. From there they unpack the Jay Clayton ODNI nomination and his SDNY history with Maduro, the Cartel de los Soles generals, Epstein, the Weiner laptop, and the Clinton Foundation. Plus the Tulsi report driving a national emergency on election integrity, the Hochul Medicaid fraud indictment, Newsom's California DOJ investigating his own wife, and the eight man B-52 crash at Edwards that has the Mossad telegram channels celebrating.

-The recently resurrected Commodore is getting back into phones, but rather than taking on the likes of Apple and Samsung at their own game, the Commodore Callback 8020 is a proudly non-conformant flip phone that wouldn't have looked out of place in the '90s. -WhatsApp is finally offering what most of its contemporaries already have: disappearing (view-once) texts. -The White House app is reportedly coming to all devices managed by the Department of Homeland Security, whether the user wants to download it or not. GovExec that it was a "cause for alarm," as any app installed on government-issued devices can "potentially create backdoor access to government networks behind the firewall."  Learn more about your ad choices. Visit podcastchoices.com/adchoices

For the latest and most important news of the day | https://www.thecanadianpressnews.ca To watch daily news videos, follow us on YouTube | https://www.youtube.com/@CdnPress The Canadian Press on X (formerly Twitter) | https://twitter.com/CdnPressNews The Canadian Press on LinkedIn | https://linkedin.com/showcase/98791543

You already have the strategy - you can have the BEST strategy in the world - who you are BEING, leading, speaking, creating, behaving WITH that strategy is what actually creates results. We're diving into the missing signals that take you from a Silent NO to a Silent YES where women find you and say "I need to be in her world!" Tune in today! Join Silent YES Grab Your Copy of the RICHCODED Best Selling Book! Access our Free $10K Day Identity Recode Apply to the RICHCODED Mastermind Join the Fame Room Connect on Instagram

Introduction   Non-weather water damage costs insurers $13 billion a year. Interior leaks account for 39% of all homeowner claims. And yet most carriers still treat prevention as a brochure recommendation—send the homeowner a discount offer, hope they find a plumber, and call it a program. Paul Vacquier thinks that's why it isn't working.   Vacquier is the founder and CEO of Beagle Services, a water security company that solves the last-mile problem carriers and homeowners can't solve on their own: getting leak detection hardware actually installed, monitored, and maintained. A California-barred litigation attorney turned insurtech operator, he built the insurance carrier playbook at Flow Technologies before Moen acquired it. What he learned there—that the technology exists but deployment at scale does not—became the genesis for Beagle.   In this conversation, Josh Hollander and Vacquier dig into why the installation gap is where loss prevention falls apart, how the industry is shifting from carrot to stick on water shutoff requirements, and what Beagle's work with carriers like PURE tells us about where prevention programs are actually headed.   Guest Bio   Paul Vacquier is the Founder and CEO of Beagle Services, a water security company operating across 17 states that installs, monitors, and maintains automatic water shutoff valves and leak detection systems for insurance carriers, brokers, and homeowners. Before founding Beagle, he built the insurance carrier go-to-market at Flow Technologies, which was later acquired by Moen (now Flow by Moen). He is a California-barred litigation attorney who came to insurtech through the startup world.   Key Topics   • The last-mile problem nobody solved — Leak detection technology has existed for over a decade. The gap isn't the hardware—it's professional installation, ongoing monitoring, and maintenance at scale. Carriers recommend devices; homeowners can't find qualified installers; the device sits in a box. Beagle exists to close that gap.   • From carrot to stick — Carriers are shifting from discount incentives ("send us a photo of your installed valve") to hard underwriting requirements at specific coverage thresholds. High-net-worth carriers like PURE have led the way. Standard lines carriers are following. The stick is now backed by data.   • The compliance illusion — A photo of an installed device and a paid invoice doesn't mean the system is on and actively protecting the home. The same problem exists with alarm systems: discounts are given, but nobody checks if the alarm was set before you left for vacation. Beagle's Watchdog product monitors device status—online, offline, alert conditions—in real time.   • What Beagle does with the data — Watchdog ingests alert data across every installed system: high pressure, small drips, thermal expansion risk, shutoff frequency, device connectivity. When an alert fires, Beagle dispatches a service visit to fix the underlying problem—toilet flappers, angle stops, pressure regulators—before it becomes a claim.   • Scaling a physical services business — Unlike SaaS, physical services don't go straight to margin as you grow. The key variable is drive time: how many installs can a technician complete per day in Atlanta, Los Angeles, or Dallas? Beagle grows market-by-market only when carrier partners generate enough demand to support a full-time local team, which drives economies of scale that lower costs for everyone.   • AI can't turn a wrench — Beagle uses AI for route optimization and operational efficiency, and is training internal models as a knowledge base for field technicians and customer service. But the core product requires humans on-site at every property. No bot can cut the pipe.   Notable Quotes   "Most carriers still treat prevention as a brochure recommendation rather than an operational program."   "You'd have a picture of the installed device and a paid invoice—but that doesn't necessarily mean the system is on and active protecting the home."   "The AI can't turn a wrench. No matter how smart the valves get, you still have to put it on. Until that day comes, we'll be here."   "Beagle's intent is to be a proactive, preventative maintenance plumbing company. All we do is referred-in work to help prevent leaks from occurring."   Resources   Guest: • Beagle Services: https://www.beagleservices.com • Paul Vacquier on LinkedIn: hhttps://www.linkedin.com/in/paulvacquier/   Host & Organization: • Joshua R. Hollander on LinkedIn: https://www.linkedin.com/in/joshuarhollander/ • Horton International (USA): https://www.horton-usa.com/ • Insurtech Leadership Podcast (LinkedIn Showcase): https://www.linkedin.com/showcase/insurtech-leadership-show   Subscribe & Review   If you enjoyed this episode, subscribe on your favorite platform and leave a review. The Insurtech Leadership Podcast is available on YouTube, Apple Podcasts, and Spotify.

More e-bike chargers are coming to New Zealand's cycling trails - in what's being touted as an economic boost for the regions. Hauraki Rail Trail CEO Diane Drummond spoke to John Campbell.

EZO, Ireland's largest private electric vehicle (EV) charging network, has today announced a new partnership with eir, launching the first of a series of dedicated high-speed urban EV charging hubs. Dublin's Walkinstown marks the beginning of this rollout, following the successful programme where EZO and eir converted 109 public payphone kiosks into EV charging stations across 13 local authorities. The Walkinstown site is the first of 50 purpose-built EZO-eir hubs planned around the country, designed to significantly improve urban charging coverage, user access and charging speeds for the growing number of electric vehicle drivers nationwide. Unlike traditional single-point charging locations, the hubs are engineered as high-capacity urban charging destinations, providing multiple ultra-fast chargers in one place to reduce wait times and deliver a more convenient experience. These new hubs also demonstrate how existing infrastructure can be efficiently adapted to support Ireland's transport transition. Established locations are being utilised by repurposing former eir telephone exchanges and upgrading operational eir depots into modern high-performing charging facilities. The Walkinstown hub, which is an operational eir depot, features three 200kW ultra-fast chargers, enabling drivers to rapidly recharge and return to the road in minutes. Strategically located in a high-demand urban area, it represents a new model of EV infrastructure focused on scale, speed and accessibility. The multi-charger hubs mark a major step forward in the EZO's strategy to deliver true national urban coverage and meet accelerating EV adoption with infrastructure designed for future demand. EZO CEO Ollie Chatten said: "The EZO–eir partnership combines telecommunications infrastructure expertise with EV technology and operations capability, enabling rapid deployment of high-speed charging facilities in prime urban locations." "The launch of our first dedicated EV charging hub is a pivotal moment for EZO and for Ireland's EV infrastructure. These hubs are about looking forward and delivering faster charging, better access and urban coverage at scale. As EV adoption continues to grow in Ireland, drivers need infrastructure that is designed for convenience and reliability. Our nationwide hub rollout will play a critical role in enabling that future." eir CEO Oliver Loomes said: "We are pleased to progress our work with EZO, having already converted 109 former public payphone kiosks into modern EV charging stations. Our broadband and fibre networks virtually connect the people of Ireland, and this project represents a natural evolution of our commitment to nationwide connectivity. "By transforming our network of buildings in urban areas into accessible EV charging points, we are extending that connection to people and communities on the ground. This collaboration will expand the accessibility of EV charging across Ireland, utilising eir-owned sites to deliver more sustainable infrastructure and helping drive environmental progress in a meaningful and practical way." See more breaking stories here.

  // GUEST // X: ⁠https://x.com/TomBilyeu⁠ Website: ⁠https://www.tombilyeu.com⁠   // SPONSORS // Blockware Solutions: ⁠⁠⁠⁠⁠https://mining.blockwaresolutions.com/breedlove⁠⁠⁠⁠⁠ Performance Lab Supplements: ⁠⁠⁠⁠⁠https://www.performancelab.com/breedlove⁠⁠⁠⁠⁠ The Farm at Okefenokee: ⁠⁠⁠⁠⁠https://okefarm.com/⁠⁠⁠⁠ // PRODUCTS I ENDORSE // Protect your mobile phone from SIM swap attacks: ⁠⁠⁠⁠⁠https://www.efani.com/breedlove⁠⁠⁠⁠⁠ Lineage Provisions (use discount code BREEDLOVE): ⁠⁠⁠⁠⁠https://lineageprovisions.com/?ref=breedlove_22⁠⁠⁠⁠⁠ Colorado Craft Beef (use discount code BREEDLOVE): ⁠⁠⁠⁠⁠https://coloradocraftbeef.com/⁠⁠⁠⁠⁠ Salt of the Earth Electrolytes: ⁠⁠⁠⁠⁠http://drinksote.com/breedlove⁠⁠⁠⁠⁠ Jawzrsize (code RobertBreedlove for 20% off): ⁠⁠⁠⁠⁠https://jawzrsize.com⁠⁠⁠⁠⁠   // UNLOCK THE WISDOM OF THE WORLD'S BEST NON-FICTION BOOKS // ⁠⁠⁠⁠⁠https://course.breedlove.io/⁠⁠⁠⁠⁠   // SUBSCRIBE TO THE CLIPS CHANNEL // ⁠⁠⁠⁠⁠https://www.youtube.com/@robertbreedloveclips2996/videos⁠⁠⁠⁠   // TIMESTAMPS // 0:00 – WiM Episode Trailer 1:27 – Podcast Begins 6:00 – What Is Inflation? Why the Word Is a Euphemism for Theft 12:08 – Mine Bitcoin with Blockware Solutions 13:10 – Money as a Call Option: Self-Ownership and Property Rights 22:00 – The Fiat Pyramid Scheme: From Gold to Central Banking 32:00 – Scarcity, the Five Properties of Money, and Why Gold Won 44:00 – The Dollar as a One-Node Database: Who Controls the List 55:00 – Zombie Companies, Capitalism, and the Darwinian Corruption of Fiat 1:09:50 – Performance Lab Supplements 1:11:00 – Bitcoin as Inviolable Property: The Gutenberg Moment 1:22:00 – Can Governments Stop Bitcoin? The Logic of Violence and History 1:35:00 – 21 Million, Divisibility, and the Zero-Sum Misconception 1:42:39 – The Farm at Okefenokee 1:43:40 – Multi-Sig, Self-Custody, and the Spectrum of Sovereignty 2:10:48 – Protect Yourself From SIM Swaps 2:11:54 – Unlock the Wisdom of the Best Non-Fiction Books // PODCAST // Podcast Website: ⁠⁠⁠⁠⁠⁠https://whatismoneypodcast.com/⁠⁠⁠⁠⁠⁠ Apple Podcast: ⁠⁠⁠⁠⁠⁠https://podcasts.apple.com/us/podcast/the-what-is-money-show/id1541404400⁠⁠⁠⁠⁠⁠ Spotify: ⁠⁠⁠⁠⁠⁠https://open.spotify.com/show/25LPvm8EewBGyfQQ1abIsE⁠⁠⁠⁠⁠⁠ RSS Feed: ⁠⁠⁠⁠⁠⁠https://feeds.simplecast.com/MLdpYXYI⁠⁠⁠⁠⁠⁠   // SUPPORT THIS CHANNEL // Bitcoin: 3D1gfxKZKMtfWaD1bkwiR6JsDzu6e9bZQ7 Sats via Strike: ⁠⁠⁠⁠⁠⁠https://strike.me/breedlove22⁠⁠⁠⁠⁠⁠ Paypal: ⁠⁠⁠⁠⁠⁠https://www.paypal.com/paypalme/RBreedlove⁠⁠⁠⁠⁠⁠ Venmo: ⁠⁠⁠⁠⁠⁠https://account.venmo.com/u/Robert-Breedlove-2⁠⁠⁠⁠⁠⁠   // SOCIAL // Breedlove X: ⁠⁠⁠⁠⁠⁠https://x.com/Breedlove22⁠⁠⁠⁠⁠⁠ WiM? X: ⁠⁠⁠⁠⁠⁠https://x.com/WhatisMoneyShow⁠⁠⁠⁠⁠⁠ Linkedin: ⁠⁠⁠⁠⁠⁠https://www.linkedin.com/in/breedlove22/⁠⁠⁠⁠⁠⁠ Instagram: ⁠⁠⁠⁠⁠⁠https://www.instagram.com/breedlove_22/⁠⁠⁠⁠⁠⁠ TikTok: ⁠⁠⁠⁠⁠⁠https://www.tiktok.com/@breedlove22⁠⁠⁠⁠⁠⁠ Substack: ⁠⁠⁠⁠⁠⁠https://breedlove22.substack.com/⁠⁠⁠⁠⁠⁠ All My Current Work: ⁠⁠⁠⁠⁠⁠https://linktr.ee/robertbreedlove⁠

Allen covers NextEra’s potential $400 billion buy of Dominion Energy, US developers racing the July tax credit deadline, Ming Yang scouting Spain for a factory, Turkey opening its first offshore wind tender, and Hornsea 3’s first foundation going in. Sign up now for Uptime Tech News, our weekly email update on all things wind technology. This episode is sponsored by Weather Guard Lightning Tech. Learn more about Weather Guard’s StrikeTape Wind Turbine LPS retrofit. Follow the show on Facebook, YouTube, Twitter, Linkedin and visit Weather Guard on the web. And subscribe to Rosemary Barnes’ YouTube channel here. Have a question we can answer on the show? Email us! Allen Hall 2025: Good morning, everyone. The world is racing at the minute, and let’s start with the biggest race of all. NextEra Energy, the largest utility in America by market value, is in talks to buy Dominion Energy of Virginia. The price? It’s about $76 a share, roughly $66 billion. With debt, the combined company would be valued at about $400 billion. That would make it the largest power deal on record. A mostly stock transaction, at least that’s what’s being reported, and a deal could come as soon as this week. Pretty shocking. Now, why does this matter to wind? NextEra is [00:01:00] not just a utility. It is one of the largest renewable energy developers on the planet. And Dominion sits on top of Northern Virginia’s data center alley, the biggest concentration of data centers in the country. Dominion expects its peak demand to double by the end of the twenty-thirties, American power consumption hit a second straight record in twenty-twenty-five, and it’s still climbing. So the company that builds more wind and solar than almost anyone wants to merge with the company that serves the hungriest grid in America. That is a race to the top. But down on the ground, developers are running a very different kind of race. Wind projects under construction in the United States are up 60% since the start of twenty-twenty-five. Solar is up about 50%. Why the surge? Well, the clock is ticking. Tax credits for wind and solar were gutted in the one big beautiful bill. Projects must begin construction by July 4th [00:02:00] and prove they are building continuously to qualify. Under the Inflation Reduction Act, those credits were supposed to phase out at the end of twenty-thirty-three. Now that deadline is just a couple of weeks away. Developers are pushing hard on projects that can make it and abandoning the ones that cannot. One solar executive put it plainly: “A lot of the projects are going to die on the vine.” And that’s a real shame. Labor is short. Of course, electricians are in demand. Transformer lead times have stretched to 18 months because data centers are buying them too. Even permits are hard to get. Projects that touch federal land, of course, that once took a month to approve are now waiting up to a year. So while NextEra races to buy the grid, developers are racing to build before the door shuts. Now, across the Atlantic, there’s a different kind of race going on. Chinese turbine manufacturer MingYang [00:03:00] Smart Energy is looking for a new home, and quick. Back in March, Britain blocked the company’s plans for a one-and-a-half billion pound factory in Scotland, mostly based on security grounds. MingYang’s European chief, Horatio Evers, says the company is now talking to Spain and scouting other locations on the continent. He says MingYang wants to build turbines in Europe with a European workforce. And this is the part I don’t understand, ’cause European workforce tend to be more expensive. However, uh, MingYang wants to build that factory, but there’s a condition. They need a guarantee that their turbines will be allowed into the market, and so far that hasn’t happened. The European Commission launched a review of Chinese manufacturers back in 2024. Those findings are still unpublished. So MingYang is racing to find a country willing to say “Yes.” Further east, Turkey is entering the offshore wind [00:04:00] race for the first time. The government has defined four areas along its western coast, all on the Aegean, for its first ever offshore wind tender. Turkey’s energy minister says Turkey aims for five gigawatts of offshore wind by 2035. The country has committed $30 billion to transmission infrastructure. And Turkey already has 15 gigawatts of onshore wind spinning today. Turkey is, of course, a NATO ally, and it straddles Europe and Asia, and now it’s stepping into offshore wind. And finally, up in the North Sea, off the coast of Norfolk, England, 75 miles from shore, Cadeler of Copenhagen just installed the first monopile foundation at Hornsea 3. When complete, Hornsea 3 will be the single largest offshore wind farm on the planet. 2.9 gigawatts, 197 foundations, enough power for 3.3 [00:05:00] million British homes. The project is owned by Danish giant Ørsted and will bring 5,000 construction jobs to the region. Hornsea 1 and 2 are already spinning, and of course, Hornsea 4 is on the drawing board. So here’s the picture. America’s two biggest utilities are racing toward a $400 billion merger. Developers are sprinting to break ground before the Fourth of July. A Chinese turbine maker is searching Europe for a factory, and Turkey is marking out its first offshore wind zones. And over in Britain, they just planted the first foundation at the world’s largest wind farm. Everyone is racing. The only question is, who gets there first? And that’s the state of the wind industry for the 18th of May, 2026. Join us tomorrow for the Uptime Wind Energy podcast

See omnystudio.com/listener for privacy information.

WBZ NewsRadio’s Chris Fama reports.See omnystudio.com/listener for privacy information.

Duji insists on having cable installed to her basement TV. The mother of the girl who had the baseball stolen from her at the Guardians game calls into the show. Lisa Kudrow interview reveals the cast of Friends makes $20 million a year in residuals. See omnystudio.com/listener for privacy information.

Duji insists on having cable installed to her basement TV. The mother of the girl who had the baseball stolen from her at the Guardians game calls into the show. Lisa Kudrow interview reveals the cast of Friends makes $20 million a year in residuals. 

In this hilarious Jubal Phone Prank, what should’ve been a simple TV installation call quickly turns into total chaos. When a woman tries to schedule a service appointment, the “installer” takes things in a wildly unprofessional—and completely unexpected—direction. What starts as a normal conversation spirals into one of the most outrageous phone calls you’ll hear. Will she hang up? Will she lose it? Or is there more going on than it seems? The wildest, most hilarious prank call podcast from The Jubal Show! Join Jubal Fresh as he masterminds the funniest and most outrageous phone pranks, catching unsuspecting victims off guard with his quick wit, absurd scenarios, and unmatched comedic timing. Whether he's posing as an over-the-top customer service rep, a clueless boss, or an eccentric neighbor, no call is safe from his unpredictable humor. Get ready to laugh out loud and cringe in the best way possible! New episodes drop every weekday—tune in and let the prank wars begin!➡︎ Submit your Jubal Phone Prank - https://thejubalshow.com This is just a tiny piece of The Jubal Show. You can find every podcast we have, including the full show every weekday right here…➡︎ https://thejubalshow.com/podcasts The Jubal Show is everywhere, and also these places: Website ➡︎ https://thejubalshow.com Instagram ➡︎ https://instagram.com/thejubalshow X/Twitter ➡︎ https://twitter.com/thejubalshow Tiktok ➡︎ https://www.tiktok.com/@the.jubal.show Facebook ➡︎ https://facebook.com/thejubalshow YouTube ➡︎ https://www.youtube.com/@JubalFresh Support the show: https://the-jubal-show.beehiiv.com/subscribeSee omnystudio.com/listener for privacy information.

In this hilarious Jubal Phone Prank, what should’ve been a simple TV installation call quickly turns into total chaos. When a woman tries to schedule a service appointment, the “installer” takes things in a wildly unprofessional—and completely unexpected—direction. What starts as a normal conversation spirals into one of the most outrageous phone calls you’ll hear. Will she hang up? Will she lose it? Or is there more going on than it seems? The wildest, most hilarious prank call podcast from The Jubal Show! Join Jubal Fresh as he masterminds the funniest and most outrageous phone pranks, catching unsuspecting victims off guard with his quick wit, absurd scenarios, and unmatched comedic timing. Whether he's posing as an over-the-top customer service rep, a clueless boss, or an eccentric neighbor, no call is safe from his unpredictable humor. Get ready to laugh out loud and cringe in the best way possible! New episodes drop every weekday—tune in and let the prank wars begin!➡︎ Submit your Jubal Phone Prank - https://thejubalshow.com This is just a tiny piece of The Jubal Show. You can find every podcast we have, including the full show every weekday right here…➡︎ https://thejubalshow.com/podcasts The Jubal Show is everywhere, and also these places: Website ➡︎ https://thejubalshow.com Instagram ➡︎ https://instagram.com/thejubalshow X/Twitter ➡︎ https://twitter.com/thejubalshow Tiktok ➡︎ https://www.tiktok.com/@the.jubal.show Facebook ➡︎ https://facebook.com/thejubalshow YouTube ➡︎ https://www.youtube.com/@JubalFresh Support the show: https://the-jubal-show.beehiiv.com/subscribeSee omnystudio.com/listener for privacy information.

Earlier this week, activists were holding a peaceful march in the port city of KuGompo - formerly East London, but disorder erupted after a protester said he was attacked by a foreigner, prompting demonstrators to damage several vehicles and shops. The trouble came amid tension over the recent installation of a Nigerian community leader in the city, who has a traditional title that can be translated as "king of the Igbo people in East London". We hear from a Nigerian community leader in Scotland. Also, what's causing the decline in the populations of cheetahs in Somaliland and the Horn of Africa region? We hear from a conservation organisation. Presenter : Nkechi Ogbonna Producers: Keikantse Shumba, Bella Twine and Blessing Aderogba Technical Producer: David Kinyanjui Senior Producer: Charles Gitonga Editor: Maryam Abdalla

What's it really like to work with Christa Gurka?In this episode of the Female emPOWERED Podcast, Christa Gurka steps out of her comfort zone and lets the results speak for themselves. Instead of teaching a strategy or business framework, Christa shares real testimonials from women inside the Fit Biz community — Pilates studio owners, physical therapists, and wellness entrepreneurs who are building profitable, sustainable businesses.You'll hear directly from business owners who have: ✔ Doubled their revenue ✔ Built teams and stepped out of full-time treatment ✔ Increased their salaries while working fewer hours ✔ Installed systems that allow them to take real vacations ✔ Built profitable PT practices, Pilates studios, and wellness businessesThese women share the real impact of coaching, mentorship, and community — and how having the right framework, accountability, and support helped them grow as CEOs.If you've ever wondered: • What does business coaching actually do for a studio owner? • How do boutique fitness and PT practice owners scale sustainably? • Is mentorship worth the investment for wellness entrepreneurs?This episode gives you the answer straight from the women doing the work.What You'll Learn in This Episode• How boutique fitness and wellness owners are scaling their businesses • Why systems and structure matter more than “marketing tricks” • How studio owners transition from practitioner to CEO • The role of mentorship and community in business growth • Real revenue growth stories from Pilates, PT, and wellness businessesWho This Episode Is ForThis episode is perfect for:• Pilates studio owners • Physical therapy clinic owners • Boutique fitness studio owners • Wellness entrepreneurs • Female business owners in the health and fitness industry • Anyone looking to build a profitable and sustainable wellness businessJoin the Fit Biz CommunityIf you're ready to create more structure, profitability, and freedom in your business, start here:

⁠

Caltrans preps for tomorrow's No Kings protests with freeway gates. Some background on this year's very active rattlesnake season. One of South LA's only golf courses reopens this weekend. Plus, more from Evening Edition. Support The L.A. Report by donating at LAist.com/join and by visiting https://laist.comSupport the show: https://laist.com

Gates are going up along the 101 to keep tomorrow's "No Kings" protests off the freeway. A former LA Unified employee is accused of being part of the one of the largest money laundering schemes in district history. UCLA sues to stop the Riverside County Sherriff's investigation into the Prop 50 election. Plus, more from Morning Edition. Support The L.A. Report by donating at LAist.com/join and by visiting https://laist.comSupport the show: https://laist.com

Anto Yeldezian is a Tāmaki-based artist of Armenian heritage, who works amongst an expanded painting practice that often leans into methodologies of printmaking. Utilising methods of monoprinting, and stencils, along with a playful use of paint and material exploration. Within his current solo show Desert Island on at Coastal Signs, Yeldezian presents a series of 7 large scale works on raw loose canvas. Installed in a manner in which the works almost engulf the gallery walls, and bring the space into a continuous field of symbols, and marks.  The works themselves harness this heavy use of motifs, and symbols as a kind of centering point to the show. The references include camels, palm trees, oil pump-jacks, Homer Simpson's thirsty bird'; ancient fossils, the triple Gs of Canterbury Clothing Company, union jacks and logos of American defence and oil companies.  Through the making of the work Yeldezian takes these symbols and applies them to various painterly techniques that almost pull them away from their own inherent meanings/references and into this place of a pattern-like language with its own set of meanings. Maya caught up with Anto about the show as well as his overall practice.

Born to Breed Cycle: was installed in you before YOU were conceived #wakeup #4bthey use #FOMO to keep you n the procreation sedation loop so their ELITE pockets can fill up w the lowly consumers/buyersThink about the messages people hear their entire lives.“You'll regret not having kids.”“You'll miss out on the meaning of life.”“You're selfish if you don't want a family.”“You'll be alone when you're older.”“It's what you're supposed to do.”These messages are not random.They are part of social conditioning that has existed for generations & centuries https://www.patreon.com/11660344/join learn to unlearn #family#fantasy

Send us Fan MailAfter years of managing rental property doors the traditional way—with keys, lockboxes, and coordinating access with contractors—Kevin and I decided it was finally time to try something different. In this episode of the Your Landlord Resource Podcast, we talk about why we installed smart locks on our rental properties and what we've learned from using them.We walk through the exact lock we chose, the Kwikset Halo touchscreen smart lock, and why it made sense for our properties. For us, the biggest benefit has been convenience. Instead of driving three hours round-trip to meet a contractor or cleaner, we can now create temporary access codes, monitor entry remotely, and lock the door from anywhere using the app.Smart locks have also made life easier for our tenants. They can enter with a code if they forget their keys, and families or roommates can each have their own access code. It also allows us to quickly change access between tenants without calling a locksmith or replacing the entire lock.Of course, smart locks are not perfect for every property so we also discuss the downsides like battery maintenance, the need for reliable Wi-Fi, installation costs, and situations where a traditional lock might still make more sense.If you're a self-managing landlord looking to create better systems and save time coordinating access to your units, this episode will give you a realistic look at whether smart locks are worth it.Links & ReferencesQuickset Halo Smart Lock Touchscreen & DeadboltQuickset Halifax Door KnobEpisode 66 Midterm Rentals ExplainedEpisode 103 We Installed Property-Wide Wi-Fi. The Pros, Cons & What to KnowConnect with Us: 

No new bus shelters were installed in Clare last year. Figures released by the Department of Transport show 2024 was the last time a shelter was put in place in this county. The data shows 31 such structures have been erected in Clare since 2018 however which is the seventh highest figure nationwide. Ennis Green Party representative Bridget Ginnity believes the drop-off is down to the change of government.

Join Kyle, Nader, Vibhu, and swyx live at NVIDIA GTC next week!Now that AIE Europe tix are ~sold out, our attention turns to Miami and World's Fair!The definitive AI Accelerator chip company has more than 10xed this AI Summer:And is now a $4.4 trillion megacorp… that is somehow still moving like a startup. We are blessed to have a unique relationship with our first ever NVIDIA guests: Kyle Kranen who gave a great inference keynote at the first World's Fair and is one of the leading architects of NVIDIA Dynamo (a Datacenter scale inference framework supporting SGLang, TRT-LLM, vLLM), and Nader Khalil, a friend of swyx from our days in Celo in The Arena, who has been drawing developers at GTC since before they were even a glimmer in the eye of NVIDIA:Nader discusses how NVIDIA Brev has drastically reduced the barriers to entry for developers to get a top of the line GPU up and running, and Kyle explains NVIDIA Dynamo as a data center scale inference engine that optimizes serving by scaling out, leveraging techniques like prefill/decode disaggregation, scheduling, and Kubernetes-based orchestration, framed around cost, latency, and quality tradeoffs. We also dive into Jensen's “SOL” (Speed of Light) first-principles urgency concept, long-context limits and model/hardware co-design, internal model APIs (https://build.nvidia.com), and upcoming Dynamo and agent sessions at GTC.Full Video pod on YouTubeTimestamps00:00 Agent Security Basics00:39 Podcast Welcome and Guests07:19 Acquisition and DevEx Shift13:48 SOL Culture and Dynamo Setup27:38 Why Scale Out Wins29:02 Scale Up Limits Explained30:24 From Laptop to Multi Node33:07 Cost Quality Latency Tradeoffs38:42 Disaggregation Prefill vs Decode41:05 Kubernetes Scaling with Grove43:20 Context Length and Co Design57:34 Security Meets Agents58:01 Agent Permissions Model59:10 Build Nvidia Inference Gateway01:01:52 Hackathons And Autonomy Dreams01:10:26 Local GPUs And Scaling Inference01:15:31 Long Running Agents And SF ReflectionsTranscriptAgent Security BasicsNader: Agents can do three things. They can access your files, they can access the internet, and then now they can write custom code and execute it. You literally only let an agent do two of those three things. If you can access your files and you can write custom code, you don't want internet access because that's one to see full vulnerability, right?If you have access to internet and your file system, you should know the full scope of what that agent's capable of doing. Otherwise, now we can get injected or something that can happen. And so that's a lot of what we've been thinking about is like, you know, how do we both enable this because it's clearly the future.But then also, you know, what, what are these enforcement points that we can start to like protect?swyx: All right.Podcast Welcome and Guestsswyx: Welcome to the Lean Space podcast in the Chromo studio. Welcome to all the guests here. Uh, we are back with our guest host Viu. Welcome. Good to have you back. And our friends, uh, Netter and Kyle from Nvidia. Welcome.Kyle: Yeah, thanks for having us.swyx: Yeah, thank you. Actually, I don't even know your titles.Uh, I know you're like architect something of Dynamo.Kyle: Yeah. I, I'm one of the engineering leaders [00:01:00] and a architects of Dynamo.swyx: And you're director of something and developers, developer tech.Nader: Yeah.swyx: You're the developers, developers, developers guy at nvidia,Nader: open source agent marketing, brev,swyx: and likeNader: Devrel tools and stuff.swyx: Yeah. BeenNader: the focus.swyx: And we're, we're kind of recording this ahead of Nvidia, GTC, which is coming to town, uh, again, uh, or taking over town, uh, which, uh, which we'll all be at. Um, and we'll talk a little bit about your sessions and stuff. Yeah.Nader: We're super excited for it.GTC Booth Stunt Storiesswyx: One of my favorite memories for Nader, like you always do like marketing stunts and like while you were at Rev, you like had this surfboard that you like, went down to GTC with and like, NA Nvidia apparently, like did so much that they bought you.Like what, what was that like? What was that?Nader: Yeah. Yeah, we, we, um. Our logo was a chaka. We, we, uh, we were always just kind of like trying to keep true to who we were. I think, you know, some stuff, startups, you're like trying to pretend that you're a bigger, more mature company than you are. And it was actually Evan Conrad from SF Compute who was just like, you guys are like previousswyx: guest.Yeah.Nader: Amazing. Oh, really? Amazing. Yeah. He was just like, guys, you're two dudes in the room. Why are you [00:02:00] pretending that you're not? Uh, and so then we were like, okay, let's make the logo a shaka. We brought surfboards to our booth to GTC and the energy was great. Yeah. Some palm trees too. They,Kyle: they actually poked out over like the, the walls so you could, you could see the bread booth.Oh, that's so funny. AndNader: no one else,Kyle: just from very far away.Nader: Oh, so you remember it backKyle: then? Yeah I remember it pre-acquisition. I was like, oh, those guys look cool,Nader: dude. That makes sense. ‘cause uh, we, so we signed up really last minute, and so we had the last booth. It was all the way in the corner. And so I was, I was worried that no one was gonna come.So that's why we had like the palm trees. We really came in with the surfboards. We even had one of our investors bring her dog and then she was just like walking the dog around to try to like, bring energy towards our booth. Yeah.swyx: Steph.Kyle: Yeah. Yeah, she's the best,swyx: you know, as a conference organizer, I love that.Right? Like, it's like everyone who sponsors a conference comes, does their booth. They're like, we are changing the future of ai or something, some generic b******t and like, no, like actually try to stand out, make it fun, right? And people still remember it after three years.Nader: Yeah. Yeah. You know what's so funny?I'll, I'll send, I'll give you this clip if you wanna, if you wanna add it [00:03:00] in, but, uh, my wife was at the time fiance, she was in medical school and she came to help us. ‘cause it was like a big moment for us. And so we, we bought this cricket, it's like a vinyl, like a vinyl, uh, printer. ‘cause like, how else are we gonna label the surfboard?So, we got a surfboard, luckily was able to purchase that on the company card. We got a cricket and it was just like fine tuning for enterprises or something like that, that we put on the. On the surfboard and it's 1:00 AM the day before we go to GTC. She's helping me put these like vinyl stickers on.And she goes, you son of, she's like, if you pull this off, you son of a b***h. And so, uh, right. Pretty much after the acquisition, I stitched that with the mag music acquisition. I sent it to our family group chat. Ohswyx: Yeah. No, well, she, she made a good choice there. Was that like basically the origin story for Launchable is that we, it was, and maybe we should explain what Brev is andNader: Yeah.Yeah. Uh, I mean, brev is just, it's a developer tool that makes it really easy to get a GPU. So we connect a bunch of different GPU sources. So the basics of it is like, how quickly can we SSH you into a G, into a GPU and whenever we would talk to users, they wanted A GPU. They wanted an A 100. And if you go to like any cloud [00:04:00] provisioning page, usually it's like three pages of forms or in the forms somewhere there's a dropdown.And in the dropdown there's some weird code that you know to translate to an A 100. And I remember just thinking like. Every time someone says they want an A 100, like the piece of text that they're telling me that they want is like, stuffed away in the corner. Yeah. And so we were like, what if the biggest piece of text was what the user's asking for?And so when you go to Brev, it's just big GPU chips with the type that you want withswyx: beautiful animations that you worked on pre, like pre you can, like, now you can just prompt it. But back in the day. Yeah. Yeah. Those were handcraft, handcrafted artisanal code.Nader: Yeah. I was actually really proud of that because, uh, it was an, i I made it in Figma.Yeah. And then I found, I was like really struggling to figure out how to turn it from like Figma to react. So what it actually is, is just an SVG and I, I have all the styles and so when you change the chip, whether it's like active or not it changes the SVG code and that somehow like renders like, looks like it's animating, but it, we just had the transition slow, but it's just like the, a JavaScript function to change the like underlying SVG.Yeah. And that was how I ended up like figuring out how to move it from from Figma. But yeah, that's Art Artisan. [00:05:00]Kyle: Speaking of marketing stunts though, he actually used those SVGs. Or kind of use those SVGs to make these cards.Nader: Oh yeah. LikeKyle: a GPU gift card Yes. That he handed out everywhere. That was actually my first impression of thatNader: one.Yeah,swyx: yeah, yeah.Nader: Yeah.swyx: I think I still have one of them.Nader: They look great.Kyle: Yeah.Nader: I have a ton of them still actually in our garage, which just, they don't have labels. We should honestly like bring, bring them back. But, um, I found this old printing press here, actually just around the corner on Ven ness. And it's a third generation San Francisco shop.And so I come in an excited startup founder trying to like, and they just have this crazy old machinery and I'm in awe. ‘cause the the whole building is so physical. Like you're seeing these machines, they have like pedals to like move these saws and whatever. I don't know what this machinery is, but I saw all three generations.Like there's like the grandpa, the father and the son, and the son was like, around my age. Well,swyx: it's like a holy, holy trinity.Nader: It's funny because we, so I just took the same SVG and we just like printed it and it's foil printing, so they make a a, a mold. That's like an inverse of like the A 100 and then they put the foil on it [00:06:00] and then they press it into the paper.And I remember once we got them, he was like, Hey, don't forget about us. You know, I guess like early Apple and Cisco's first business cards were all made there. And so he was like, yeah, we, we get like the startup businesses but then as they mature, they kind of go somewhere else. And so I actually, I think we were talking with marketing about like using them for some, we should go back and make some cards.swyx: Yeah, yeah, yeah. You know, I remember, you know, as a very, very small breadth investor, I was like, why are we spending time like, doing these like stunts for GPUs? Like, you know, I think like as a, you know, typical like cloud hard hardware person, you go into an AWS you pick like T five X xl, whatever, and it's just like from a list and you look at the specs like, why animate this GP?And, and I, I do think like it just shows the level of care that goes throughout birth and Yeah. And now, and also the, and,Nader: and Nvidia. I think that's what the, the thing that struck me most when we first came in was like the amount of passion that everyone has. Like, I think, um, you know, you talk to, you talk to Kyle, you talk to, like, every VP that I've met at Nvidia goes so close to the metal.Like, I remember it was almost a year ago, and like my VP asked me, he's like, Hey, [00:07:00] what's cursor? And like, are you using it? And if so, why? Surprised at this, and he downloaded Cursor and he was asking me to help him like, use it. And I thought that was, uh, or like, just show him what he, you know, why we were using it.And so, the amount of care that I think everyone has and the passion, appreciate, passion and appreciation for the moment. Right. This is a very unique time. So it's really cool to see everyone really like, uh, appreciate that.swyx: Yeah.Acquisition and DevEx Shiftswyx: One thing I wanted to do before we move over to sort of like research topics and, uh, the, the stuff that Kyle's working on is just tell the story of the acquisition, right?Like, not many people have been, been through an acquisition with Nvidia. What's it like? Uh, what, yeah, just anything you'd like to say.Nader: It's a crazy experience. I think, uh, you know, we were the thing that was the most exciting for us was. Our goal was just to make it easier for developers.We wanted to find access to GPUs, make it easier to do that. And then all, oh, actually your question about launchable. So launchable was just make one click exper, like one click deploys for any software on top of the GPU. Mm-hmm. And so what we really liked about Nvidia was that it felt like we just got a lot more resources to do all of that.I think, uh, you [00:08:00] know, NVIDIA's goal is to make things as easy for developers as possible. So there was a really nice like synergy there. I think that, you know, when it comes to like an acquisition, I think the amount that the soul of the products align, I think is gonna be. Is going speak to the success of the acquisition.Yeah. And so it in many ways feels like we're home. This is a really great outcome for us. Like we you know, I love brev.nvidia.com. Like you should, you should use it's, it's theKyle: front page for GPUs.Nader: Yeah. Yeah. If you want GP views,Kyle: you go there, getswyx: it there, and it's like internally is growing very quickly.I, I don't remember You said some stats there.Nader: Yeah, yeah, yeah. It's, uh, I, I wish I had the exact numbers, but like internally, externally, it's been growing really quickly. We've been working with a bunch of partners with a bunch of different customers and ISVs, if you have a solution that you want someone that runs on the GPU and you want people to use it quickly, we can bundle it up, uh, in a launchable and make it a one click run.If you're doing things and you want just like a sandbox or something to run on, right. Like open claw. Huge moment. Super exciting. Our, uh, and we'll talk into it more, but. You know, internally, people wanna run this, and you, we know we have to be really careful from the security implications. Do we let this run on the corporate network?Security's guidance was, Hey, [00:09:00] run this on breath, it's in, you know, it's, it's, it's a vm, it's sitting in the cloud, it's off the corporate network. It's isolated. And so that's been our stance internally and externally about how to even run something like open call while we figure out how to run these things securely.But yeah,swyx: I think there's also like, you almost like we're the right team at the right time when Nvidia is starting to invest a lot more in developer experience or whatever you call it. Yeah. Uh, UX or I don't know what you call it, like software. Like obviously NVIDIA is always invested in software, but like, there's like, this is like a different audience.Yeah. It's aNader: widerKyle: developer base.swyx: Yeah. Right.Nader: Yeah. Yeah. You know, it's funny, it's like, it's not, uh,swyx: so like, what, what is it called internally? What, what is this that people should be aware that is going on there?Nader: Uh, what, like developer experienceswyx: or, yeah, yeah. Is it's called just developer experience or is there like a broader strategy hereNader: in Nvidia?Um, Nvidia always wants to make a good developer experience. The thing is and a lot of the technology is just really complicated. Like, it's not, it's uh, you know, I think, um. The thing that's been really growing or the AI's growing is having a huge moment, not [00:10:00] because like, let's say data scientists in 2018, were quiet then and are much louder now.The pie is com, right? There's a whole bunch of new audiences. My mom's wondering what she's doing. My sister's learned, like taught herself how to code. Like the, um, you know, I, I actually think just generally AI's a big equalizer and you're seeing a more like technologically literate society, I guess.Like everyone's, everyone's learning how to code. Uh, there isn't really an excuse for that. And so building a good UX means that you really understand who your end user is. And when your end user becomes such a wide, uh, variety of people, then you have to almost like reinvent the practice, right? Yeah. You haveKyle: to, and actually build more developer ux, right?Because the, there are tiers of developer base that were added. You know, the, the hackers that are building on top of open claw, right? For example, have never used gpu. They don't know what kuda is. They, they, they just want to run something.Nader: Yeah.Kyle: You need new UX that is not just. Hey, you know, how do you program something in Cuda and run it?And then, and then we built, you know, like when Deep Learning was getting big, we built, we built Torch and, and, but so recently the amount of like [00:11:00] layers that are added to that developer stack has just exploded because AI has become ubiquitous. Everyone's using it in different ways. Yeah. It'sNader: moving fast in every direction.Vertical, horizontal.Vibhu: Yeah. You guys, you even take it down to hardware, like the DGX Spark, you know, it's, it's basically the same system as just throwing it up on big GPU cluster.Nader: Yeah, yeah, yeah. It's amazing. Blackwell.swyx: Yeah. Uh, we saw the preview at the last year's GTC and that was one of the better performing, uh, videos so far, and video coverage so far.Awesome. This will beat it. Um,Nader: that wasswyx: actually, we have fingersNader: crossed. Yeah.DGX Spark and Remote AccessNader: Even when Grace Blackwell or when, um, uh, DGX Spark was first coming out getting to be involved in that from the beginning of the developer experience. And it just comes back to what youswyx: were involved.Nader: Yeah. St. St.swyx: Mars.Nader: Yeah. Yeah. I mean from, it was just like, I, I got an email, we just got thrown into the loop and suddenly yeah, I, it was actually really funny ‘cause I'm still pretty fresh from the acquisition and I'm, I'm getting an email from a bunch of the engineering VPs about like, the new hardware, GPU chip, like we're, or not chip, but just GPU system that we're putting out.And I'm like, okay, cool. Matters. Now involved with this for the ux, I'm like. What am I gonna do [00:12:00] here? So, I remember the first meeting, I was just like kind of quiet as I was hearing engineering VPs talk about what this box could be, what it could do, how we should use it. And I remember, uh, one of the first ideas that people were idea was like, oh, the first thing that it was like, I think a quote was like, the first thing someone's gonna wanna do with this is get two of them and run a Kubernetes cluster on top of them.And I was like, oh, I think I know why I'm here. I was like, the first thing we're doing is easy. SSH into the machine. And then, and you know, just kind of like scoping it down of like, once you can do that every, you, like the person who wants to run a Kubernetes cluster onto Sparks has a higher propensity for pain, then, then you know someone who buys it and wants to run open Claw right now, right?If you can make sure that that's as effortless as possible, then the rest becomes easy. So there's a tool called Nvidia Sync. It just makes the SSH connection really simple. So, you know, if you think about it like. If you have a Mac, uh, or a PC or whatever, if you have a laptop and you buy this GPU and you want to use it, you should be able to use it like it's A-A-G-P-U in the cloud, right?Um, but there's all this friction of like, how do you actually get into that? That's part of [00:13:00] Revs value proposition is just, you know, there's a CLI that wraps SSH and makes it simple. And so our goal is just get you into that machine really easily. And one thing we just launched at CES, it's in, it's still in like early access.We're ironing out some kinks, but it should be ready by GTC. You can register your spark on Brev. And so now if youswyx: like remote managed yeah, local hardware. Single pane of glass. Yeah. Yeah. Because Brev can already manage other clouds anyway, right?Vibhu: Yeah, yeah. And you use the spark on Brev as well, right?Nader: Yeah. But yeah, exactly. So, so you, you, so you, you set it up at home you can run the command on it, and then it gets it's essentially it'll appear in your Brev account, and then you can take your laptop to a Starbucks or to a cafe, and you'll continue to use your, you can continue use your spark just like any other cloud node on Brev.Yeah. Yeah. And it's just like a pre-provisioned centerswyx: in yourNader: home. Yeah, exactly.swyx: Yeah. Yeah.Vibhu: Tiny little data center.Nader: Tiny little, the size ofVibhu: your phone.SOL Culture and Dynamo Setupswyx: One more thing before we move on to Kyle. Just have so many Jensen stories and I just love, love mining Jensen stories. Uh, my favorite so far is SOL. Uh, what is, yeah, what is S-O-L-S-O-LNader: is actually, i, I think [00:14:00] of all the lessons I've learned, that one's definitely my favorite.Kyle: It'll always stick with you.Nader: Yeah. Yeah. I, you know, in your startup, everything's existential, right? Like we've, we've run out of money. We were like, on the risk of, of losing payroll, we've had to contract our team because we l ran outta money. And so like, um, because of that you're really always forcing yourself to I to like understand the root cause of everything.If you get a date, if you get a timeline, you know exactly why that date or timeline is there. You're, you're pushing every boundary and like, you're not just say, you're not just accepting like a, a no. Just because. And so as you start to introduce more layers, as you start to become a much larger organization, SOL is is essentially like what is the physics, right?The speed of light moves at a certain speed. So if flight's moving some slower, then you know something's in the way. So before trying to like layer reality back in of like, why can't this be delivered at some date? Let's just understand the physics. What is the theoretical limit to like, uh, how fast this can go?And then start to tell me why. ‘cause otherwise people will start telling you why something can't be done. But actually I think any great leader's goal is just to create urgency. Yeah. [00:15:00] There's an infiniteKyle: create compelling events, right?Nader: Yeah.Kyle: Yeah. So l is a term video is used to instigate a compelling event.You say this is done. How do we get there? What is the minimum? As much as necessary, as little as possible thing that it takes for us to get exactly here and. It helps you just break through a bunch of noise.swyx: Yeah.Kyle: Instantly.swyx: One thing I'm unclear about is, can only Jensen use the SOL card? Like, oh, no, no, no.Not everyone get the b******t out because obviously it's Jensen, but like, can someone else be like, no, likeKyle: frontline engineers use it.Nader: Yeah. Every, I think it's not so much about like, get the b******t out. It's like, it's like, give me the root understanding, right? Like, if you tell me something takes three weeks, it like, well, what's the first principles?Yeah, the first principles. It's like, what's the, what? Like why is it three weeks? What is the actual yeah. What's the actual limit of why this is gonna take three weeks? If you're gonna, if you, if let's say you wanted to buy a new computer and someone told you it's gonna be here in five days, what's the SOL?Well, like the SOL is like, I could walk into a Best Buy and pick it up for you. Right? So then anything that's like beyond that is, and is that practical? Is that how we're gonna, you know, let's say give everyone in the [00:16:00] company a laptop, like obviously not. So then like that's the SOL and then it's like, okay, well if we have to get more than 10, suddenly there might be some, right?And so now we can kind of piece the reality back.swyx: So, so this is the. Paul Graham do things that don't scale. Yeah. And this is also the, what people would now call behi agency. Yeah.Kyle: It's actually really interesting because there's a, there's a second hardware angle to SOL that like doesn't come up for all the org sol is used like culturally at aswyx: media for everything.I'm also mining for like, I think that can be annoying sometimes. And like someone keeps going IOO you and you're like, guys, like we have to be stable. We have to, we to f*****g plan. Yeah.Kyle: It's an interesting balance.Nader: Yeah. I encounter that with like, actually just with, with Alec, right? ‘cause we, we have a new conference so we need to launch, we have, we have goals of what we wanna launch by, uh, by the conference and like, yeah.At the end of the day, where isswyx: this GTC?Nader: Um, well this is like, so we, I mean we did it for CES, we did for GT CDC before that we're doing it for GTC San Jose. So I mean, like every, you know, we have a new moment. Um, and we want to launch something. Yeah. And we want to do so at SOL and that does mean that some, there's some level of prioritization that needs [00:17:00] to happen.And so it, it is difficult, right? I think, um, you have to be careful with what you're pushing. You know, stability is important and that should be factored into S-O-L-S-O-L isn't just like, build everything and let it break, you know, that, that's part of the conversation. So as you're laying, layering in all the details, one of them might be, Hey, we could build this, but then it's not gonna be stable for X, y, z reasons.And so that was like, one of our conversations for CES was, you know, hey, like we, we can get this into early access registering your spark with brev. But there are a lot of things that we need to do in order to feel really comfortable from a security perspective, right? There's a lot of networking involved before we deliver that to users.So it's like, okay. Let's get this to a point where we can at least let people experiment with it. We had it in a booth, we had it in Jensen's keynote, and then let's go iron out all the networking kinks. And that's not easy. And so, uh, that can come later. And so that was the way that we layered that back in.Yeah. ButKyle: It's not really about saying like, you don't have to do the, the maintenance or operational work. It's more about saying, you know, it's kind of like [00:18:00] highlights how progress is incremental, right? Like, what is the minimum thing that we can get to. And then there's SOL for like every component after that.But there's the SOL to get you, get you to the, the starting line. And that, that's usually how it's asked. Yeah. On the other side, you know, like SOL came out of like hardware at Nvidia. Right. So SOL is like literally if we ran the accelerator or the GPU with like at basically full speed with like no other constraints, like how FAST would be able to make a program go.swyx: Yeah. Yeah. Right.Kyle: Soswyx: in, in training that like, you know, then you work back to like some percentage of like MFU for example.Kyle: Yeah, that's a, that's a great example. So like, there's an, there's an S-O-L-M-F-U, and then there's like, you know, what's practically achievable.swyx: Cool. Should we move on to sort of, uh, Kyle's side?Uh, Kyle, you're coming more from the data science world. And, uh, I, I mean I always, whenever, whenever I meet someone who's done working in tabular stuff, graph neural networks, time series, these are basically when I go to new reps, I go to ICML, I walk the back halls. There's always like a small group of graph people.Yes. Absolute small group of tabular people. [00:19:00] And like, there's no one there. And like, it's very like, you know what I mean? Like, yeah, no, like it's, it's important interesting work if you care about solving the problems that they solve.Kyle: Yeah.swyx: But everyone else is just LMS all the time.Kyle: Yeah. I mean it's like, it's like the black hole, right?Has the event horizon reached this yet in nerves? Um,swyx: but like, you know, those are, those are transformers too. Yeah. And, and those are also like interesting things. Anyway, uh, I just wanted to spend a little bit of time on, on those, that background before we go into Dynamo, uh, proper.Kyle: Yeah, sure. I took a different path to Nvidia than that, or I joined six years ago, seven, if you count, when I was an intern.So I joined Nvidia, like right outta college. And the first thing I jumped into was not what I'd done in, during internship, which was like, you know, like some stuff for autonomous vehicles, like heavyweight object detection. I jumped into like, you know, something, I'm like, recommenders, this is popular. Andswyx: yeah, he did RexiKyle: as well.Yeah, Rexi. Yeah. I mean that, that was the taboo data at the time, right? You have tables of like, audience qualities and item qualities, and you're trying to figure out like which member of [00:20:00] the audience matches which item or, or more practically which item matches which member of the audience. And at the time, really it was like we were trying to enable.Uh, recommender, which had historically been like a little bit of a CP based workflow into something that like, ran really well in GPUs. And it's since been done. Like there are a bunch of libraries for Axis that run on GPUs. Uh, the common models like Deeplearning recommendation model, which came outta meta and the wide and deep model, which was used or was released by Google were very accelerated by GPUs using, you know, the fast HBM on the chips, especially to do, you know, vector lookups.But it was very interesting at the time and super, super relevant because like we were starting to get like. This explosion of feeds and things that required rec recommenders to just actively be on all the time. And sort of transitioned that a little bit towards graph neural networks when I discovered them because I was like, okay, you can actually use graphical neural networks to represent like, relationships between people, items, concepts, and that, that interested me.So I jumped into that at [00:21:00] Nvidia and, and got really involved for like two-ish years.swyx: Yeah. Uh, and something I learned from Brian Zaro Yeah. Is that you can just kind of choose your own path in Nvidia.Kyle: Oh my God. Yeah.swyx: Which is not a normal big Corp thing. Yeah. Like you, you have a lane, you stay in your lane.Nader: I think probably the reason why I enjoy being in a, a big company, the mission is the boss probably from a startup guy. Yeah. The missionswyx: is the boss.Nader: Yeah. Uh, it feels like a big game of pickup basketball. Like, you know, if you play one, if you wanna play basketball, you just go up to the court and you're like, Hey look, we're gonna play this game and we need three.Yeah. And you just like find your three. That's honestly for every new initiative that's what it feels like. Yeah.Vibhu: It also like shows, right? Like Nvidia. Just releasing state-of-the-art stuff in every domain. Yeah. Like, okay, you expect foundation models with Nemo tron voice just randomly parakeet.Call parakeet just comes out another one, uh, voice. TheKyle: video voice team has always been producing.Vibhu: Yeah. There's always just every other domain of paper that comes out, dataset that comes out. It's like, I mean, it also stems back to what Nvidia has to do, right? You have to make chips years before they're actually produced.Right? So you need to know, you need to really [00:22:00] focus. TheKyle: design process starts likeVibhu: exactlyKyle: three to five years before the chip gets to the market.Vibhu: Yeah. I, I'm curious more about what that's like, right? So like, you have specialist teams. Is it just like, you know, people find an interest, you go in, you go deep on whatever, and that kind of feeds back into, you know, okay, we, we expect predictions.Like the internals at Nvidia must be crazy. Right? You know? Yeah. Yeah. You know, you, you must. Not even without selling to people, you have your own predictions of where things are going. Yeah. And they're very based, very grounded. Right?Kyle: Yeah. It, it, it's really interesting. So there's like two things that I think that Amed does, which are quite interesting.Uh, one is like, we really index into passion. There's a big. Sort of organizational top sound push to like ensure that people are working on the things that they're passionate about. So if someone proposes something that's interesting, many times they can just email someone like way up the chain that they would find this relevant and say like, Hey, can I go work on this?Nader: It's actually like I worked at a, a big company for a couple years before, uh, starting on my startup journey and like, it felt very weird if you were to like email out of chain, if that makes [00:23:00] sense. Yeah. The emails at Nvidia are like mosh pitsswyx: shoot,Nader: and it's just like 60 people, just whatever. And like they're, there's this,swyx: they got messy like, reply all you,Nader: oh, it's in, it's insane.It's insane. They justKyle: help. You know, Maxim,Nader: the context. But, but that's actually like, I've actually, so this is a weird thing where I used to be like, why would we send emails? We have Slack. I am the entire, I'm the exact opposite. I feel so bad for anyone who's like messaging me on Slack ‘cause I'm so unresponsive.swyx: Your emailNader: Maxi, email Maxim. I'm email maxing Now email is a different, email is perfect because man, we can't work together. I'm email is great, right? Because important threads get bumped back up, right? Yeah, yeah. Um, and so Slack doesn't do that. So I just have like this casino going off on the right or on the left and like, I don't know which thread was from where or what, but like the threads get And then also just like the subject, so you can have like working threads.I think what's difficult is like when you're small, if you're just not 40,000 people I think Slack will work fine, but there's, I don't know what the inflection point is. There is gonna be a point where that becomes really messy and you'll actually prefer having email. ‘cause you can have working threads.You can cc more than nine people in a thread.Kyle: You can fork stuff.Nader: You can [00:24:00] fork stuff, which is super nice and just like y Yeah. And so, but that is part of where you can propose a plan. You can also just. Start, honestly, momentum's the only authority, right? So like, if you can just start, start to make a little bit of progress and show someone something, and then they can try it.That's, I think what's been, you know, I think the most effective way to push anything for forward. And that's both at Nvidia and I think just generally.Kyle: Yeah, there's, there's the other concept that like is explored a lot at Nvidia, which is this idea of a zero billion dollar business. Like market creation is a big thing at Nvidia.Like,swyx: oh, you want to go and start a zero billion dollar business?Kyle: Jensen says, we are completely happy investing in zero billion dollar markets. We don't care if this creates revenue. It's important for us to know about this market. We think it will be important in the future. It can be zero billion dollars for a while.I'm probably minging as words here for, but like, you know, like, I'll give an example. NVIDIA's been working on autonomous driving for a a long time,swyx: like an Nvidia car.Kyle: No, they, they'veVibhu: used the Mercedes, right? They're around the HQ and I think it finally just got licensed out. Now they're starting to be used quite a [00:25:00] bit.For 10 years you've been seeing Mercedes with Nvidia logos driving.Kyle: If you're in like the South San Santa Clara, it's, it's actually from South. Yeah. So, um. Zero billion dollar markets are, are a thing like, you know, Jensen,swyx: I mean, okay, look, cars are not a zero billion dollar market. But yeah, that's a bad example.Nader: I think, I think he's, he's messaging, uh, zero today, but, or even like internally, right? Like, like it's like, uh, an org doesn't have to ruthlessly find revenue very quickly to justify their existence. Right. Like a lot of the important research, a lot of the important technology being developed that, that's kind ofKyle: where research, research is very ide ideologically free at Nvidia.Yeah. Like they can pursue things that they wereswyx: Were you research officially?Kyle: I was never in research. Officially. I was always in engineering. Yeah. We in, I'm in an org called Deep Warning Algorithms, which is basically just how do we make things that are relevant to deep warning go fast.swyx: That sounds freaking cool.Vibhu: And I think a lot of that is underappreciated, right? Like time series. This week Google put out time. FF paper. Yeah. A new time series, paper res. Uh, Symantec, ID [00:26:00] started applying Transformers LMS to Yes. Rec system. Yes. And when you think the scale of companies deploying these right. Amazon recommendations, Google web search, it's like, it's huge scale andKyle: Yeah.Vibhu: You want fast?Kyle: Yeah. Yeah. Yeah. Actually it's, it, I, there's a fun moment that brought me like full circle. Like, uh, Amazon Ads recently gave a talk where they talked about using Dynamo for generative recommendation, which was like super, like weirdly cathartic for me. I'm like, oh my God. I've, I've supplanted what I was working on.Like, I, you're using LMS now to do what I was doing five years ago.swyx: Yeah. Amazing. And let's go right into Dynamo. Uh, maybe introduce Yeah, sure. To the top down and Yeah.Kyle: I think at this point a lot of people are familiar with the term of inference. Like funnily enough, like I went from, you know, inference being like a really niche topic to being something that's like discussed on like normal people's Twitter feeds.It's,Nader: it's on billboardsKyle: here now. Yeah. Very, very strange. Driving, driving, seeing just an inference ad on 1 0 1 inference at scale is becoming a lot more important. Uh, we have these moments like, you know, open claw where you have these [00:27:00] agents that take lots and lots of tokens, but produce, incredible results.There are many different aspects of test time scaling so that, you know, you can use more inference to generate a better result than if you were to use like a short amount of inference. There's reasoning, there's quiring, there's, adding agency to the model, allowing it to call tools and use skills.Dyno sort came about at Nvidia. Because myself and a couple others were, were sort of talking about the, these concepts that like, you know, you have inference engines like VLMS, shelan, tenor, TLM and they have like one single copy. They, they, they sort of think about like things as like one single copy, like one replica, right?Why Scale Out WinsKyle: Like one version of the model. But when you're actually serving things at scale, you can't just scale up that replica because you end up with like performance problems. There's a scaling limit to scaling up replicas. So you actually have to scale out to use a, maybe some Kubernetes type terminology.We kind of realized that there was like. A lot of potential optimization that we could do in scaling out and building systems for data [00:28:00] center scale inference. So Dynamo is this data center scale inference engine that sits on top of the frameworks like VLM Shilling and 10 T lm and just makes things go faster because you can leverage the economy of scale.The fact that you have KV cash, which we can define a little bit later, uh, in all these machines that is like unique and you wanna figure out like the ways to maximize your cash hits or you want to employ new techniques in inference like disaggregation, which Dynamo had introduced to the world in, in, in March, not introduced, it was a academic talk, but beforehand.But we are, you know, one of the first frameworks to start, supporting it. And we wanna like, sort of combine all these techniques into sort of a modular framework that allows you to. Accelerate your inference at scale.Nader: By the way, Kyle and I became friends on my first date, Nvidia, and I always loved, ‘cause like he always teaches meswyx: new things.Yeah. By the way, this is why I wanted to put two of you together. I was like, yeah, this is, this is gonna beKyle: good. It's very, it's very different, you know, like we've, we, we've, we've talked to each other a bunch [00:29:00] actually, you asked like, why, why can't we scale up?Nader: Yeah.Scale Up Limits ExplainedNader: model, you said model replicas.Kyle: Yeah. So you, so scale up means assigning moreswyx: heavier?Kyle: Yeah, heavier. Like making things heavier. Yeah, adding more GPUs. Adding more CPUs. Scale out is just like having a barrier saying, I'm gonna duplicate my representation of the model or a representation of this microservice or something, and I'm gonna like, replicate it Many times.Handle, load. And the reason that you can't scale, scale up, uh, past some points is like, you know, there, there, there are sort of hardware bounds and algorithmic bounds on, on that type of scaling. So I'll give you a good example that's like very trivial. Let's say you're on an H 100. The Maxim ENV link domain for H 100, for most Ds H one hundreds is heus, right?So if you scaled up past that, you're gonna have to figure out ways to handle the fact that now for the GPUs to communicate, you have to do it over Infin band, which is still very fast, but is not as fast as ENV link.swyx: Is it like one order of magnitude, like hundreds or,Kyle: it's about an order of magnitude?Yeah. Okay. Um, soswyx: not terrible.Kyle: [00:30:00] Yeah. I, I need to, I need to remember the, the data sheet here, like, I think it's like about 500 gigabytes. Uh, a second unidirectional for ENV link, and about 50 gigabytes a second unidirectional for Infin Band. I, it, it depends on the, the generation.swyx: I just wanna set this up for people who are not familiar with these kinds of like layers and the trash speedVibhu: and all that.Of course.From Laptop to Multi NodeVibhu: Also, maybe even just going like a few steps back before that, like most people are very familiar with. You see a, you know, you can use on your laptop, whatever these steel viol, lm you can just run inference there. All, there's all, you can, youcan run it on thatVibhu: laptop. You can run on laptop.Then you get to, okay, uh, models got pretty big, right? JLM five, they doubled the size, so mm-hmm. Uh, what do you do when you have to go from, okay, I can get 128 gigs of memory. I can run it on a spark. Then you have to go multi GPU. Yeah. Okay. Multi GPU, there's some support there. Now, if I'm a company and I don't have like.I'm not hiring the best researchers for this. Right. But I need to go [00:31:00] multi-node, right? I have a lot of servers. Okay, now there's efficiency problems, right? You can have multiple eight H 100 nodes, but, you know, is that as a, like, how do you do that efficiently?Kyle: Yeah. How do you like represent them? How do you choose how to represent the model?Yeah, exactly right. That's a, that's like a hard question. Everyone asks, how do you size oh, I wanna run GLM five, which just came out new model. There have been like four of them in the past week, by the way, like a bunch of new models.swyx: You know why? Right? Deep seek.Kyle: No comment. Oh. Yeah, but Ggl, LM five, right?We, we have this, new model. It's, it's like a large size, and you have to figure out how to both scale up and scale out, right? Because you have to find the right representation that you care about. Everyone does this differently. Let's be very clear. Everyone figures this out in their own path.Nader: I feel like a lot of AI or ML even is like, is like this. I think people think, you know, I, I was, there was some tweet a few months ago that was like, why hasn't fine tuning as a service taken off? You know, that might be me. It might have been you. Yeah. But people want it to be such an easy recipe to follow.But even like if you look at an ML model and specificKyle: to you Yeah,Nader: yeah.Kyle: And the [00:32:00] model,Nader: the situation, and there's just so much tinkering, right? Like when you see a model that has however many experts in the ME model, it's like, why that many experts? I don't, they, you know, they tried a bunch of things and that one seemed to do better.I think when it comes to how you're serving inference, you know, you have a bunch of decisions to make and there you can always argue that you can take something and make it more optimal. But I think it's this internal calibration and appetite for continued calibration.Vibhu: Yeah. And that doesn't mean like, you know, people aren't taking a shot at this, like tinker from thinking machines, you know?Yeah. RL as a service. Yeah, totally. It's, it also gets even harder when you try to do big model training, right? We're not the best at training Moes, uh, when they're pre-trained. Like we saw this with LAMA three, right? They're trained in such a sparse way that meta knows there's gonna be a bunch of inference done on these, right?They'll open source it, but it's very trained for what meta infrastructure wants, right? They wanna, they wanna inference it a lot. Now the question to basically think about is, okay, say you wanna serve a chat application, a coding copilot, right? You're doing a layer of rl, you're serving a model for X amount of people.Is it a chat model, a coding model? Dynamo, you know, back to that,Kyle: it's [00:33:00] like, yeah, sorry. So you we, we sort of like jumped off of, you know, jumped, uh, on that topic. Everyone has like, their own, own journey.Cost Quality Latency TradeoffsKyle: And I, I like to think of it as defined by like, what is the model you need? What is the accuracy you need?Actually I talked to NA about this earlier. There's three axes you care about. What is the quality that you're able to produce? So like, are you accurate enough or can you complete the task with enough, performance, high enough performance. Yeah, yeah. Uh, there's cost. Can you serve the model or serve your workflow?Because it's not just the model anymore, it's the workflow. It's the multi turn with an agent cheaply enough. And then can you serve it fast enough? And we're seeing all three of these, like, play out, like we saw, we saw new models from OpenAI that you know, are faster. You have like these new fast versions of models.You can change the amount of thinking to change the amount of quality, right? Produce more tokens, but at a higher cost in a, in a higher latency. And really like when you start this journey of like trying to figure out how you wanna host a model, you, you, you think about three things. What is the model I need to serve?How many times do I need to call it? What is the input sequence link was [00:34:00] the, what does the workflow look like on top of it? What is the SLA, what is the latency SLA that I need to achieve? Because there's usually some, this is usually like a constant, you, you know, the SLA that you need to hit and then like you try and find the lowest cost version that hits all of these constraints.Usually, you know, you, you start with those things and you say you, you kind of do like a bit of experimentation across some common configurations. You change the tensor parallel size, which is a form of parallelismVibhu: I take, it goes even deeper first. Gotta think what model.Kyle: Yes, course,ofKyle: course. It's like, it's like a multi-step design process because as you said, you can, you can choose a smaller model and then do more test time scaling and it'll equate the quality of a larger model because you're doing the test time scaling or you're adding a harness or something.So yes, it, it goes way deeper than that. But from the performance perspective, like once you get to the model you need, you need to host, you look at that and you say, Hey. I have this model, I need to serve it at the speed. What is the right configuration for that?Nader: You guys see the recent, uh, there was a paper I just saw like a few days ago that, uh, if you run [00:35:00] the same prompt twice, you're getting like double Just try itagain.Nader: Yeah, exactly.Vibhu: And you get a lot. Yeah. But the, the key thing there is you give the context of the failed try, right? Yeah. So it takes a shot. And this has been like, you know, basic guidance for quite a while. Just try again. ‘cause you know, trying, just try again. Did you try again? All adviceNader: in life.Vibhu: Just, it's a paper from Google, if I'm not mistaken, right?Yeah,Vibhu: yeah. I think it, it's like a seven bas little short paper. Yeah. Yeah. The title's very cute. And it's just like, yeah, just try again. Give it ask context,Kyle: multi-shot. You just like, say like, hey, like, you know, like take, take a little bit more, take a little bit more information, try and fail. Fail.Vibhu: And that basic concept has gone pretty deep.There's like, um, self distillation, rl where you, you do self distillation, you do rl and you have past failure and you know, that gives some signal so people take, try it again. Not strong enough.swyx: Uh, for, for listeners, uh, who listen to here, uh, vivo actually, and I, and we run a second YouTube channel for our paper club where, oh, that's awesome.Vivo just covered this. Yeah. Awesome. Self desolation and all that's, that's why he, to speed [00:36:00] on it.Nader: I'll to check it out.swyx: Yeah. It, it's just a good practice, like everyone needs, like a paper club where like you just read papers together and the social pressure just kind of forces you to just,Nader: we, we,there'sNader: like a big inference.Kyle: ReadingNader: group at a video. I feel so bad every time. I I, he put it on like, on our, he shared it.swyx: One, one ofNader: your guys,swyx: uh, is, is big in that, I forget es han Yeah, yeah,Kyle: es Han's on my team. Actually. Funny. There's a, there's a, there's a employee transfer between us. Han worked for Nater at Brev, and now he, he's on my team.He wasNader: our head of ai. And then, yeah, once we got in, andswyx: because I'm always looking for like, okay, can, can I start at another podcast that only does that thing? Yeah. And, uh, Esan was like, I was trying to like nudge Esan into like, is there something here? I mean, I don't think there's, there's new infant techniques every day.So it's like, it's likeKyle: you would, you would actually be surprised, um, the amount of blog posts you see. And ifswyx: there's a period where it was like, Medusa hydra, what Eagle, like, youKyle: know, now we have new forms of decode, uh, we have new forms of specula, of decoding or new,swyx: what,Kyle: what are youVibhu: excited? And it's exciting when you guys put out something like Tron.‘cause I remember the paper on this Tron three, [00:37:00] uh, the amount of like post train, the on tokens that the GPU rich can just train on. And it, it was a hybrid state space model, right? Yeah.Kyle: It's co-designed for the hardware.Vibhu: Yeah, go design for the hardware. And one of the things was always, you know, the state space models don't scale as well when you do a conversion or whatever the performance.And you guys are like, no, just keep draining. And Nitron shows a lot of that. Yeah.Nader: Also, something cool about Nitron it was released in layers, if you will, very similar to Dynamo. It's, it's, it's essentially it was released as you can, the pre-training, post-training data sets are released. Yeah. The recipes on how to do it are released.The model itself is released. It's full model. You just benefit from us turning on the GPUs. But there are companies like, uh, ServiceNow took the dataset and they trained their own model and we were super excited and like, you know, celebrated that work.ZoomVibhu: different. Zoom is, zoom is CGI, I think, uh, you know, also just to add like a lot of models don't put out based models and if there's that, why is fine tuning not taken off?You know, you can do your own training. Yeah,Kyle: sure.Vibhu: You guys put out based model, I think you put out everything.Nader: I believe I know [00:38:00]swyx: about base. BasicallyVibhu: without baseswyx: basic can be cancelable.Vibhu: Yeah. Base can be cancelable.swyx: Yeah.Vibhu: Safety training.swyx: Did we get a full picture of dymo? I, I don't know if we, what,Nader: what I'd love is you, you mentioned the three axes like break it down of like, you know, what's prefilled decode and like what are the optimizations that we can get with Dynamo?Kyle: Yeah. That, that's, that's, that's a great point. So to summarize on that three axis problem, right, there are three things that determine whether or not something can be done with inference, cost, quality, latency, right? Dynamo is supposed to be there to provide you like the runtime that allows you to pull levers to, you know, mix it up and move around the parade of frontier or the preto surface that determines is this actually possible with inference And AI todayNader: gives you the knobs.Kyle: Yeah, exactly. It gives you the knobs.Disaggregation Prefill vs DecodeKyle: Uh, and one thing that like we, we use a lot in contemporary inference and is, you know, starting to like pick up from, you know, in, in general knowledge is this co concept of disaggregation. So historically. Models would be hosted with a single inference engine. And that inference engine [00:39:00] would ping pong between two phases.There's prefill where you're reading the sequence generating KV cache, which is basically just a set of vectors that represent the sequence. And then using that KV cache to generate new tokens, which is called Decode. And some brilliant researchers across multiple different papers essentially made the realization that if you separate these two phases, you actually gain some benefits.Those benefits are basically a you don't have to worry about step synchronous scheduling. So the way that an inference engine works is you do one step and then you finish it, and then you schedule, you start scheduling the next step there. It's not like fully asynchronous. And the problem with that is you would have, uh, essentially pre-fill and decode are, are actually very different in terms of both their resource requirements and their sometimes their runtime.So you would have like prefill that would like block decode steps because you, you'd still be pre-filing and you couldn't schedule because you know the step has to end. So you remove that scheduling issue and then you also allow you, or you yourself, to like [00:40:00] split the work into two different ki types of pools.So pre-fill typically, and, and this changes as, as model architecture changes. Pre-fill is, right now, compute bound most of the time with the sequence is sufficiently long. It's compute bound. On the decode side because you're doing a full Passover, all the weights and the entire sequence, every time you do a decode step and you're, you don't have the quadratic computation of KV cache, it's usually memory bound because you're retrieving a linear amount of memory and you're doing a linear amount of compute as opposed to prefill where you retrieve a linear amount of memory and then use a quadratic.You know,Nader: it's funny, someone exo Labs did a really cool demo where for the DGX Spark, which has a lot more compute, you can do the pre the compute hungry prefill on a DG X spark and then do the decode on a, on a Mac. Yeah. And soVibhu: that's faster.Nader: Yeah. Yeah.Kyle: So you could, you can do that. You can do machine strat stratification.Nader: Yeah.Kyle: And like with our future generation generations of hardware, we actually announced, like with Reuben, this [00:41:00] new accelerator that is prefilled specific. It's called Reuben, CPX. SoKubernetes Scaling with GroveNader: I have a question when you do the scale out. Yeah. Is scaling out easier with Dynamo? Because when you need a new node, you can dedicate it to either the Prefill or, uh, decode.Kyle: Yeah. So Dynamo actually has like a, a Kubernetes component in it called Grove that allows you to, to do this like crazy scaling specialization. It has like this hot, it's a representation that, I don't wanna go too deep into Kubernetes here, but there was a previous way that you would like launch multi-node work.Uh, it's called Leader Worker Set. It's in the Kubernetes standard, and Leader worker set is great. It served a lot of people super well for a long period of time. But one of the things that it's struggles with is representing a set of cases where you have a multi-node replica that has a pair, right?You know, prefill and decode, or it's not paired, but it has like a second stage that has a ratio that changes over time. And prefill and decode are like two different things as your workload changes, right? The amount of prefill you'll need to do may change. [00:42:00] The amount of decode that you, you'll need to do might change, right?Like, let's say you start getting like insanely long queries, right? That probably means that your prefill scales like harder because you're hitting these, this quadratic scaling growth.swyx: Yeah.And then for listeners, like prefill will be long input. Decode would be long output, for example, right?Kyle: Yeah. So like decode, decode scale. I mean, decode is funny because the amount of tokens that you produce scales with the output length, but the amount of work that you do per step scales with the amount of tokens in the context.swyx: Yes.Kyle: So both scales with the input and the output.swyx: That's true.Kyle: But on the pre-fold view code side, like if.Suddenly, like the amount of work you're doing on the decode side stays about the same or like scales a little bit, and then the prefilled side like jumps up a lot. You actually don't want that ratio to be the same. You want it to change over time. So Dynamo has a set of components that A, tell you how to scale.It tells you how many prefilled workers and decoded workers you, it thinks you should have, and also provides a scheduling API for Kubernetes that allows you to actually represent and affect this scheduling on, on, on your actual [00:43:00] hardware, on your compute infrastructure.Nader: Not gonna lie. I feel a little embarrassed for being proud of my SVG function earlier.swyx: No, itNader: wasreallyKyle: cute. I, Iswyx: likeNader: it's all,swyx: it's all engineering. It's all engineering. Um, that's where I'mKyle: technical.swyx: One thing I'm, I'm kind of just curious about with all with you see at a systems level, everything going on here. Mm-hmm. And we, you know, we're scaling it up in, in multi, in distributed systems.Context Length and Co Designswyx: Um, I think one thing that's like kind of, of the moment right now is people are asking, is there any SOL sort of upper bounds. In terms of like, let's call, just call it context length for one for of a better word, but you can break it down however you like.Nader: Yeah.swyx: I just think like, well, yeah, I mean, like clearly you can engage in hybrid architectures and throw in some state space models in there.All, all you want, but it looks, still looks very attention heavy.Kyle: Yes. Uh, yeah. Long context is attention heavy. I mean, we have these hybrid models, um,swyx: to take and most, most models like cap out at a million contexts and that's it. Yeah. Like for the last two years has been it.Kyle: Yeah. The model hardware context co-design thing that we're seeing these days is actually super [00:44:00] interesting.It's like my, my passion, like my secret side passion. We see models like Kimmy or G-P-T-O-S-S. I'm use these because I, I know specific things about these models. So Kimmy two comes out, right? And it's an interesting model. It's like, like a deep seek style architecture is MLA. It's basically deep seek, scaled like a little bit differently, um, and obviously trained differently as well.But they, they talked about, why they made the design choices for context. Kimmy has more experts, but fewer attention heads, and I believe a slightly smaller attention, uh, like dimension. But I need to remember, I need to check that. Uh, it doesn't matter. But they discussed this actually at length in a blog post on ji, which is like our pu which is like credit puswyx: Yeah.Kyle: Um, in, in China. Chinese red.swyx: Yeah.Kyle: It's, yeah. So it, it's, it's actually an incredible blog post. Uh, like all the mls people in, in, in that, I've seen that on GPU are like very brilliant, but they, they talk about like the creators of Kimi K two [00:45:00] actually like, talked about it on, on, on there in the blog post.And they say, we, we actually did an experiment, right? Attention scales with the number of heads, obviously. Like if you have 64 heads versus 32 heads, you do half the work of attention. You still scale quadratic, but you do half the work. And they made a, a very specific like. Sort of barter in their system, in their architecture, they basically said, Hey, what if we gave it more experts, so we're gonna use more memory capacity.But we keep the amount of activated experts the same. We increase the expert sparsity, so we have fewer experts act. The ratio to of experts activated to number of experts is smaller, and we decrease the number of attention heads.Vibhu: And kind of for context, what the, what we had been seeing was you make models sparser instead.So no one was really touching heads. You're just having, uh,Kyle: well, they, they did, they implicitly made it sparser.Vibhu: Yeah, yeah. For, for Kimmy. They did,Kyle: yes.Vibhu: They also made it sparser. But basically what we were seeing was people were at the level of, okay, there's a sparsity ratio. You want more total parameters, less active, and that's sparsity.[00:46:00]But what you see from papers, like, the labs like moonshot deep seek, they go to the level of, okay, outside of just number of experts, you can also change how many attention heads and less attention layers. More attention. Layers. Layers, yeah. Yes, yes. So, and that's all basically coming back to, just tied together is like hardware model, co-design, which isKyle: hardware model, co model, context, co-design.Vibhu: Yeah.Kyle: Right. Like if you were training a, a model that was like. Really, really short context, uh, or like really is good at super short context tasks. You may like design it in a way such that like you don't care about attention scaling because it hasn't hit that, like the turning point where like the quadratic curve takes over.Nader: How do you consider attention or context as a separate part of the co-design? Like I would imagine hardware or just how I would've thought of it is like hardware model. Co-design would be hardware model context co-designKyle: because the harness and the context that is produced by the harness is a part of the model.Once it's trained in,Vibhu: like even though towards the end you'll do long context, you're not changing architecture through I see. Training. Yeah.Kyle: I mean you can try.swyx: You're saying [00:47:00] everyone's training the harness into the model.Kyle: I would say to some degree, orswyx: there's co-design for harness. I know there's a small amount, but I feel like not everyone has like gone full send on this.Kyle: I think, I think I think it's important to internalize the harness that you think the model will be running. Running into the model.swyx: Yeah. Interesting. Okay. Bash is like the universal harness,Kyle: right? Like I'll, I'll give. An example here, right? I mean, or just like a, like a, it's easy proof, right? If you can train against a harness and you're using that harness for everything, wouldn't you just train with the harness to ensure that you get the best possible quality out of,swyx: Well, the, uh, I, I can provide a counter argument.Yeah, sure. Which is what you wanna provide a generally useful model for other people to plug into their harnesses, right? So if youKyle: Yeah. Harnesses can be open, open source, right?swyx: Yeah. So I mean, that's, that's effectively what's happening with Codex.Kyle: Yeah.swyx: And, but like you may want like a different search tool and then you may have to name it differently or,Nader: I don't know how much people have pushed on this, but can you.Train a model, would it be, have you have people compared training a model for the for the harness versus [00:48:00] like post training forswyx: I think it's the same thing. It's the same thing. It's okay. Just extra post training. INader: see.swyx: And so, I mean, cognition does this course, it does this where you, you just have to like, if your tool is slightly different, um, either force your tool to be like the tool that they train for.Hmm. Or undo their training for their tool and then Oh, that's re retrain. Yeah. It's, it's really annoying and like,Kyle: I would hope that eventually we hit like a certain level of generality with respect to training newswyx: tools. This is not a GI like, it's, this is a really stupid like. Learn my tool b***h.Like, I don't know if, I don't know if I can say that, but like, you know, um, I think what my point kind of is, is that there's, like, I look at slopes of the scaling laws and like, this slope is not working, man. We, we are at a million token con

We continue our study of how evil was rising in Russia as the Blessed Mother was appearing at Fatima.Please support the Our Lady of Fatima Podcast:http://buymeacoffee.com/TerenceMStantonLike and subscribe on YouTube:https://m.youtube.com/@OurLadyOfFatimaPodcastFollow us on X:@FatimapodcastThank you!

Ryan and Emily discuss Hillary lies about Epstein connections, Israeli gov installed surveillance for Epstein, Trump sputters nonsense at Iran, Trump bombs more boats. To become a Breaking Points Premium Member and watch/listen to the show AD FREE, uncut and 1 hour early visit: www.breakingpoints.comMerch Store: https://shop.breakingpoints.com/See omnystudio.com/listener for privacy information.

A dangerous Arctic blast will hit our area this weekend... The new archbishop will be installed today at St Patrick's Cathedral... A woman literally gives blood to get a Harry Styles ticket full 471 Fri, 06 Feb 2026 10:48:31 +0000 7W1QFgQFm5t7IYS9zRvUWT1rUGDHW1pW emailnewsletter,news 1010 WINS ALL LOCAL emailnewsletter,news A dangerous Arctic blast will hit our area this weekend... The new archbishop will be installed today at St Patrick's Cathedral... A woman literally gives blood to get a Harry Styles ticket The podcast is hyper-focused on local news, issues and events in the New York City area. This podcast's purpose is to give New Yorkers New York news about their neighborhoods and shine a light on the issues happening in their backyard. 2024 © 2021 Audacy, Inc.

The All Local Afternoon Update for Friday, February 6 2026

 Sandy City has installed lit stop signs following an outcry from the community, after a deadly auto pedestrian accident and outcry of concern from the community. Sandy Mayor Monica Zoltanski joins Holly and Greg to discuss.

Andrew Lowth, RTÉ reporter, on Iarnród Eireann's new safety camera at the Merrion Gates in South Dublin railway level crossing

Leila Philip describes how a flow device installed by Mike Callahan saved an Audubon sanctuary pond during Hurricane Ida, proving that coexistence strategies are often more cost-effective than repairing flood damage. She concludes by emphasizing beavers as agents of hope, noting their wetlands store vast amounts of carbon and provide critical resilience against droughts and floods.1890

Craig Unger investigates the "October Surprise" following the 1979 seizure of 52 American hostages in Tehran. Iran's revolution overthrew the Shah, installed by the US in 1953, creating an anti-American Islamic Republic. The failed Desert One rescue mission on April 24, 1980, killed eight Americans and shocked the Carter administration, effectively ending his re-election prospects. Carter's weak position was exacerbated by his contentious relationship with Israeli Prime Minister Menachem Begin following the Camp David Accords. Candidate Ronald Reagan and his soon-to-be campaign head, Bill Casey, observed the developing crisis. Guest: Craig Unger. 1850 TEHRAN

BLISS: WEST COAST URBAN ISSUES AND THE PACK FIRE Guest: Jeff Bliss Seattle elected socialist Kate Wilson, who wants public grocery stores. The Luxor Pyramid in Las Vegas has installed a massive slide for visitors. Both San Francisco and Santa Monica are seeing major business failures and mall auctions due to unchecked crime and vagrancy. Los Angeles Mayor Bass requested citizen help for cleanup before the Olympics. Meanwhile, the 3,000-acre Pack Fire in Mono County is being aided by heavy rain. 1926

-- On the Show: -- A Fox News poll shows 60 percent of Americans blame Donald Trump for rising grocery prices, leaving Republicans panicked as he becomes tied to the inflation problem he once exploited -- Donald Trump, the oldest president to start a term, installs a paper sign labeled "Oval Office" to mark the room, prompting mockery online about his memory and taste -- Psychiatrist Dr. Bandy Lee warns that Donald Trump's insecurity and quest for control make him increasingly volatile, comparing his behavior to dangerous offenders she has studied -- Gavin Newsom shuts down a reporter on Meet the Press who accuses him of normalizing Trump's behavior, explaining he is mocking extremism, not amplifying it -- Donald Trump floods Truth Social with frantic all-caps rants about the filibuster, election fraud, and redistricting as his grip on power and control visibly unravels -- Donald Trump risks a constitutional crisis as he prepares to defy a Supreme Court ruling on tariffs, testing whether the nation's highest court has any real power to stop him -- Ted Cruz and Maria Bartiromo push false claims that the FBI probe "Arctic Frost" was Biden's Watergate, distracting from the Epstein files and real investigations into election interference -- The Friday Feedback segment -- On the Bonus Show: Conservative reactions to Zohran Mamdani winning the NYC mayor's race, the right tears itself apart over Nick Fuentes' appearance on Tucker Carlson's show, and much more...