Podcasts about svg

Summary The Grip Strip Podcast Episode 315 discusses recent motorsport events including IndyCar, NASCAR, and other racing series while previewing upcoming races. Major Points Christian Lundgaard claims his first IndyCar victory after 47 races. Polesitter Alex Palou faced issues, while Felix Rosenqvist had multiple early crashes. SVG dominates the NASCAR Tripleheader at Watkins Glen, marking his first win of 2026. Zilisch achieves three consecutive wins in the O'Reilly series with a last-lap pass. Kaden Honeycutt earns wins in both the Truck Series and ARCA heading to Dover. The episode includes updates on various racing series: Indy NXT, WEC, WRC, MotoGP, and more. Preview of Indy 500 Qualifying and picks for upcoming NASCAR events.

https://itayverchik.co.il/ase/אחת הטעויות הנפוצות ביותר בבניית אתרי וורדפרס היא התקנת עשרות תוספים (Plugins) קטנים עבור פעולות פשוטות: תוסף אחד לשכפול פוסטים, תוסף שני לאישור העלאת קבצי SVG, תוסף שלישי לשינוי כתובת ההתחברות לאתר, ותוסף רביעי לשינוי סדר התפריט. כל תוסף כזה מכביד על השרת, מאט את האתר ופותח פרצות אבטחה.בסרטון הזה אני מציג לכם את Admin and Site Enhancements (או בקיצור: ASE) – תוסף מודולרי אחד שמרכז בתוכו עשרות כלים חיוניים לניהול וורדפרס. היתרון הגדול שלו הוא שאתם מפעילים אך ורק את הפיצ'רים שאתם צריכים, והשאר נשאר כבוי ולא מעמיס על קוד האתר.מה נראה במדריך?ניהול תוכן ומדיה: איך להפעיל שכפול פוסטים ועמודים בקליק (Duplicate), לאפשר העלאת קבצי וקטור (SVG) בצורה מאובטחת, ולהחליף קבצי מדיה קיימים מבלי לשבור קישורים.אבטחת האתר (Security): איך לשנות את כתובת ההתחברות הסטנדרטית (wp-admin) כדי למנוע פריצות, ואיך להגביל את מספר ניסיונות ההתחברות השגויים (Limit Login Attempts).שיפור ממשק הניהול (Admin Interface): איך לנקות את לוח הבקרה (Dashboard) מכל ההודעות והפרסומות המציקות של תוספים אחרים, ואיך לסדר או להסתיר פריטים בתפריט הצדדי.אופטימיזציה וביצועים: ניהול גרסאות (Revisions Control) כדי למנוע ניפוח של מסד הנתונים, ושינוי כתובת השולח (SMTP) להודעות המערכת של האתר.מעבר לשימוש ב-ASE יעזור לכם לצמצם את כמות התוספים באתר בחצי, לשפר את המהירות ולשמור על סביבת עבודה נקייה ומקצועית.המדריך עזר לכם לעשות סדר באתר הוורדפרס שלכם? אל תשכחו לעשות לייק לסרטון, להירשם לערוץ וללחוץ על הפעמון כדי לקבל עדכונים על עוד מדריכי וורדפרס, אופטימיזציה לאתרים, ניהול שרתים ושיווק דיגיטלי.

In this episode, Parker Kligerman and Landon Cassill break down Parker's upcoming Truck Series race at Michigan, diving into rear spring setup philosophies and aerodynamic strategies. They recap Nashville's thrilling Cup race finale before debating race lengths and stage breaks in NASCAR. Driver news includes Corey Heim's 2027 Cup commitment and Shane van Gisbergen's impressive oval progression. The guys also preview Monaco and discuss Mercedes' FIA power unit controversy. Leave us a voicemail! https://moneylap.com Or email us! friends@themoneylap.com Timestamps: 01:00 - Intro 05:48 - The eRacr eNASCAR Team Update 10:45 - NASCAR Nashville Weekend Recap 12:15 - Debate: Should NASCAR Races Be Shorter? 28:25 - Amazon Prime's NASCAR Viewership 31:02 - Praise for Amazon's Broadcast Team 32:48 - Corey Heim to 23XI Racing in 2027 34:23 - Project 91 and Driver News 38:27 - High Horsepower and SVG's Performance 44:45 - NASCAR O'Reilly and Truck Series News 46:40 - Formula 1 Monaco GP Preview 50:00 - IndyCar Detroit Recap and Gateway Preview 51:27 - Listener Comments 56:39 - Weekend Race Picks (Timestamps are a rough timing and may require a little scrubbing to find the start of the topic) The Money Lap is the ultimate motorsport show (not a podcast) with Parker Kligerman and Landon Cassill professional racecar drivers and hilarious hosts taking you through the world of motorsports. Covering NASCAR, F1, Indycar, and more, they'll provide the scoop, gossip, laughs, and stories from the racing biz. With over 2400 unique products currently in stock, Spoiler Diecast boasts one of the largest inventories in the industry. We are NASCAR focused, offering a wide range of diecast and apparel options. But that's not all. We've expanded our catalog to include diecast for dirt/sprint cars, Indycar, and F1. As passionate racing fans ourselves, we're constantly growing our offerings to cater to different forms of racing. Use promo code "moneylap" for free shipping for orders over $20. https://www.spoilerdiecast.com/ Copyright 2026, Pixel Racing, LLC. All Rights Reserved.

NHRA Top Fuel rookie Maddi Gordon joins Corey LaJoie and Skip Flores to explain what 12,000 horsepower really feels like, how she earned her way in the shop, what Ron Capps saw in her, and how she once won a round with no shift lights, no two-step, and no data.Corey and Skip also recap Nashville, SVG's continued rise, Denny Hamlin's move, O'Reilly racing, and why simple floors and big horsepower might be the answer.All this and more on Stacking Pennies Podcast. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Pre-show: Marco has something to commend Ubiquiti marketing video Spanning Tree Protocol Sonos & Networking Documentation Follow-up: Formula 1 on Apple TV The case for alarm reminders (via Matthew Cave) SVG can do animations — and way more! (via Vítor) SVG can do THAT‽ Yes, you can use AI for ffmpeg, but have you tried Lossless Cut? SF Symbols in Marco’s Reminder app (via Clarko) How can we bemoan Electron and cheer WebViews? (via Julian Gamble) If Finder moves are no good, are mvs the same? Defrag lives on …in APFS diskutil apfs defragment [disk] enable [disk] is something along the lines of diske3 or disk3s1, that you get via diskutil list MJ Tsai AI Sentiment AI levels… down?… your worst coworker (via Nathan) Ireland compels data center developers to bring their own clean energy (via Ian Robinson) Large Energy User Action Plan Perspectives on art Original Monet The Ferrari Luce Previously on ATP Purosangue Jaguar I-Pace BMW i3 BMW i8 GMA T.33 Porsche Taycan Galleries The Verge Car and Driver Exterior Interior Coverage The Verge Top Gear Cleo Abram MKBHD (stationary tour) ba-dum tss John’s EV Stupidity Checklist Saturday Night Live Affordance Post-show: RIP Destiny 2 Associated layoffs, because, of course Destiny 1 on Wikipedia Penny Arcade Members-only ATP Overtime: Bambu vs. its community How one private message could change the face of 3D printing Sponsored by: zocdoc: Find the right doctor, right now. Squarespace: Save 10% off your first purchase of a website or domain using code atp. Become a member for ATP Overtime, ad-free episodes, member specials, and our early-release, unedited “bootleg” feed!

In deze aflevering geeft Rick een update over het nieuwe HTML sizes attribuut, bespreekt Michele de AI prijsverhogingen, hebben we het over HTML in Canvas en AI SVG generators. Ook bespreken we de mindset om juist slechte dingen te ontwerpen en knutselt Rick met Home Assistant. 00:50 - Update van HTML Sizes auto attribuut - https://piccalil.li/blog/the-end-of-responsive-images/ 07:40 - Prijzen van AI modellen gaan omhoog 18:00 - CSS Object-view-box - https://developer.mozilla.org/en-US/docs/Web/CSS/Reference/Properties/object-view-box 20:05 - HTML in Canvas - https://x.com/wesbos/status/2041594973674483851?s=52&t=fe46zCuaw_E4SsdlMbCChw 24:55 - Why designing crap makes you a better designer - https://uxdesign.cc/why-designing-terrible-solutions-makes-you-a-better-designer-76b2f0f59956 28:50 - SVG's genereren met Quiver AI - https://x.com/quiverai/status/2044864082180706721?s=52&t=fe46zCuaw_E4SsdlMbCChw 32:30 - Rick's geknutselde wall tablet met Home Assistant 39:09 - CSSDay komt er weer aan 41:25 - Benning Duspol - https://www.benning.de/products-en/testing-measuring-and-safety-equipment/test-equipment-voltage-tester/voltage-tester-duspol.html 44:28 - Johnny Motion op X - https://x.com/JohnnyMotion

The Final Lap Weekly is loaded this week as Kerry Murphey and Toby Christie break down a massive week in motorsports! SVG does it again on the road course with a huge Watkins Glen win, proving once more that Shane van Gisbergen is becoming one of NASCAR's most dangerous road-course weapons. Plus, Denny Hamlin captures the NASCAR All-Star Race at Dover, adding another major moment to his already headline-filled season. Then the show shifts to breaking news: Kyle Busch has been hospitalized with what has been described as a “severe illness” and will miss the Coca-Cola 600 weekend at Charlotte Motor Speedway, with Austin Hill stepping into the No. 8 Chevrolet. Rowdy Dragon stops by with Fantasy NASCAR Picks for the Coca-Cola 600, and the crew previews the biggest racing weekend of the year: Formula 1, the Indianapolis 500, and NASCAR's marathon crown jewel, the Coca-Cola 600 from Charlotte Motor Speedway. If you love racing, this is the weekend — and this episode covers it all! This episode is dedicated to my Mom whom I lost on race morning of Watkins Glen weekend. She was a huge NASCAR fan, and Tony Stewart fan, she will be missed. -Kerry NASCAR News Provided By: http://tobychristie.com -Listen on Spotify -Listen on Apple Podcasts -Click To Play Fantasy NASCAR With Us!  -Giving Fun Is Here: Patreon.com/thefinallap NASCAR podcast, The Final Lap Weekly, Kerry Murphey, Toby Christie, Kyle Busch hospitalized, Kyle Busch severe illness, Kyle Busch Coca-Cola 600, Austin Hill No. 8, Charlotte Motor Speedway, Coca-Cola 600 preview, NASCAR Charlotte preview, SVG Watkins Glen, Shane van Gisbergen wins Watkins Glen, Watkins Glen recap, Denny Hamlin All Star Race, NASCAR All Star Race Dover, Rowdy Dragon Fantasy NASCAR, Fantasy NASCAR picks, Coke 600 fantasy picks, Indianapolis 500, Indy 500 weekend, Formula 1, biggest racing weekend, NASCAR news, NASCAR breaking news, NASCAR Cup Series, NASCAR race recap Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

Kyle Robert and Brian Twining are in to preview the Coca-Cola 600 as NASCAR returns to points racing post All-Star break. They look at the outright betting board discuss their favorite strategies for a race. Are we set up for a Denny Domination?But first they recap an impressive SVG win, DraftKings lineups and the betting card from Watkins Glen. We got did we get right beyond the SVG outright wagers?Subscribe to the Green White Checkered our FREE newsletter on Substack for more picks, DraftKings picks and bets every race day. Plus race recaps and early line shopping every Tuesday https://aoppodcast.substack.com/Follow Win the Race on YouTube - https://www.youtube.com/@UChJp58R4PTvPmzYcjXlVNPQ X - https://x.com/WINTHERACEP1Subscribe to Win the Race www.wintherace.com00:00 Intro02:37 Watkins Glen Betting and DFS Recap12:38 Coca-Cola 600 Outright Odds29:56 Coca-Cola 600 Placements and Match-ups47:35 Coca-Cola 600 Betting Card Recap

SVG said "screw fuel strategy" and proves that impressive racing is more entertaining than impressive fuel saving at The Glen. We talk the latest NASCAR news - including why on earth the Chicago Street course could return next year - along with our Paint Scheme Preview and Picks for the All-Star Race in Dover. The Rundown:- Watkins Glen - SVG is in another universe- NASCAR actually enforces track limits - and it all worked out just fine- The Glen ratings- NASCAR Standings- NASCAR News:- Ricky Stenhouse Jr. signs a new deal- The Glen is moving back to the playoffs- Chicago Street Course return? Why?- Katherine Legge attempting the double- Silly Season rumors- Sponsor News- Dover! Our Paint Scheme Preview and Picks for the All-Star RaceFind the latest episodes at InTheDraftShow.com, follow on Bluesky and Instagram @InTheDraftShow – and like the show on Facebook at facebook.com/InTheDraftShowThanks for listening!

Shane van Gisbergen wins again at Watkins Glen — and once again the question comes up: are we watching the greatest road course driver NASCAR has ever seen? In Season 5, Episode 16 of The Backstretch Podcast, Heather Williams and crew chief Chris Carrier break down SVG's latest road course masterclass and what separates him from the rest of the field whenever NASCAR turns right. We also dive into:

Ah, snap, here we go again. It's another 30 minutes of nothing but the best Dirty Mo Media has to offer. It's Dirty Thirty time, y'all! First up, Dale Jr. wants everyone to know about Shan van Gisbergen's unique footwork that sets him apart (by a few seconds...) from the rest of the field. Then we hear from SVG himself on whether he feels it's truly an advantage or not. Over in the land of spotters, the Door Bumper Clear crew welcomed Hall of Famer Kurt Busch to the table, where he told us about his championship run in 2004, his imaginary friends, and the cougar that rode with him at Talladega. Dale Jr. interviewed basketball's newest phenom and Charlotte Hornets rookie, Kon Knueppel! He discusses the moment he got called up and the Rookie of the Year battle with Cooper Flagg. Last but not least, we have an epic Bless Your 'Hardt moment. Dale & Amy play a rousing round of "This or That," where the conversation about hard vs. soft taco shells divides the room between dirty minds and innocent foodies.  Another week down, another 30 minutes come and gone — feels faster every week! Don't forget, our new Zero To Freedom line is LIVE on shop.dirtymomedia.com Check out Dirty Mo Media on YouTube: https://www.youtube.com/@DirtyMoMedia Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

NASCAR Roundtable Publisher Tyler Jones (@TylerJonesLive), and The Racing Experts Founder Dominic Aragon (@DominicAragon) are joined by KickIn The Tires Editor Jerry Jordan (@JerryJordan_KTT).(0:30-9:55) Watkins Glen Race Recap: Shane van Gisbergen wins at The Glen, how SVG stacks up historically, and Michael McDowell's strong showing.(9:55-14:00) Introducing Jerry Jordan.(14:00-37:50) Jerry Jordan on Shane van Gisbergen, Tyler Reedick, Kyle Busch's future, Dover, and SMI's future schedules.(37:50-1:05:00) News and Notes: Ricky Stenhouse Jr.'s extension, RFK Racing's pursuit of another charter, NASCAR Hall of Fame nominees, and All-Star Race Preview + Odds.

Episode 279 of NasCardRadio is packed with NASCAR racing and trading card hobby talk! Val and Logan recap the weekend races from Watkins Glen, discuss SVG's continued road course dominance, Connor Zilisch's growing hobby market, and the latest Panini Instant releases. The guys also dive deep into the idea of bringing back NASCAR-only card and memorabilia shows and debate whether drivers charging for autographs could actually help the hobby. Also in this episode: • Listener pulls an unbelievable Dale Earnhardt autograph from a sealed vintage Max set • King's Court features massive NASCAR card sales and rare 1/1s • Indy memorabilia show discussion • NASCAR fan day experiences • Vintage NASCAR card stories and hobby history Thanks for listening to NasCardRadio — where trading cards and racing meet!

It's All-Star Weekend at Dover. Chase McCabe takes you through what to expect, plus fall out from SVG's big win at The Glen and he's joined by Rookie Connor Zilisch and Fox Sports' Michael Waltrip. 

Eric Jang walks through how to build AlphaGo from scratch, but with modern AI tools.Sometimes you understand the future better by stepping backward. AlphaGo is still the cleanest worked example of the primitives of intelligence: search, learning from experience, and self-play. You have to go back to 2017 to get insight into how the more general AIs of the future might learn.Once he explained how AlphaGo works, it gave us the context to have a discussion about how RL works in LLMs and how it could work better – naive policy gradient RL has to figure out which of the 100k+ tokens in your trajectory actually got you the right answer, while AlphaGo's MCTS suggests a strictly better action every single move, giving you a training target that sidesteps the credit assignment problem. The way humans learn is surely closer to the second.Eric also kickstarted an Autoresearch loop on his project. And it was very interesting to discuss which parts of AI research LLMs can already automate pretty well (implementing and running experiments, optimizing hyperparameters) and which they still struggle with (choosing the right question to investigate next, escaping research dead ends). Informative to all the recent discussion about when we should expect an intelligence explosion, and what it would look like from the inside.Watch on YouTube. Read the transcript.And check out the flashcards I wrote to retain the insights.Sponsors* Cursor‘s agent SDK let me build a pipeline to generate flashcards for this episode. For each card, I had an agent read the transcript, ingest blackboard screenshots, generate an SVG visual, and run everything through a critic. A durable agent is much better at this kind of work than a chain of LLM calls, and Cursor's SDK made it easy. Check out the cards at flashcards.dwarkesh.com and get started with the SDK at cursor.com/dwarkesh* Jane Street gave me a real deep-dive tour of one of their datacenters. I got to ask a bunch of questions to Ron Minsky, who co-leads Jane Street's tech group, and Dan Pontecorvo, who runs Jane Street's physical engineering team. They were willing to literally pull up the floorboards and take out racks to explain how everything works. Check out the full tour at janestreet.com/dwarkeshTimestamps(00:00:00) – Basics of Go(00:08:17) – Monte Carlo Tree Search(00:32:04) – What the neural network does(01:00:33) – Self-play(01:25:38) – Alternative RL approaches(01:45:47) – Why doesn't MCTS work for LLMs(02:01:09) – Off-policy training(02:12:02) – RL is even more information inefficient than you thought(02:22:16) – Automated AI researchers Get full access to Dwarkesh Podcast at www.dwarkesh.com/subscribe

Episode 121: NASCAR debrief with SVG Don't worry, this isn't just another right foot braking chat. This is SVG at his best. 00:00:00 INTRO 00:03:02 Trucks, O'reillys, Zillisch Incident 00:10:27 Coming Through The Pack At Watkins 00:13:38 Sunday Night Kick Ons 00:14:57 Road Course Pressure 00:25:17 Dover Million Dollar Purse 00:25:48 Who Can Challenge SVG 00:28:03 SVG Picks Best Current Driver 00:28:55 SMAC & SVG Audio Recording 00:35:54 Marcos Ambrose Chat 00:41:01 Could Supercars Do Longer Races 00:56:34 San Diego Street Course 01:05:30 Supercars Record a voice message: https://memo.fm/apexhuntersunited/ Get yaself some AHU merch: https://apexhuntersunited.com/ Patreon: https://patreon.com/ApexHuntersUnited?utm_medium=unknown&utm_source=join_link&utm_campaign=creatorshare_creator&utm_content=copyLink eToro: https://www.etoro.com/au/?utm_medium=TV&utm_source=128759&utm_content=20601&utm_serial=Apex_Hunters&utm_campaign=Apex_Hunters&utm_term East Coast Car Rentals Discount code: AHU15 for 15% off at: https://www.eastcoastcarrentals.com.au/ http://www.lancastermotors.com.au/ https://www.tricoproducts.com.au/ https://www.shawandpartners.com.au/home  

In this episode of The Money Lap, hosts Parker and Landon Cassill recap a packed motorsports weekend at Watkins Glen, highlighting Shane Van Gisbergen's dominant Cup Series win and his Right Foot Braking Dominance! They praise NASCAR's physical track limit barriers and strong race control. Kaden Honeycutt's breakout Truck Series victory gets a shoutout, as does Connor Zilisch's impressive O'Reilly Series comeback win. The hosts also preview the All-Star race at Dover, discuss silly season rumors, and touch on Katherine Legge's Indy 500/Coca-Cola 600 double attempt before sharing their race picks. Leave us a voicemail! https://moneylap.com Or email us! friends@themoneylap.com Timestamps: 00:00 - Intro 02:23 - Virtual Race Team and Past Events 04:54 - Parker's RV Booking Venture 07:44 - Landon's Go-Kart Camping Trip 10:27 - NASCAR's New Track Limits at Watkins Glen 11:32 - Truck Race Winner Caden Honeycutt 15:31 - O'Reilly Series Race Recap 21:53 - Jesse Love's Performance 24:23 - Shane van Gisbergen's Cup Race Win 26:21 - SVG's Driving Technique 32:22 - Advice for Young Drivers 43:41 - Cody Ware Incident and Race Control 46:51 - All-Star Race at Dover Preview 57:42 - Ricky Stenhouse Jr.'s Contract Extension 1:02:04 - Silly Season Rumors and Michael McDowell 1:04:25 - Katherine Legge's Indy 500/Coke 600 Double 1:06:14 - PR Lap 1:09:10 - Outro (Timestamps are a rough timing and may require a little scrubbing to find the start of the topic) With over 2400 unique products currently in stock, Spoiler Diecast boasts one of the largest inventories in the industry. We are NASCAR focused, offering a wide range of diecast and apparel options. But that's not all. We've expanded our catalog to include diecast for dirt/sprint cars, Indycar, and F1. As passionate racing fans ourselves, we're constantly growing our offerings to cater to different forms of racing. Use promo code "moneylap" for free shipping. https://www.spoilerdiecast.com/ The Money Lap is the ultimate motorsport show (not a podcast) with Parker Kligerman and Landon Cassill professional racecar drivers and hilarious hosts taking you through the world of motorsports. Covering NASCAR, F1, Indycar, and more, they'll provide the scoop, gossip, laughs, and stories from the racing biz. Make sure to subscribe, review and follow us for the coolest stuff in motorsports https://www.instagram.com/themoneylap https://x.com/themoneylap https://www.tiktok.com/@themoneylap Copyright Pixel Racing, LLC 2026

Back in the silo after a dominating performance by SVG! We talk all about the Truck Series, O'reilly's Series, and of course, the incredible clinic on how to win Watkins Glen by none other than Shane Van Gisbergen. We look ahead to the Allstar Race from Dover and make a couple of picks for our weekly head-to-head battle. IndyCar has kicked off the month of May with an exciting Indy Grand Prix on the road course. We talk about the upcoming week of practices and 500 qualifying this coming weekend.NHRA heads to Joliet Illinois for the Route 66 Nationals this weekend. Thanks for tuning in! 

In this edition of Into The Smoke, Evan recaps SVG's absurd performance at Watkins Glen, and if this Sunday's lackluster All-Star Race could be the end of the road for Dover.See omnystudio.com/listener for privacy information.

The morning of Thursday, November 20, 1969 started with a bang for the islanders on the Windward coast of Saint Vincent Island. For some, it was like the gods had finally gotten around to answering their prayers. A huge party broke out on the beach shortly after sunrise.And within hours, it spread to dozens of nearby villages.  But as the weekend progressed, the locals realized that something was horribly wrong, and that the once-in-a-lifetime windfall was actually a curse in disguise.  Cultural BackgroundSt. Vincent and the Grenadines, or SVG, is located in the southwestern Caribbean between Saint Lucia to the north and Barbados and Grenada to the south. The country is made up of 32 islands and cays and only has about 150 square miles (390 square km) of territory – most of which is on the northernmost island of Saint Vincent. Saint Vincent is also home to the capital of Kingstown – not to be confused with Kingston, Jamaica, which is nearly 1,100 miles (1,770 km) to the northwest.  In the late 1960s, SVG had a population of about 95,000 residents – about two-thirds of whom were natives of African descent. By some estimates, nearly three-quarters of the population worked in banana production which accounted for the lion's share of the country's economy. The locals worked hard on their small family plots and eked out comfortable if modest livings. And when it was time for recreation, they usually engaged in the island's most quintessential pastime – liming. In layman's terms, liming is slang for relaxing, gossipping, and enjoying the pleasant weather and beautiful scenery with friends and family.  And sometimes, they threw in another element – uber-strong island “overproof” rum called Jack Iron. And by strong, we're talking about 150 to 180-proof.  To put that into perspective, most spirits like Scotch, vodka and American bourbon are 80-proof, or 40% alcohol by volume. By comparison, 180-proof Jack Iron is more than twice as strong – or about 90% alcohol by volume.  And unlike Scotch and Bourbon, it's clear because the locals drink it immediately after distillation instead of aging it in oak barrels. Most Jack Iron is produced in small home stills where quality control is minimal. And due to its potency, it smells more like an industrial solvent than an intoxicating beverage fit for human consumption. As for how it got its name, one common explanation is that consuming it makes drinkers feel like they've been whalloped in the head with an iron car jack. Then again, the “iron” may be a reference to masculine constitution. As in, you pretty much have to be made of iron to drink it because it packs such a punch. From the immediate numbing of the lips and mouth, to the face-twisting throat burn to the final kick in the abdomen when the liquid finally enters the stomach, the experience is nothing short of unforgettable.  In fact, Jack Iron is so entrenched in the local culture that islanders usually pour a small portion of every new bottle onto the ground so deceased ancestors can enjoy it too. And fishermen, laborers and banana farms often take a few nips before starting their day as a way of fortifying themselves against the strenuous work ahead. But as ubiquitous as Jack Iron is, the islanders generally disapprove of public drunkenness. Actually, they revere drinkers who can hold their liquor. The goal is to consume just enough to get a jolt before work or to take the edge off while liming away a lazy afternoon. But when the conditions are just right – like they were in the fall of 1969 – the islanders aren't afraid to let loose and throw caution to the wind.Shipwreck On the night of Wednesday, November 19, the 90-ton schooner, Ruth 114, was traveling from Trinidad to Martinique carrying a dozen casks of Jack Iron, 100 drums of methanol – or wood alcohol – and 150 drums of aviation fuel called avgas. Before continuing on, it's worth pointing out that the drums of fuel and methanol were marked with big, red “DANGER” warnings. Anyway..the storm got so bad by 3:00 the following morning that the schooner sustained serious sail and rudder damage, sprung a leak, and began filling up with seawater. The eight-man crew tried in vain to save the vessel and its valuable cargo. But before long, Captain Kenneth Richardson saw the writing on the wall and ordered everyone to abandon ship. At the time, they were within sight of the beach at Colonarie on Saint Vincent's Windward coast.The crew launched a lifeboat, rowed to shore safely and watched the listing schooner disappear into the darkness. After that, it drifted in the heavy seas before turning landward and running aground at Big Level Beach near the village of Sandy Bay.And when the sun came up, curious villagers waded out into the surf, climbed aboard, inspected the damaged vessel and quickly began relieving it of its precious cargo. By then, Captain Richardson had alerted the police and told them where he thought the schooner would be. Two vessels from Kingstown were dispatched to locate the Ruth 114 shortly thereafter, but they never found it. PartyLuckily, the hardest part of the salvage operation was getting the drums and casks over the gunwale and into the surf.And since the drums floated, it was just a matter of pushing them toward land and rolling them onto the beach. In less than an hour, dozens of drums and casks were lined up just waiting to be tapped. And before long, word spread to nearby villages like Owia, Sandy Bay, Rose Bank and Orange Hill that there was enough Iron Jack rum to keep everybody buzzed for weeks on end.  Within the hour, the beach was crowded with hundreds of locals intent on getting their fair share. For many, it felt like a once-in-a-lifetime “Manna from Heaven” moment. Or in local terms, a gift from the sea. There was also a sense of urgency, because everyone knew it was only a matter of time before the police showed up, confiscated the cargo and brought the impromptu party to a grinding halt.  As such, the wood casks containing the Jack Iron rum were immediately tapped. It's unclear if it turned into a free-for-all or if the locals who made the discovery managed to maintain some semblance or order. Whatever the case, the villagers began filling up everything from coffee cups and teapots to glass jars and empty soda bottles. And in the chaos, they also opened the metal drums and began consuming the avgas and methanol– even though they were clearly marked with big warning signs and ominous red Xs. Like Jack Iron, avgas and methanol are usually relatively clear. So in the heat of the moment, it's not that surprising that they didn't notice they weren't drinking the real thing. Of course, the question was, couldn't they taste and smell the difference?  After all, avgas is a lot like gasoline. And methanol has even more of a kick than Jack Iron. Nonetheless, they apparently weren't aware that they were consuming potentially deadly substances. And by then, some of them had already consumed real Jack Iron which lowered their inhibitions, numbed their taste beds, and made their noses far less sensitive than they would have otherwise been. As for the methanol and avgas, some of the partiers turned it into punch by adding sugar, water and lime juice which masked the taste and smell even more. In the early going, the grateful revelers felt like they always did after drinking intoxicating spirits..warm, tipsy, and downright jovial.With so many drums, the party continued throughout the day, into the night and well into the weekend. That said, the furor eventually died down as the crowd dispersed.  And at that moment, the islanders who found the schooner decided that they had a rare opportunity to make some serious money. And with that, they began selling what was left.After that, the buyers took what they thought was bona fide Jack Iron rum back to their homes and businesses where they consumed it, sold it, and gave it to close friends and family members in their own villages and other villages up and down the coast.  Aftermath/Medical ResponseThe fun and festive atmosphere took an alarming and unexpected turn about a day later. By then, many of the formerly happy villagers were experiencing serious symptoms including dizziness, loss of motor skills, stomach cramps, nausea and vomiting, as well as blurry vision like they were viewing their surroundings through a blinding snowstorm. Interestingly, not everyone who came down with these symptoms drank that much. At that point, they had no idea what was happening. But below the surface, their bodies were busy metabolizing the methanol and avgas into toxic formaldehyde and formic acid. Patients began showing up at local clinics en masse on November 22 and 23. And by the following day, ambulances from all over the island began arriving at Kingstown General Hospital. In a matter of hours, the facility and its woefully unprepared staff were dealing with hundreds of sick patients, many of who were teetering on the edge of death. Writhing, moaning, vomiting, and in some cases comatose islanders were crammed into every nook and cranny. Many were relegated to straw mats on both sides of the already-cramped corridors because the rooms were totally full. By then, the hospital staff knew about the shipwreck and the liquid from the metal drums that the sick patients consumed. The problem was, they had no way of knowing if they drank straight methanol or avgas which was actually a mixture of fuel, methanol and other toxic hydrocarbons.And to make matters worse, they couldn't pump the pati

Nick Felice and Paul Russo return to the studio dry and warm on this edition of Fresh Takes. The guys recap NASCAR at Watkins Glen, where the main storylines were the weather, mud, and SVG dominating again. Next, they talk about the NBA, where two series have been sweeps while the others continue to battle out in physical fashion. Lastly, the guys revisit a conversation from a couple of weeks ago as Paul Skenes continues his hot start to the season on the mound.

Shane Van Gisbergen's road course dominance continues, and Dale Earnhardt Jr. is here to unpack it all on a new episode of Dirty Air. He joins co-host TJ Majors to chat all things Watkins Glen and look ahead to the All-Star race at Dover: - Exactly what SVG is doing differently than all other NASCAR drivers at road courses - The Trans Am Series is training a new generation of great road racers - Catching up on all the calamity from Watkins Glen - The risk of making unnecessary changes to tracks - Race winner Shane Van Gisbergen joins the show - Recapping this year's format for the All-Star race   During the Ask Jr. portion of the episode, listeners sent in questions regarding: - Cole Swindell at the CARS Tour race at Ace Speedway - Kasey Kahne and Boo Weekley are still winning - The new Hell Let Loose game - Dale's 1999 Busch Series win at Watkins Glen - Cage diving with sharks - Hats or die-casts - Greenville-Pickens Speedway updates - Multi-class racing in NASCAR Check out Dirty Mo Media on YouTube: https://www.youtube.com/@DirtyMoMedia Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

We are almost halfway through the regular season as we leave Watkins Glen behind just as SVG left the field behind on Sunday to gain his first win of 2026. The broadcast leaves things to be desired, and we discuss the upcoming All-Star Race format. We make our picks for Dover and look at who still has a chance to point into the Chase-Offs. Make sure to follow us on all socials and like and share!https://linktr.ee/gasisontherightpodcast

In the Mapcreator booth at NAB in Las Vegas, Julia Schellekens provides an update on their service that delivers detailed maps for news and other organizations who want to clearly show what is happening where. With a wide array of export and animation capabilities to help drive home the information, it is almost certain that you have seen their product in use no matter where in the world you are.  Show Notes: Chapters: 00:03 MacVoices at NAB 2026 00:08 Chuck Joiner opens from NAB in Las Vegas 00:12 Returning to the Mapcreator booth 00:24 Julia joins Chuck to show what is new 00:37 What Mapcreator is and how it works00:43 Creating static, interactive, and animated maps 00:47 Mapping tools for journalists and reporters 01:37 Helping news agencies focus on the story 02:16 What's new with MapCreator this year 02:26 Newsroom system and Adobe workflow integrations 02:52 Keeping users in their preferred design tools 03:29 Maps and visuals as storytelling tools 03:41 Creating animations quickly from GPX files 04:05 Matching map creation to fast-moving news 04:12 Export options for interactive maps 04:26 Static map exports including PNG, JPEG, PDF, and SVG 04:34 Animated exports including MOV, MP4, WebM, and image sequences 05:27 Why Mapcreator is more than a quick coded tool 05:34 Reducing manual work and saving production time 05:49 Mapcreator website: Mapcreator.io Support:      Become a MacVoices Patron on Patreon      http://patreon.com/macvoices      Enjoy this episode? Make a one-time donation with PayPal Connect:      Web:      http://macvoices.com      Twitter:      http://www.twitter.com/chuckjoiner      http://www.twitter.com/macvoices      Mastodon:      https://mastodon.cloud/@chuckjoiner      Facebook:      http://www.facebook.com/chuck.joiner      MacVoices Page on Facebook:      http://www.facebook.com/macvoices/      MacVoices Group on Facebook:      http://www.facebook.com/groups/macvoice      LinkedIn:      https://www.linkedin.com/in/chuckjoiner/      Instagram:      https://www.instagram.com/chuckjoiner/ Subscribe:      Audio in iTunes      Video in iTunes      Subscribe manually via iTunes or any podcatcher:      Audio: http://www.macvoices.com/rss/macvoicesrss      Video: http://www.macvoices.com/rss/macvoicesvideorss

Fuel saving, cut line conversations, and Shane van Gisbergen putting on another road course masterclass. This week on Action Detrimental, the guys break down Ross Chastain running out of gas late, why Watkins Glen was still a solid points day, and how frustrating it can be to save fuel instead of driving all out. Plus, they dive into NASCAR's road course coverage issues and why fans at home are missing too much of the action during some of the biggest moments of the race. They also debate whether a road course belongs in the playoffs, if anyone can eventually challenge SVG on these tracks, and why Connor Zilisch might be the next guy up. Add in the Ryan Preece penalty controversy, Kaden Honeycutt's first Truck Series win, and a look ahead to All-Star Weekend, and there is plenty to unpack in this one. Let us know in the comments if you think NASCAR should keep a road course in the playoffs! Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

This week on Stacking Pennies, Corey LaJoie sits down with a guest fans have been asking for: his dad, Randy LaJoie.Randy talks about being on the NASCAR Hall of Fame ballot, why the Hall should recognize more than just Cup Series greatness, the Cup deal he turned down after his Busch Series championships, the backyard go-kart track where Corey learned to race, and the seat company that became a major part of his legacy.Plus, Corey, Randy, and Ryan Flores break down Connor Zilisch's wild Watkins Glen win, SVG's road-course dominance, Formula Drift, IndyCar push-to-pass drama, Buckshot Jones stories, Dover memories, and the safety lessons short-track racers still need to hear.Drop your favorite Randy LaJoie memory in the comments, and let us know: Does the NASCAR Hall of Fame give lower-division racers enough respect?See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

In the ongoing debate of SVG vs. the field on road courses, SVG once again prevailed at Watkins Glen. Our resident NASCAR reporters Jeff Gluck and Jordan Bianchi were on the case to continue the discussion of SVG being the best NASCAR road racer of all-time and what to be done about the lack of action in the first 75 laps of the race. Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

Mac & Fitty start Monday's show, talking about the drama that unfolded at the Truist Championship, as an unlikely winner emerged, they talk about SVG's dominance at Watkins Glen, and dive into the Hornets lottery result, they replay sound from Panthers rookie minicamp, and the entire sports weekend overallSee omnystudio.com/listener for privacy information.

SVG had to win Watkins Glen the hard way after tracking the leaders down from 20+ seconds back to capture his seventh Cup victory. Hear what Shane had to say in Victory Lane after the race. 

Kyle Robert and Brian Twining get you set to Go Bowling at the Glen. NASCAR is getting ready for the second road course of the season at Watkins Glen. The guys run through every driver on DraftKings to break down their favorite targets and fades for this weeks NASCAR DFS slate! Then they build THREE GPP lineups for the race. But first, the guys talk through the updated Go Bowling at the Glen outright betting board. Shane Van Gisbergen is now a minus money favorite. Is there value with anyone not named SVG? How should YOU build your betting card? We break it all down!For more of our favorite bets and the full card make sure you are subscribed to the completely FREE Newsletter! It can be found at aoppodcast.substack.comAs a reminder, check out our friends over at @WINTHERACEP1  for an amazing selection of tools, games and discord. Their 100K simulations are among the best in market.00:00 Intro03:21 Watkins Glen Updated Betting Odds17:58 Watkins Glen High priced options24:55 Watkins Glen Mid pack options32:19 Watkins Glen Cheaper options34:37 Watkins Glen GPP lineups51:21 Watkins Glen Placings, Props and More

This week's Dirty Thirty is going to be all the buzz around town — and yes, that is a pun referring to the swarm at the Earnhardt house. Get ready to rock and roll on into the best 30 minutes of your week with Dirty Mo Media! Batting leadoff is Dale Jr. discussing Carson Hocevar's outing at the Met Gala, the moments he remembers being in the pop culture spotlight, and why he thinks more drivers should do the same. In the two spot, Door Bumper Clear heard from many No. 9 fans, known better around that set as "Chasesexuals." It's safe to say they were one happy bunch this week... You also get to meet someone named Pickles, who sounds like a trip. This week's guest interview on the Dale Jr. Download was with Mr. Mustache himself, Ryan Blaney! He talks about fatherhood and bonding with his own father, Dave Blaney, over life, racing, and everything in between. As you read earlier, the Earnhardts have had a fun week dealing with a swarm of bees that decided to use their back porch as a vacation rental for spring break. And last but not least, Denny Hamlin discusses SVG's chances of making the playoffs leading into the weekend at Watkins Glen. That's all for now! But before you go, head on over to shop.dirtymomedia.com to check out our new "Zero To Freedom" merch line. Check out Dirty Mo Media on YouTube: https://www.youtube.com/@DirtyMoMedia Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

Parker and Landon are back after a brief hiatus, catching up on everything motorsports. Landon shares updates on his kids' go-kart racing success and his first crew chief win, while Parker recaps his Truck Series return at Texas, finishing 11th. They break down Chase Elliott's Cup win, Ryan Preece's retaliation penalty, and Kyle Busch's struggles at RCR. The guys also discuss Watkins Glen's new track limit barriers, Kimi Antonelli's dominant F1 stretch, the FIA's potential V8 engine return, and Indy 500 preparations. The episode closes with a heartfelt tribute to the late Alex Zanardi. Leave us a voicemail! https://moneylap.com Or email us! friends@themoneylap.com Timestamps: 00:00 - Intro 07:58 - Parker's Truck Race at Texas 15:51 - Reading Apple Reviews 20:41 - Landon's Panini Card Easter Eggs 26:48 - AJ is Engaged! 27:40 - NASCAR Cup Series at Texas Recap 29:37 - Ryan Preece's Penalty 35:29 - Kyle Busch's Struggles Continue 40:29 - SVG's Playoff Chances & Spire's Speed 54:02 - Watkins Glen Track Limit Changes 1:00:09 - F1 Miami Grand Prix & Young Drivers 1:10:51 - Future of F1 Engines 1:12:49 - Indy 500 & Alex Zanardi Tribute 1:16:09 - PR Lap 1:20:38 - Outro (Timestamps are a rough timing and may require a little scrubbing to find the start of the topic) The Money Lap is the ultimate motorsport show (not a podcast) with Parker Kligerman and Landon Cassill professional racecar drivers and hilarious hosts taking you through the world of motorsports. Covering NASCAR, F1, Indycar, and more, they'll provide the scoop, gossip, laughs, and stories from the racing biz. With over 2400 unique products currently in stock, Spoiler Diecast boasts one of the largest inventories in the industry. We are NASCAR focused, offering a wide range of diecast and apparel options. But that's not all. We've expanded our catalog to include diecast for dirt/sprint cars, Indycar, and F1. As passionate racing fans ourselves, we're constantly growing our offerings to cater to different forms of racing. Use promo code "moneylap" for free shipping for orders over $20. https://www.spoilerdiecast.com/ Copyright 2026, Pixel Racing, LLC. All Rights Reserved.

Kyle Robert and Brian Twining are in to preview Watkins Glen as NASCAR gets ready to Go Bowling at the Glen They look at the outright betting board discuss their favorite strategies for a race that has SVG priced so short.But first they recap another Chase Elliott win, the Wurth 400 and more including DraftKings lineups and the betting cards.Subscribe to the Green White Checkered our FREE newsletter on Substack for more picks, DraftKings picks and bets every race day. Plus race recaps and early line shopping every Tuesday https://aoppodcast.substack.com/Follow Win the Race on YouTube - https://www.youtube.com/@UChJp58R4PTvPmzYcjXlVNPQ X - https://x.com/WINTHERACEP1Subscribe to Win the Race www.wintherace.com00:00 Intro01:50 Wurth 400 Betting and DFS Recap22:52 Watkins Glen Outright Odds56:02 Watkins Glen Betting Card Recap

Chase Elliott gets the win, but Denny Hamlin was right there with him. What looked like a simple P2 on paper was anything but, as Texas turned into a full-on track position battle where one restart could make or break your day. Denny breaks down how it slipped away. From getting buried in traffic to timing that final restart just about as perfectly as possible… and still coming up short. Was staying out the right call? Why did passing become nearly impossible late? And how close he actually was to clearing the 9 for the lead. Then it's everything else from a chaotic Texas weekend. Strategy gambles, pit road madness, and plenty for Actions Detrimental to sort through. Denny weighs in on the Kyle Busch situation, Preece vs. Gibbs, and the restarts that had everyone on edge. Plus, strong runs from Bowman, Bubba charging back through the field, and Spire showing real speed. We also dive into the points picture, where Tyler Reddick is in a league of his own, and what it'll take for SVG to make a push. A runner-up finish, a lot of what-ifs, and a race that was one move away from a very different ending. Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

Guest: Raymond Little — Founder, SVG Roofing Coaching | Contra ShoesGuest Links: Facebook: Raymond Wendell Little | Instagram: https://www.instagram.com/rwl612/Raymond Little built a roofing company from zero to nearly $100 million, exited to private equity for $40 million, and now runs SVG helping owner-operators between $1M and $10M break through their plateaus. In this episode, Raymond gets raw about what actually works in roofing sales in 2026, starting with storm vs retail in today's market, why wind claims are getting harder everywhere, and why the four-to-eight knocking window beats the nine-to-five mindset most new companies are still stuck in. He breaks down why you should never poach million-dollar producers from other companies but instead build them yourself, why a hefty override or ownership needs to be in the field driving the team daily, and his rule that you can't develop anyone greater than yourself. The conversation digs into Raymond's hiring philosophy built around second-chance people, team players, and good energy over credentials or personality tests, his 90-day ride-along system where new reps work the first 4-5 deals in the truck with him from knock to build, and the sales tactic of using the adjuster and homeowner as "teachers" to elevate new reps while making the process fully transparent. Raymond also shares why personal development around physical health, clean living, and healthy relationships is the foundation his entire company was built on, the real numbers on what 1099 reps should earn per lead, why one roof a week pays the bills and three a week means you stop checking price tags, and his mentor story of following Kurt the Nintendo and hitting half of what that man accomplished as his own definition of success. He also gets into Contra Shoes, the lightweight flexible roofing shoe a quarter the weight of Cougar Paws, designed for reps who knock and climb all day.

Send us Fan MailWhat happens when the business you love physically can't come with you? In this episode, Andi sits down with Cindy Bader of Patterns on the Prairie to talk about building - and rebuilding - a quilting business around the realities of your life.Cindy started quilting as a first-generation quilter on a $60 Walmart Singer that she had to spin the flywheel to start. Nearly two decades ago, worsening carpal tunnel pushed her out of a desk job and into a computerized longarm business she ran from home while raising three kids. Then COVID opened the door to snowbirding - and she hit a new wall: you can't exactly pack up a twelve-foot longarm frame and take it to Texas.So she pivoted again. Inspired by a 2:00 a.m. idea, Cindy started designing what she calls mosaic applique - fusible applique patterns with small gaps between the pieces, pre-reversed templates, color-sorted layouts, and a numbered reference page so customers can build each design from the center out like a puzzle. She recently added SVG files for cutting machines and uses a hotfix adhesive that stays permanent through washing, so there's no stitching around every little piece.If you've ever felt boxed in by the physical or seasonal limits of your current quilting business, this conversation is a reminder that the constraint often points directly at your next move.Don't miss an episode! Like, comment, and subscribe for more quilting stories, tips, and industry insights.Chapters00:00 Introduction and Cindy's Background02:20 Cindy's First Quilt and Early Sewing Memories03:17 Transition from Hobbyist to Business Owner05:47 Starting a Business During Carpal Tunnel Challenges08:35 Discovering Quilt Pattern Design and Expanding Horizons10:32 Introduction to Mosaic Applique Patterns12:54 Design Process and Customer Pain Points14:31 Innovative Application Techniques and Tools15:30 Teaching and Sharing Patterns in Person and Online16:42 Marketing Strategies and Word of Mouth17:35 Family Support and Tech Skills in Business21:41 Upcoming Events and New Pattern Releases22:16 Where to Find Cindy and Her Patterns23:03 Rapid Fire: Favorite Quilt Colors and Pattern Ideas33:01 Closing Remarks and ThanksConnect with Cindy:Website: https://patternsontheprairie.comInstagram: @patternsontheprairieFacebook: @patternsontheprairieYouTube: @patternsontheprairieWant More Quilting Business Content?

What if you could scan a property in 5 minutes with your iPhone and have a professional floor plan delivered within 24 hours, starting at $11? That's exactly what Roomio does.  Tom Sparks sits down with Steven, co-founder of Phoria, the team behind Captur3d.  For the first look at Roomio, their new smartphone floor plan tool built for real estate photographers, agents, and anyone who needs a professional floor plan fast. Steven walks through everything: how the LiDAR-based capture works, the step-by-step scanning process, accuracy benchmarks, pricing, delivery pipeline, ANSI compliance progress, and what's coming next including non-LiDAR and Android support.  Tom puts it through its paces with real questions from a working photographer's perspective, branded templates, multi-user accounts, scan pausing, SVG delivery, commercial property support, and a feature request for a fake camera rig to fool skeptical agents. Steven also reveals that WGAN members get two free floor plans to test drive the platform via wgan.info/Roomio.  For real estate photographers looking to add floor plans as a high-margin add-on service without expensive hardware, this conversation covers everything you need to know.

The Door Bumper Clear crew returns from Martinsville after a weekend that seems like it couldn't have gone worse, but things brighten up because we have Todd Gilliland joining us, who is all smiles. In the opening segment, or B.S. as we like to call it, we cover tons of ground, including the cause for Luke Baldwin's unfortunate wreck, Bubba Wallace's detrimental crash, and why the world of ARCA was buzzing this week. In Spot On, Spot Off, the topics we brought to the table were: - Was Alan Gustafson's call luck or strategy (or maybe even a little of both) - The package at Martinsville and the racing product - Jesse Love & Rajah Caruth's well-handled post-race conversation - The NASCAR Hall Of Fame Nominees List In Reaction Theatre, we hear from the Chasesexuals, try to pronounce SVG's full name, and get a not-so-nice Easter message for Denny Hamlin. Following that up is S*** Show Hall of Fame, and it felt like our nominees were being served up on a silver platter — with everything from Nashville Fairgrounds' short tracks faux pas to Porsches flying over catch fences. For Ask DBC, we ask Todd Gilliland if he really looks at the flag man, what he's doing with his week off, and what his go-to road trip snacks are. The gang wraps up with DBC picks, Weekend Winners, and their closing thoughts before teasing who we have coming on next week — hint: an undeniable Hall of Famer is making his return! Head to shop.dirtymomedia.com to get your DBC merch! Want more DBC? Check out and subscribe to the new DBC YouTube channel! Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

Kenny caught up with INDYCAR pilot Scott McLaughlin from the Team Penske 60th Anniversary luncheon at Phoenix Raceway to shoot the breeze about a wide range of things. Learn the difference between a NASCAR Cup Series stock car and the last two generations of Australia's Supercars, as well as how he was able to best SVG. The driver of the “Thirsty Three” talks moving on from his disastrous attempt in the 2025 Indianapolis 500 and his punchy friendship with Bubba Wallace that keeps him grounded.

Making his triumphant return to the guest seat on Door Bumper Clear, Jon Wood, President of Wood Brothers Racing, joins the crew to discuss the race in Las Vegas, speeding tickets & the end of throwback weekend. After catching up with what Jon's been up to, the usual suspects, Freddie Kraft, Tommy Baldwin & Karsyn Elledge, kick us off with what happened in Las Vegas: speeding penalties galore, Denny Hamlin's dominating performance, and some post-race beef between ex-teammates, Ross Chastain & Daniel Suarez. In Spot On, Spot Off, the crew discusses: - Denny Hamlin's chances of breaking 70 career wins - Throwback Weekend is coming to an end after 10 years - How soon will SVG win on an oval track? This week's calls in Reaction Theatre were something to behold, with fans crushing beers and commenting on Freddie's uncharacteristically wild hair, and he reveals the reason behind the long locks. There were so many nominees for S*** Show Hall of Fame this week that it was hard for the crew to remember them all. And in Ask DBC, even though we are only 5 races into the year, you guys asked about silly season, so Freddie talks about some rumors he's heard around the garage. We wrap up with DBC Picks, Weekend Winners, and what we're looking forward to heading into the race weekend at Darlington. We will see y'all next time! Don't forget to check out the merch at shop.dirtymomedia.com! Want more DBC? Check out and subscribe to the new DBC YouTube channel! Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

Claude Cowork came out of an accident.Felix and the Anthropic team noticed something interesting with Claude Code: many users were using it primarily for all kinds of messy knowledge work instead of coding. Even technical builders would use it for lots of non-technical work.Even more shocking, Claude cowork wrote itself. With a team of humans simply orchestrating multiple claude code instances, the tool was ready after a brief week and a half.This isn't Felix's first rodeo with impactful and playful desktop apps. He's helped ship the Slack desktop app and is a core maintainer of Electron the open-source software framework used for building cross-platform desktop applications, even putting Windows 95 into an Electron app that runs on macOS, Windows, and Linux.In this episode, Felix joins us to unpack why execution has suddenly become cheap enough that teams can “just build all the candidates” and why the real frontier in AI products is no longer better chat, but trusted task execution.He also shares why Anthropic is betting on local-first agent workflows, why skills may matter more than most people realize, and how the hardest questions ahead are about autonomy, safety, portability, and the changing shape of knowledge work itself.We discuss* Felix's path: Slack desktop app, Electron, Windows 95 in JavaScript, and now building Claude Cowork at Anthropic* What Claude Cowork actually is: a more user-friendly, VM-based version of Claude Code designed to bring agentic workflows to non-terminal-native users* Why “user-friendly” does not mean “less powerful”: Cowork as a superset product, much like how VS Code initially looked simpler than Visual Studio but became more hackable and extensible* Anthropic's prototype-first culture: why Cowork was built in 10 days using many pre-existing internal pieces, and how internal prototypes shaped the final product* Why execution is getting cheap: the shift from long memos, specs, and debate toward rapidly building multiple candidates and choosing based on reality instead of theory* The local debate: why Felix thinks Silicon Valley is undervaluing the local computer, and why putting Claude “where you work” is often more powerful* Why Claude gets its own computer: the VM as both a safety boundary and a capability unlock, letting Claude install tools, run scripts, and work more independently without constant approval* Safety through sandboxing: why “approve every command” is not a real long-term UX, and how virtual machines create a middle ground between uselessly safe and dangerously autonomous* How Cowork differs from Claude Code: coding evals vs. knowledge-work evals, different system-prompt tradeoffs, longer planning horizons, and heavier use of planning and clarification tools* Why skills matter: simple markdown-based instructions as a lightweight abstraction layer for reusable workflows, personalized automation, and portable agent behavior* Skills vs. MCPs: why Felix is increasingly interested in file-based, text-native interfaces that tell the model what to do, rather than forcing everything through rigid tool schemas* The portability problem: why personal skills should move across agent products, and the unresolved tension between public reusable workflows and private user-specific context* Real use cases already happening today: uploading videos, organizing files, handling taxes, managing calendars, debugging internal crashes, analyzing finances, and automating repetitive browser workflows* Why AI products should work with your existing stack: Anthropic's bias toward integrating with Chrome, Office, and existing workflows instead of rebuilding every app from scratch* Computer use one year later: how much better it has gotten, why vision plus browser context is such a superpower, and why letting Claude see the thing it is working on changes everything* Why many “AI verticals” may get compressed: specialized wrappers may matter in the short term, but better general models and stronger primitives could absorb a lot of narrow use cases* The future of junior work: Felix's concerns about entry-level roles, labor-market disruption, and whether AI can compress early-career learning into denser simulated experience* Why Waterloo grads stand out: internships, shipping experience, and learning how real teams build products versus purely theoretical academic preparation* The agentic future of the desktop: what it means for Claude to have its own computer, whether AI should act on your machine or a remote one, and how intimacy with personal data changes the product design space* Why Electron still mattered: shipping Chromium as a controlled rendering stack, the limits of OS-native webviews, and why browser engines remain one of the great software abstractions* Anthropic's Labs mentality: wild internal experiments, half-broken future-looking prototypes, and the broader effort to move users from asking questions to delegating increasingly long and valuable tasks* Why the endgame is not just more capability, but more independence: teaching users to trust AI with bigger scopes of work, for longer durations, with fewer interventionsFelix Rieseberg* X: https://x.com/felixrieseberg* LinkedIn: https://www.linkedin.com/in/felixrieseberg* Website: https://felixrieseberg.com/Anthropic* Website: http://anthropic.comFull Video PodTimestamps00:00 — Cheap execution and building all the candidates00:44 — Intro in the new Kernel studio02:47 — What Claude Cowork is04:18 — Why user-friendly can be more powerful05:33 — How Anthropic built Cowork07:09 — Prototype-first product development08:00 — Why local computers still matter09:20 — Skills, primitives, and platform leverage12:13 — Cowork's architecture: VM + Chrome + system prompt15:38 — Felix's own bug-fixing Cowork workflows17:38 — Local-first agents20:16 — Evals, planning, and knowledge-work optimization23:14 — What Anthropic means by evals24:21 — Scaffolding, tools, and why skills matter27:44 — Demo: YouTube uploads and self-generated skills31:03 — Calendar automation and cleaning your desktop34:47 — Browser context and why DOM access matters37:47 — Skills portability and plugins44:36 — Which AI categories survive?46:19 — Junior jobs, simulated work, and labor disruption52:00 — Gradual takeoff vs big-bang takeoff53:42 — Finance, taxes, and enterprise verticals56:24 — Vision and the improvement in computer use57:31 — Why Claude writes its own scripts58:06 — Should Claude have its own computer?1:01:26 — Windows 95 in JavaScript1:03:19 — VM tradeoffs and sandbox design1:07:23 — Approval fatigue and safe delegation1:11:18 — The future of Cowork1:12:27 — What comes next for agentic knowledge work1:15:13 — Electron, Chromium, and desktop software lessons1:22:16 — Multiplayer agents and coworker-to-coworker workflows1:26:05 — Anthropic Labs and closing thoughtsTranscriptAlessio: Hey everyone. Welcome to the Latent Space Podcast, our first one in the new studio. This is Alessio, founder of Kernel Labs, and I'm joined by swyx, editor of Latent Space.swyx: Yeah, so nice to be here. Thanks to, uh, TJ, Alessio, Allen helping to set everything up. It looks beautiful. We even have the logo outside.Yeah, kind.Felix: It's like really nice, right? When you walk in here as a guest, you're like, ah, this is a serious production. You're like, feel it immediately.swyx: Yeah. Felix, you've been, you're, you're currently a product manager of Cowork or,Felix: uh, really Technicswyx: Eng. Yeah. The, the identities are kind of vague member technical staff.Felix: I know member staff is like, the official title will carry around forever.swyx: Yeah. I basically kind of wanted, like we've been. Kinda obsessed. I, I've been using it a lot, even for managing latent space. Like, uh, cowork helps me upload videos and like title things and like edit and everything. It's, it's like really amazing.Alessio: Cool. He said multiple times Cowork has said gi in the group track.swyx: Yeah, yeah, yeah. So, so we have a second, uh, we have a second channel, uh, for latent space tv. Uh, and I, uh, and uh, we basically, this is our Discord meetup. Um, and I I, we have like Claude Coworks, it might be a GI, I don't know if we, we have, uh, uploaded it yet, but one of the sessions was like a, like a Claude cowork thing.Felix: I, you have to see, I would love to see it. Like, I'm so curious, like one of the most fun parts of my job is like constantly see the weird things people use Cowork for because it's obviously like very hard for us to actually design for specific use cases we do. But like every single person who's like most amazed is usually amazed about a thing that I didn't even expect cowork would be good at.Um, we have a new designer and it's one of the first small tasks. I was like, Hey, we need like a new emoji for cowork for our internal stock. It's like a pretty small thing. I like, can you please do it? And he drew an SVG and just gave it to coworker was like, can you animate this emoji? And now it has like this beautiful loopy animation.Um, and I mean, I think obviously this goes down to like, it turns out you can do more things with code than you expected, but it, it's like that kind of stuff that is really fun to me. So, long story short, I would love to see like, the kind of things you're doing.swyx: I'll pull it up. I'll pull it up.Felix: Yeah. Yeah.swyx: Uh, but before we get into it, I, I think always wanna start with like a top level. What is Claude Cowork for people who haven't heard of it? Haven't tried it out.Felix: Okay. Uh, real quick, Claude Cowork is a user friendly version of Claude Code. So the way it basically works is we have Claude Code and for us, fairly impressive agent harness that over December we noticed more and more people are using either, even though they're not technical, they, they're not at home in the terminal or they are at home in the terminal, but they started using Claude Code for non-coding workloads, right?Like managing expenses or like filling out receipts or organizing a knowledge base. Like there was a big obsidian moment that a lot of people liked and we wanted to capitalize on that, but also bring, bring this capability to people who are not terminal native and who might not know how to like brew and store something.So cowork is Claude Code running in original machine with a little bit of padding, a little bit more guardrails, making it a little safer and a little bit more convenient for people who don't wanna first open up the terminal when they go to work.swyx: It's interesting, uh, that is kind of. Pitch that way as a more user friendly thing because I always feel like it, it, to me, I I treat it as like why I'm familiar with Claude Code.Like we, we did a Claude Code episode Yeah. A year ago. But this one is like even more power user tools ‘cause it, uh, it kind of integrates much better with like clotting Chrome and, uh, in all the, all the other tooling. But like, maybe, maybe that's like a perception thing, right? LikeFelix: No, honestly, I don't think you're wrong.This is like a, a thing I've been thinking a lot about for like the last two weeks. So,swyx: but when they say user friendly, it's like, oh, it's the dumb down version. But no, actually this is the superset.Felix: Yeah. Like, I think a similar thing happened, A similar thing happened to me about 10 years ago, like maybe 12 years ago when I was at Microsoft and we started working on, on Electron and like browser-based technologies and cross-platform stuff.And one of the first use cases was Visual Studio Code, which used to be a website. And the initial narrative was, or Visual Studio Code is, is like a more user-friendly version of Visual Studio. But in a similar vein, I think there was some voices saying, oh, this is. For serious developers, like, we're not gonna use this.Right? For like anything. And I think in the end what happened is people have different stories about why Visual Studio Code became such a big thing. But my personal, my personal belief is that the Hackability and the extendability has like played a pretty big role, right? You can hook in Visual Studio Code that like almost any workload, it's so easy to hack on, so easy to put extensions for it.And I think cowork might be hitting a similar thing where it's very easy to extend and it's very easy to bring into your workflows. Uh, so the convenience I think is a bit of a, it's obviously the thing we strive for as developers, but I think the way people find value in it then is by probably mapping it onto whatever they actually have to do in their job.Alessio: So end of last year, you see the spike of like non-technical usage and clock code. What's the design process to say we should make clock code work? Because I mean, you built it in only 10 days. Um, I'm sure there was some discussion before on whether it's easier to use mean. You know, like making, making like a desktop GUI is obviously one way to do it, but like there's a lot of nuance in the product.Like maybe talk people through what was like the trigger of like, we should build a separate thing. We should not build like a different plot code thing. And then maybe some of the more interesting design decisions that maybe you didn't take.Felix: Yeah, I think philanthropic, we've been thinking about ways to move people who are comfortable with using Claude to answer questions and bring more of the power of like this thing to now like, execute tasks for you.I can like solve problems for you can like build things for you. How do we bring that capability to people who are currently mostly comfortable with like a like question answer paradigm within the chat. And we've had a lot of prototypes around that. Just going back as far as like easily a year and a half.Like we had a lot of people working on that. Um, and internally philanthropic is a very prototype demo, first culture. We have a lot of like internal prototypes that don't reach the public. What Cowork actually became is like we sort of picked the right pieces out of the many prototypes that we had.Right. And that's, that's maybe also like, I think an important qualifier whenever people mention this like 10 day number. I do think it's important to me to mention that within Double Scratch there was like a lot of stuff already happening, right? Like, and I think it's important for people to remember that when you build a website, you use React, you use like a bunch of other things.And this is like a similar scenario with like a lot of pieces we already had. Um, and in terms of decision path, I think we live in like an interesting new world where execution is actually quite cheap.swyx: Mm-hmm.Felix: So maybe, maybe what you would do That's so crazy. The year. I know it's wild.swyx: You should be, ideas are cheap.Execution is the hard part. IFelix: know. And like the, we, we used to live in this world maybe where you would take a product manager and the product manager would go to a number of potential customers and in this like very low bandwidth way, would try to. Try to like tease out what are the problems they're having, what are they willing to buy?Um, and then maybe what can you build to like drive out that need and then you go back and you like draft a spec and you think about it and then like you make a design and you execute it. We internally philanthropic app, not pretty much closer to the point where we're like, don't even write a memo, just like build, like let's build all the candidates very quickly.Let's just build all of them and then pick the best ones. I think the, the decision that is most impactful both for the product as well for the users right now is like the way we put value on your local computer. I think that's a big decision point a lot of people have thought about. Should this thing, whatever it is, should it ultimately run into computer or should it run in the cloud?‘cause they're big trade offs, right?Alessio: I guess like if we solve auth, it would be easy to do in the cloud. But I think like the fact that I can just download any file from anywhere and then put it and cowork there, it's like a big unlock. Um, I mean it's interesting you mentioned reusing certain pieces. I think this is something I've been thinking about even with Claude Code, right?The price of like writing code is going to zero, blah, blah, blah. But it actually seems like the value of having some sort of platform substrate is like increasing because as you build these new things, you can kind of plug them together.Felix: Yeah.Alessio: So I almost feel like when people are saying, oh, the value of a lot of software is gonna zero because you can recreate it, to me it's almost like the opposite.It's like having an existing platform to build on top of. It's like even more valuable because you can kind of bolt things on.Felix: Yeah.Alessio: You have obviously mcps, you have skills, you have like obviously the models, which is a big part. All these things kind of come together. Do you feel like that's a valid way to think about it, where people should invest even more in kind of like primitives.To rebuild on or are you like recreating a lot of it each time because like things change and it's easier to rewrite than reuse?Felix: You know, I think, I think you're right. I think you're right that the holistic platform is really useful. And this is maybe a whole like a somewhat contrarian view to a lot of people in ai.I actually don't think that the future is going to be hyper personalized software down to the point where everyone is running their own version. Like, I actually think it's going to be quite hard for all of us to have our own internal chat tool and like, if I wanna talk to you, likeswyx: howFelix: is that gonna work, right?In the, in the context of cowork and how we build it, I think it's a bit of a combination. Like what the, the execution that gets cheap is not necessarily rebuilding all the primitives. I think our priori, there's also not a lot of value in it. So for instance, my team did not think about rebuilding clock code.We're like very much started with the. The core thesis of this should be Claude Code.Mm-hmm.Felix: And then we'll like build things on top of it. The part of the execution that gets a little cheaper is like, how do you take all of these Lego pieces and put them together in a way that makes sense for users?It's like actually valuable. You have so many different approaches now in terms of what kind of, what kind of things do you actually elevate to a primitive, do you strongly believe that all your products should be built by just combining primitive that the public also has available? Do you keep some things internal?Um, and I think that's still evolving, but I think what's probably gonna go away is like, I'm not sure if it's gonna fully go away, but I'm gonna say, I think for me personally, I will probably no longer try to come up with a really good product without testing up with people. This is not a new concept, but wherever you used to have to make costly decisions around, do we pick technology A or technology B, or do we like, um, build it this way, build it the other way.I really strongly believe now you just build all of them and try them out with a small focus group and then whatever, whatever is better is what you go with. Right. And that, that is probably quite different even from how we maybe worked a year ago. Right. Like, I think, I think this happened very recently.Alessio: Yeah. I started building something in on Electron since you're here. Coincidence. Uh, but then Electron and like SQL Light are like, there's like some issues that like between development and like, uh, building anyway. And I was like, let's just rebuild the whole thing in Swift and just recreated the whole thing in Swift.And it's like, I. It's done.swyx: You know, I didn't take any effort. I, I, I don't even know Swift.Alessio: Yeah, exactly. I was like, I'm the, I'm not reviewing it anyway, whatever. You can write in whatever language you pick, but the important stuff that I did was not write the electron bindings. Yeah. It was like the logic of what happens in the app, you know, and then the model is like, yeah, I can just recreate the same thing as withswyx: Yeah.I, I think you still want, especially for people who are doing like high performance software or like very complex software, uh, you still want like, some view of the architecture. Uh, but you can use markdown for that,Felix: right? Yeah.swyx: Uh, you don't actually have to read the code again. I, I'm still like on a sort of like a definitional thing.Um, can we build a good mental model of Claude Cowork? Um, this is what I have, right? Like you you said it's like fundamentally cloud co. We don't wanna touch it. There's the cloud app, there's clouding Chrome. I think you guys do something different in planning, but, uh, I've been talking with Tariq who is on the cloud co team, and you guys are, he's like, no, we just exposed planning.Maybe we can clarify like, what are the major pieces. That people should be aware. It goes into cowork, like,Felix: okay, I think you basically have them. So really, um, you can, you can take planning more or less out. I think there's a few things that are really valuable in cowork. Um, the virtual machine is probably the most powerful thing.So we currently run like a, we currently run like a lightweight VM and we put clocked out into the vm and we do that for, for, um, a number of reasons. Safety and security is a big one, but even if you, even if you ignore for a second safety and security and you're just like, okay, Yolo, I want this thing to do whatever.It is quite powerful to give Claus on computer that is like generally a good idea. And in terms of architecture and UX and everything else that we've been working on, philanthropic, it often is quite useful for you to like anthropomorphize, um, clot aggressively and just be like, this is a person. What will you do if you give a, if you had a person, right?Yeah. And the analogy I've given my dad this morning who is still like quite insistent on using chat even for like coding things, is if you were a developer and your employer told you that you don't need a computer, they're just gonna like, send you emails with a code and you send emails with code back like that, maybe work for Patrick Miles in the back, but that it's not very effective.Um, so what we can do with the VM is because it's a, it's a Linux system, Claude Code has more or less free reign to install whatever needs to install. It can install Python, it can install no js. We do have strict network ingress and egress controls. So you can still, as, as a user in like plain human language, make it clear to, to the entire system what you're okay with and what you're not okay with.But at no point do we have to ask a real person, like a, like a person who might be in marketing or a lawyer. I'd have to go to a lawyer and be like, are you okay with me installing Homebrew?Alessio: Yeah, yeah.Felix: Right. Because the implications of the question and the answer are complex and nuanced and like, not, not easy to reason about.This gives us a lot of distraction that makes Cloud very powerful. Now then around it, we, we do probably have a number of things that also keeps growing almost every single week that you're probably noticing that make cowork maybe better for certain tasks than just cloud. Cloud on its own. Yeah. But most of those actually live in the system prompt.They're about like, what can we infer about the work that you do? What can we, what can we intru in the system prompt to make that more effective? It's of course the like very tight integration with Cloud and Chrome. You're noticing that a lot of people, especially as the models get better, a lot of people throw up their hands when it comes to MCP connectors in this area.I'm not gonna, I'm not gonna go through like 25 M CCP connectors, click off everywhere and then like half of them don't let me do the things anyway. So Cloud and Chrome is quite powerful because we can just talk to the cloud and Chrome sub agent and that will just do things for you.swyx: Yeah, so, so one example right in MCPI, honestly, I think that the state of MCP is kind of, kind of.Really hard to integrate. Um, I need to, I needed to add, uh, Figma MCP to the coding agent that I use.Felix: Yeah.swyx: Uh, and, but I didn't wanna read the docs, so I just had caught to it. And it's, it's great at reading docs and the same, same way I had to set up like a Google Cloud, um, account for some project I was working on and get some API keys somewhere.And Google Cloud is famously super hard to navigate, so I just didn't wanna deal with any of it. I just used Claude CoworkFelix: within the first week of developing on Core. This happened very, very quickly. Um, I caught myself by starting to use cowork for coding tasks, which is not ostensibly what we built it for, right?We don't need to. But I found myself, um, I found myself like on our internal, internal tool that we have for, to collect crashes and just like debugging information and I found myself sort like picking out the ones that I think we can easily fix versus the ones that might be like kernel corruption or something else on the operating system.And I found myself sort of picking these out and then just telling Clark, go fix this bug. I was like, what am I doing here? Go one level up, tell a cowork, I want you to go to all these crash tools. I want you to find all the bugs that you think are fixable and not like an operating system crash. And then I want you to tell another cloud to like fix all of that.Um, and that's, that's, that's sort of another cloud,swyx: just so it can spin up another instance or,Felix: uh, it, currently what I do is, um, and this is a bit of a hack, but I tell it to use clockwork remote to which website itself? Yeah, that's interesting. So you basically take, if you, if you imagine like a dashboard with like 20 bucks, you, this is remote control or clock or remote, or, sorry, I just wanted to confirm what, the way I'm using it is.I have cowork running and I'm telling cowork, here's where I normally go every morning to find the latest bugs. Go read the entire bug list, separate out which ones are fixable, which ones are, are fixable, and then for the fixable ones, four is this almost loop. For each bug, write a markdown file with a prompt.And then for each markdown v, that is a prompt. Start of a cloud set. So natively Claude Code hasswyx: this concept of subagents. Mm-hmm. And this is basically a subagent, but you're not using the subagent functionality.Felix: I'm not using the subagent functionality. And the reason I'm not is because I'm firing that off as a Claude Code remoteswyx: task.Felix: Yes. That's kind of nice. ‘cause then I can just fire it off. I can go to my next meeting and in Claude Code remote. Now the work is happening.swyx: Mm-hmm. Yeah. You, you see like you're already starting to use the cloud over your local machine. And I think this is one of those things where like. Shouldn't just everything just be cloud first, right?Felix: Ah, this is such a good group. I'm like solely bad about this. I have so many thoughts about that. Okay. So I generally believe that Silicon Valley overall is undervaluing the local computer. And my default argument for that is always how come we're all using MacBooks and not like an iPad or a Chromebook?Um, that there is like still value in, in having a local machine. And now when I think about Clot, it's this entity that is supposed to be very useful to you, like it tremendously useful to you. I think that entity needs to have access to all the same tools you have access to. Otherwise it's gonna be hamstrung in like all these complex ways.And there's, there's sort of two approaches we could take. We could say, okay, we're gonna like one by one chip away at everything that is at your computer and move it into the cloud. That's, that's one way to do it. Um, and I think other products have taken that path. I personally, this is a very personal opinion, but I personally, for the amount of tools that I use.Just don't have the patience to give another tool like permissions to every single thing and keep those permissions up to date. The second thing that I'm still grappling with, and I don't have a good answer for anyone just yet, but the second thing I'm still grappling with is what does it look like for someone to slurp up your entire work and put that in the cloud?Like if I, just as an example, like if you could click a button and it just clone your entire computer into the cloud, is that something that you would want? I'm not totally convinced yet that all everyone will. Mm-hmm. And that is sort of like upstream of all the technical issues we're gonna have. ‘cause like in general, I think the world is not ready for this kind of stuff.Like, I'll give you one quick example that would probably be very easy for us. So as a desktop app, we in theory with your permission, can do a lot of things on your computer, including reading your Chrome cookies. If we really want to do right, we could take your Chrome cookies, you would have to decrypt them for us.We could put those on the cloud if we really felt like it. Pretty easy solution. That would be super cool. We could just be like, oh, we can do all your tasks in the cloud now. Um, a lot of websites, thanks, include it. If, if they see the same authentication from like two different locations, we'll just lock down your account and now you have to go to the branch and be like, okay, I, I'm here with my passport.You actually know that. Wow. Yeah. As tired as well are of the term agent for the age agent future, I think there's a lot of stuff that sort of slowly needs to catch up and until that's the case, the way I, as someone's working on clock and make Cloud most effective is to like put it where you are working.swyx: Anything else? I thought with our mental model, so like, basically like, uh, part of me also just want, like the more I understand how it works, the more I can use it to its full potential. Right?Felix: Yeah.swyx: And so what I'm get hearing from you is you told me to delete the planning thing. You're not doing anything special on, on the, that's only exclusive to Qua cowork.Felix: We have some tricks for this sort of like change week over week. We eval cowork maybe against different use cases than he would evil clock code, right? If you think about it this way. Okay, so like clock code is our eval clock cowork. Yeah. So clock code is like quite optimized for coding tasks and we mostly value it whether or not we're getting better or worse depending on how good it is at like a typical suite job.And Clark Cowork on the other hand, we evaluate more against typical knowledge work, the kind of stuff he would find in finance or in like maybe a, like in like a legal office. Um, my personal use case is always like managing my things, like managing my personal mortgage or something like that, right? Or like wealth planning for me and my family.Those are the kinds of use cases we eval, clock cowork on. And what you might be picking up on is like the subtle changes we make to the system. Prompt what we put in the system, prompt how we steer, clot with the tools we give it. Um, like either it'd be better in one or the other direction and whether there's a trade off, try us exist a lot.CLO code will be better of a code and Claude Cowork will be better. For non-coding tasks, will those gaps still exist in the next three generations of models? It's like a little unclear to me though.swyx: Yeah,Felix: because right now these like hyper optimizations we make, I'm not sure for how long they're still be relevant.swyx: I think what I was referring to was also, it, it just, uh, it qualitatively felt different when I probably, it's just all prompting and I'm reading too much into it, but like the, the fact that it comes out with like a nine step plan, I can edit the plan and give feedback and, and, and see it execute the plan.Yeah. It felt more long range than in Claude Code, but maybe that already existed in Claude Code and you just build a nicer UI for it.Felix: It's kind of both. Um, like if the Clark Code people who build the planning functionalities would city, they probably say yes, we have all of those things in Clark code and they do.Um, I think people tend to give cowork. Tasks that are maybe of longer time horizon, I thought isswyx: so long. Yeah.Felix: That's like one thing, right? It's just like that the, the chunk of work tends to be maybe a little bigger. And then the second thing is that because the work, when it gets longer, it gets a little bit more ambiguous.We do tell co-work to make heavy use of the planning tool or to make heavy use of the ask user question tool, right? We do want it to come up with like. Different scenarios of, okay, tease out what the user actually wants. Don't go off to work for like four hours and then come back with the wrong thing.And you're probably picking up on that.swyx: Yeah.Felix: Um, I wish I could tell you I like built this magical thing and it's like, there's some secret sauce,swyx: but No, no, no. I mean, it's, it's just clarity is good that, you know, engineers just want to know. Yeah. They can, they can plan around it. And then I think also for me, um, I am realizing I have to switch to my, my other machine because this is a new machine that doesn't have my session.But, uh, yeah, the, the, the planning is really important for, for me to like approve or like to see whether it's like, it's right. The ask is, the question is so beautifully presented. I mean, it also, it also available in like cursor and, and in Claude Code. But like, I, I think like it's so nice to see that it, like it's kind of for me like to understand that it gets me, it gets what I want to do.Felix: Yeah.swyx: Yeah.Felix: It probably very hardswyx: just on the topical evals. Mm-hmm. When you say eval, I think people are very vague about what it means. Is it just like vibe testing or do you have like automated programmatic evals of Claude Cowork?Felix: When we say eval, uh, what we really mean is that we essentially take the entire transcript, including all the tools that clot has available ultimately to it, and we then measure what are the outputs, depending on what we tweak, right?So we do run that a lot. We use that in training. Um, we use that in, in like, if you sort of separate out post training from like the scaffolding around it. Cowork sort of exists in the scaffolding space, but obviously we also train on it a little bit. Um, so when we say eval, we mean given the certain transcript, what do the outputs look like?Including the file outputs as well as like the actual token outputs, like the ones that you see in the chat window.Alessio: I'm curious, um, how much of the failure modes are the model intelligence versus like the usage of the end tool to put the intelligence in? Like the well planning is like a good example, right?It's like one thing is to come up with a plan. The other thing is like make a nice spreadsheet. Yeah. That kind of runs you through the plan. Like how have you seen that? Well,Felix: the thing that I grapple with a lot is that whatever scaffolding you come up with, I think we still have a bit of sort of like model overhang where the model is dramatically more capable than right.Users end up using it for. And I think part of that is that we're just not getting the model all the tools to do all the things that's theory capable of, right? There's like one thing, um, however, whenever you do build the scaffolding, I'm sort of wondering at what point, at what point will that scaffolding go away and like how much you invest in figuring out what the right scaffolding is.It's kind of up to, it's a little bit of a bet. And one thing that I as an NJ quite enjoy is that like working in philanthropic and working at a frontier lab, I maybe have a little bit more insight into what's coming, coming down the chute in terms of like, what's the next model, what is the model capable of?What is good at, what is it bad at? And I'm, I'm increasingly wondering, is the right thing for us to like really invest too much in sort of these like scaffolding corrections where the model might otherwise not misbehave, but just not do the thing that you want?Alessio: Yeah.Felix: Or is it to just like give it as many capabilities as possible, try to make those safe so there's the worst case scenarios, likeno status might be otherwise.And then just simply wait a second for the next model drop. I'm personally, currently more leaning into the ladder. I think we're gonna see a lot of like applications and companies that do very impressive things with ai that in the short term might seem very effective ‘cause they're very specialized to individual use cases.But I think once models get better generalization and get better at like those specific use cases without being super guided on those, I'm not sure how long that's gonna stick around. And you can kind of, kind of already see this in like skills and NCP servers, right? Mm-hmm. We've, we've already seen sort of this like slow shift from MCP service to skills.And like, maybe a good example is Barry who made skills. He was initially hacking on something that honestly looked a lot, looked, looked a lot like what Cowork does today. It was sort of thinking about what if cowork, but for like people who don't wanna build code. Mm-hmm. And, um, he too did that as a prototype inside the desktop app.One of the first use cases we thought of were, okay, what, what are like coding like use cases that could really benefit from graphical interfaces and like from being a little separated from the actual underlying code. And everyone comes with the same answers. Data analysis,Alessio: right?Felix: Yeah. Or saying how many users do we have today?How many, like, it's always data analysis. And I think the thing that ultimately led to skills is that we wanted to connect this little prototype to our data warehouse and. The team very quickly discovered that like instead of building a custom tool for the thing to talk our data warehouse, they just like meet and embarked on follow like mm-hmm.Dear Claude, if you want to get data, here's the end point. Here's what the API looks like. You'll figure it out.swyx: Ah.Felix: And then it be hand over control. Yeah, yeah. Also just like maybe go one step up in the layer of abstractions, right. Just, yeah. Instead of, instead of telling the thing, here's ACL I, please call the CLI, or here's an MCP.Please call this ECT shape. Just like this is the end point. If you wanna know something, if you post here, maybe you can do post sql. It's gonna be okay. And that ended up being so effective that they started trying the same pattern of like just giving the model a markdown file that describes whatever it needs to do.That the whole thing eventually became skills and we're like. We should package this up. This is a good idea.swyx: Yeah. Um, we've had Barry Mahesh, uh, on, on our conference and uh, he's uh, definitely got a good idea there.Felix: Yeah.swyx: I wanted to show you the, how I've been using Claude Cowork.Felix: Uh, this is was my favorite part.swyx: This is this. So this is like me, uh, this is how we run the Discord. Uh, we literally, uh, at first I didn't trust Cloud Core. This was my very first usage.Felix: Okay.swyx: Right. So then I was like, okay, I will just try to manually download from Zoom all my recordings and upload it to YouTube. Yeah. Because this is a very laborious process.I got a click, click, click YouTube, um, isn't super user friendly. Uh, and it just did it. And then I was like, actually, you know, even the download from Zoom part, I should also. Put into Claude Cowork, and then I did it right. Here's a bunch of, and it starts compacting here, and it, and it, it starts to even be able to do things like look through the individual frames of the video to name the video so I can upload it auto automatically.Oh, that is, and this replaces my job as a YouTuber. We will forever appreciate your creative Yes. You know, and so that's great. Uh, but then by the way, it compacts and makes, makes like a new thing, right? So I, I don't, I don't have the initial, initial thing, but then I asked it to make its own skills so that it, so that something that's repetitive and one-off and human guided becomes more automated and I can use the skills independently and reuse them.Uh, and it obviously you can write skills and that goes into context and skills at the bottom here, which is, which is so nice. Um, so I have all these skills that, that I now sort of do on a weekly basis. Uh, I know you've released scheduled Coworks, which I haven't done yet, butFelix: course I should try them. I, I think this is like so wonderful and fun for me to see because.One thing that is very fun for me about skills in particular is that they're so easy to make. Like anyone can make a skill, like a text message, could be a skill, and they can be so hyper personalized to you. And this is like sort of the subtraction layer, right? Like, um, I, I'm just guessing, but I assume, heck, you are very good at your job.You're probably given this thing some guidance about how to do it, right? I,swyx: I just said, wrap everything up into, into a skill, right?Felix: Yeah.swyx: And then, uh, and then I was like, actually, sometimes I might need to break, uh, things apart because some parts fail or some parts might be needed in individually. So I told it to split one skill into three skills.So it's like a skill splitting thing, and then there's like a parent skill that just orchestrates all of them if I want to use that. You know, like, um, I think that's, that's like really good. Uh, and, and, uh, there's, there's one more part, which is the, uh, Google Chrome thing that I told you about.Felix: Yeah.swyx: Where I'm like, okay, you know, what's better than uploading, using Claude Coworks to YouTube?Like actually. Looking at the docs to like programmatically upload to YouTube and then putting that in a skill. And I've never done that before. I don't want to deal with Google Cloud. Yeah. So Claude Cowork does it for me.Felix: That is really cool.swyx: So, so I, I just, I don't care. I just, like, I do a thing. I don't, it doesn't really matter.Felix: That is really cool. And then you've, I assume paired the skill just with the script that it's built.swyx: Yeah, no, I just update, update the skills.Felix: Oh, that is beautiful. Yeah. That's wonderful.swyx: It's kind of like a skill, like, uh, uh, basically I think like the way that people ease into Claude Cowork is like take a knowledge work task that you would normally be clicking around for and then, uh, try to turn, turn that, and then you do the, okay, well what if you went further?Okay. And then when, if you went further, when, if you, and it sort of expand the scope of cowork as you gain trust with it and, and also teach it how to replace you.Felix: Yeah. It's like a little bit like playing factorial, but for your own life. Uh, like you say, you start really small.swyx: Yeah.Felix: You start automating something really tiny and like.Once it clicks, you keep adding onto this like automation empire. Just like make your life easier and easier. My favorite skill has been, um, every single morning Kohlberg starts looking at my calendar and make sure that there's conflicts because people tend to schedule a lot of meetings, sometimes last minute, sometimes miss it soft and painful.And a lot of products have existed like that A lot. I've written in the custom prompt there. I haven't made it a skill, um, honestly should.swyx: Yeah.Felix: But I've given it like pretty clear instructions about okay, here are some people, if they book over other meetings, I'm probably gonna go to their meeting. Like if Dario schedules a meeting.swyx: Right.Felix: Not try to reschedule down. Right. Um, and I think there's some other rules in there about like what kind of meetings I care more about what kind of meetings I care less about. What is okay to like, maybe pun like when I want to be, when I want to be working, when I don't want to be working. And it's those really small things that I can think kind of click with people.Right. When we launch co-work, I think one of the US races that went most viral on Twitter. X was clean up your desktop, which is stuff, because silly, that's such a smart thing, right? Like you don't need to model to clean up your desktop. Not really. Um,swyx: like this, like clean up my desktop.Felix: Yeah, exactly. Yeah.swyx: I need to, I need to choose my desktop, right? I guess give it access to my desktop.Felix: Yeah.swyx: Okay. Uh, okay. This is very scary. Oh, we'll do it.Alessio: I did, I did it with my downloads folder. It was like, you have so many term sheets and there's like eight copies of your rental lease for your office. I was like, all right.Like, don't yell at me.Felix: It's like, it's not such a small task. And then like, I, I would never go out there and normally otherwise and tell people I've pulled a product. It can organize your folder. Right. Um, because it feels small. But I think to your point like,swyx: oh, here's, here's the, here's the ask user questions.Felix: Yeah.swyx: Uh,Felix: beautiful. Right. Elite obvious junk. You probably shouldn't click that.Alessio: No.Felix: If he's not done right.swyx: As long as it's reversible, I don'tAlessio: make up blend to,swyx: yeah. Uh, yeah. No, I, I have a, I have a typical, everything is super messy folder. So, yes. I think this, this is super helpful. So this is a pretty simple task.Mm-hmm. But I've, okay, here it is. Right. Here's the progress. I don't see this in, that's why I'm like, this gotta be something different than, uh, than Claude Code, because I'm like, weFelix: do. Yeah. That's, we do system prompt that. We're like, all right. We want you to think about like, this task Yeah. Methodology.Yeah.swyx: And then I can, I can, I can do like little suggestions for, for, for these things. It's beautiful. Look at this. I, I can, I can like say like, oh, don't do that. Don't do this. It's amazing.Felix: I'm so happy. You like it. Um, I mean, the other way around, like we're part of the Clark core team, if you would like this in Clark COVID.swyx: Yeah. Yeah. Yeah. Uh, so, so yeah, I mean, uh, this is really good. Obviously I, I'm like kind of raving about it. Uh, you know, I have other things like sign up for pg e so if you can do phone calls for me, that'd be great. Um, I, I do, peopleFelix: have done that. Obviously you can't do that natively, but people have done that with like, various other providers.swyx: Yeah. Uh, and then this is like signing up for the Figma MCP. Um, I, I really am trying to do like everything, um, data analysis as well. I do think, um, oh, design to code, uh, very, very good. Right? So like, here's a Figma file, take it. And then this is where like a lot of other tasks is like knowledge work, like replace my manual clicking, but this is no, I would normally use Claude Code or uh, Claude Code for this, but because I perceive that you have better Chrome integrationFelix: mm-hmm.swyx: I, I think you can actually do a better job of this. And I, this, this is one shot at my, uh, conference website.Felix: That's pretty cool. Like at some point I would love to like, hear how you feel about code. In the desktop apps, which is like I never use, which is the, the same team. Same team.swyx: So I use the call code in terminal, which I, I perceive to be the default way of cloud coding.Felix: So one thing this has,swyx: sorry, I'm just like, I'm notFelix: here, I'm not here. All products. Can I talk about other stuff? Like I, I'm not sure if people out there wanna like hear me advertise my stuff for like an hour. Please do that. Um, this thing is like a builtin browser, which is a thing a lot of products have said.Yeah, it's a builtin browser. And I think giving cloud eyes into like what you're actually working on makes it so much more effective. And that's probably what you've seen in cohort because it can see Chrome, it can like debug the dom, it can like see things. Um, that does make it more powerful.swyx: Yeah. So, so I think, uh, my mental model was kind broken.‘cause I only use this cowork because I thought it had a, a browser thing in it. But I understand that the Claude Code app. The app version of Claude Code does have a built-in browser. I've seen, I've seen this preview thing.Felix: Yeah.swyx: I just, I've never used it.Felix: But in the end, in the end, you sort of have it by hard.Yeah. You basically get the same thing. Right? Like the, the, the additional skill that you're describing is chart is better if we can see what it's working on. Right. That's, that's sort of like the summary here and like whether it's using your Chromeswyx: Yeah.Felix: Or it's just like making up its own little like browser.It doesn't really make a big difference because either way it's gonna see what it's working on and that just makes it much better. And then you don't have to run QA for your cloud.swyx: Why doesn't it pick up my existing Claude Code sessions? ‘cause I, I mean, obviously I've used Claude Code, but Excellent question.Um, don't have a good answer other than like, we're honest. Just haven't Yeah. This is what the Open AI team does. Okay. Uh, cool. I I I don't have other, like, I, I just, I, I do wanna expand people's minds and also maybe show people if they haven't really done it, but like, I, I think it's very interesting how I sometimes use this more than I use, I mean, I use dia, right?Yeah. Um, I, and I use, uh, I've used like all the other agentic browsers and philanthropic didn't have to build an agentic browser because you just had Claude Cowork and that's enough.Felix: Yeah. I also think like maybe integrating with number of excellent browsers out there, it's like currently on my personal priority list, a little higher than like trying to rebuild a browser from scratch.Yeah. You know, never say never, but I think going back to this idea of like, we wanna plug this into an entire existing workflow, I think our goal is actually to not replace any of the applications we have in your computer. But instead of like, work really well within a new workflow,Alessio: make the new one. Yeah.Are, it seems that nowadays, especially on the browser, most of the innovation is like user ergonomics. It's not really like the underlying browser engine. So I feel like to call it, it doesn't really matter if it's like the, uh, or Chrome or Alice, whatever.Felix: Yeah. We wanna, we wanna meet you wherever you are.Which is like, like obviously I would say that, but it's also just generally true because I don't wanna shrink my potential user base artificially by saying, okay, like, I'm gonna start building for the people who are willing to switch browsers.Alessio: Right.Felix: That's such a, like, you know, like many lawsuits have been filed over who gets to review the browser and like a lot of money has switched hands over the question of like, which browser is default and which search engine is default within the browser.Um, I just wanna build for, yeah, I wanna build for swyx essentially. Like, I wanna, I wanna, I wanna build for people who have a number of annoying tasks that they feel like. Maybe clock could do it. Could do it for them.Alessio: Yeah. What do you think about skills portability? I think there's been one thing, I use another thing called zo, which is kinda like a cloud computer plus agent.And I have a skill to add visitors to the office. Yeah. So whenever somebody has to come in after hours, they need to check in downstairs. Um, but I wanna like text the thing, so it doesn't really work in, in cowork, but now that skill is in the zone harness and it's not in my cowork thing. And then if I make a change, it's gotta, I gotta sync them.How do you see that going? Like I see memory as like. Cloud personal, kinda like, I don't necessarily want my memories to be cross thing.Felix: Yeah.Alessio: But I do want my skills to be cross agent that I use. I think with MTPs, people do the same thing. It's like, oh, Mt. P Gateway. Mt P registry. I don't really know if that's like a business.So I'm curious like if you've had any thoughts in the area.Felix: I think for me, this is sort of where I go back to the really basic primitives for our skills are file-based instead of like this complicated thing that exists inside a place somewhere that is like super proprietary. I'm really leaning into the idea of like, it's all just files and vultures, and that makes it very portable on its own.Right. We do have skills as part of this container format, which was just called plugins.Alessio: Mm-hmm.Felix: And plugins are available both for Claude Code and Claude Code work the same format, and you can install plugins. This works in cowork today. You can basically say, I'm gonna add a whole, like just a GitHub repo as a.Skills marketplace or like a plugin marketplace. And that's how we're doing portability. I think we have a lot of room left to grow in. How do we make it easy for people to know that they can write skills? How do we make it easy for them to just like, share a skill with you? Because obviously all the words I just said, right?Like I'm losing most of the knowledge worker base out there, right. And start by saying, oh, you can connect to GitHub repo. It's not exactly how most people will end up working in like a general knowledge worker space. Um, but I think there's something there. And another thing that's there that I think has not really been properly explored is the, the, the combination of which part of the skill is very portable and then which part of the skill is like very personal to you.Right. And I think that's something we haven't really solved as an industry. Hmm.swyx: It's like, which, how you wanna introduce more structure to the skill or have always have like. Public skill, private skill, you know, pair. Yeah, yeah. Kind of. I think there'sFelix: like a, like the easiest way to do this, which is we do like use string interpolation or something.Right, right. Yeah, yeah. Insert username here, insert like phone number, insert, like known folder, locations, that kind of stuff. Um, that's probably clunky. That's why we haven't built it. Um, but I do think someone is going to come up with like an interesting way to keep everything we like about skills. The portability is just a file, it's just marked down.It's just text, honestly. Right. Like a text file words. The complete lack of structure, which means you don't need any kind of tutorial to write a skill. Just like explain it to Claude the way he would explain it to me and Claude will probably get it before I work. Mm-hmm. Right? You're just like, for booking a flight, tell Claude how to book a flight the same way we tell him somewhere.I just started working here today. But combine that with a very like, personal thing. Um, maybe we'll stick with a booking a flight example. I don't actually think. AI should be booking flights. I think the tools we have is yes.swyx: Yeah. Finally, somebody says it. It's the default demo that everyone's making.Felix: I'mswyx: like, I even against like booking demos, it is not a good showcase.Felix: Yeah. I'm like, I just wanna book my flight myself. But, um, I think there's a lot of things that have a personal and a non-personal component and that's maybe why people reach for flight booking because some things are very universal. Yeah. Super flight is usually better, right? Like few people try to book the most expensive flight.And then some things are quite personal about like what times you prefer, which seat you prefer, which airports you prefer. Combining that and like a skill format that is actually portable, compatible, easy to understand for people. I think that would be very exciting. We just haven't figured it out yet.Alessio: Yeah, I think the text part every, I think everybody by now has some sort of like cloud file thing. Either Dropbox, Google Drive, whatever. So it feels like in a way it should basically like sim link. My skills into all my agent harnesses. Yeah. Just keep those ing like we have internally this like valuable tokens repo, which is like all the commands sub agents.It's good. Uh, and then I build like a TUI where you can start it and be like, you know, install this command and this three sub agents into this agent in this folder and just copy paste this. It doesn't do anything. It literally cp the file into that. But I feel like there should be something similar where like whenever I go into a new thing, it's like, hey, here's like the link to exactly the cloud folder and just bring down these skills into this.Yeah. Like today it doesn't quite work like that. Like if I install a new agent, I cannot, I have to like copy paste all the skills and I don't even know where they are.Felix: Yeah.Alessio: That's like the big problem. It's like where do I find them?Felix: Yeah.Alessio: Um, so I'm curious like in the future like that, that almost feels like my personal productivity thing will be my skills.Felix: Yeah.Alessio: Is not really the product that I use. Everybody has access to the same product. But today there's, that just looks like copy pasting ME files, IFelix: think so many things I, I really like thinking about agents and LLMs just as like another coworker. So many attempts have made to build documentation companies that are like, oh, we're gonna solve oil documentation problems.Um, I myself, like spend a little bit of time working in notion, right? I'm like deeply familiar with the concept of let's get everyone on the same page. Mm-hmm. Right? And what you're basically saying here is you want all your agents to be on the same page about your preferences, about the skills, about the way they ought to work and like how they ought to execute.And I'm not sure what the right thing is going to be if it's going to be some, some company that can say, all right, we're as an independent body, we're not trying to like, push into any particular product. It's our job to be like the skill authority, and we provide, I don't know, we're gonna be the Dropbox of skills and we can just sim link us into all the products we want to use.I'm not sure that's gonna be viable business, but as, as an idea, it would be cool.Alessio: Yeah. Yeah. I think so many things are just going away as businesses. It's like, how am I supposed to do it? I'm not even asking somebody to make a product about it. Like yeah. I wanna personally know. And there's things like you said, it's like you almost wanna skill and then interpolate it between personal and work.So if I'm booking a fly for work, it's different than I'm booking a flight personally.Felix: Yeah.Alessio: In some ways, yeah. But like a lot of the scaffolding is the same, you know? Cool.Felix: I mean, as an engineer I will tell you like, you know, technic a person to technic a person. I will just be like siblings.Alessio: Well that's what, that's what I do.We call that MD and agents that MD's just the same how sim length. And so it is like, that works, but it feels like, yeah, I don't know. MaybeFelix: you can always go one, you can always tell cowork problem and then cowork will solve it for you. Just make the siblings. That's like one way to do it.Alessio: That's true.That's true. All right. Everything is called cowork.Felix: Uh, potentially spicy. Question for both of you.swyx: Uh, which of these industries will go away?Alessio: Okay, so what Felix was saying before is interesting. There's busy like. The short term pressure of like, we need to turn these tokens into valuable things, which is I should build the last mile product that harness the model.And then there's the question of like, long term, which ones are gonna still be valuable? And I think you're kind of seeing this today with like, uh, you know, the coding space in a way is kind of like everybody's moving up and up in stack because you need more than just turning tokens into code. I think search, like enterprise search is kind of saying the same thing.Like with G Clean and like all these different companies is like, at the end of the day, if Cowork is the one doing all the work, the search itself is like such a small part that like, I don't know if I'm really gonna pay that much money just to do search. It's almost like everything is like a cowork vertical.So like how much can cowork first party support?swyx: Mm-hmm.Alessio: And how much can it not? I think for a lot of these things, the planning thing that you were showing do Which one? The planning. The planning.swyx: Okay. Yeah. Yeah.Alessio: That's one thing where like most of the value that these agents provide is like they're better at planning for specific tasks.Yeah. And have better tools for it.swyx: Yeah.Alessio: But I think the models are now moving in that direction and they have the right harnesses and they're on your computer. So for me it's almost like if for the end customer trusts your startup to be the provider of that task result, then I think that works. This is, uh, something that, this is a shortswyx: spike that we're, we're working on.Uh, yeah.Felix: I think, look, I'll, I'll, I'll tell you this, like I don't think I'm the best person to like actually estimate which industry is going to be hit the hardest. But I do think that at philanthropic as a group of people, we're deeply worried about the impact. That the tools are going to have on the labor market, especially for like junior employees that, because I think, I think it's only honest to say that when we talk about automating a lot away, a lot of the work that we personally find annoying that we maybe think's not the best use of our time.In a lot of industries, that kind of work would've been given to a junior entry level employee. Yeah. Right. And I think it's, it's only, it's only right to be really worried about that and like worry what that's going to do in particular to people like enter the shop market.Alessio: Mm-hmm. I have a solution for that.Which you make them, you create simulative jobs for them.Felix: Okay.Alessio: So this is, this is like half joke, half true. So if you think about software engineering, when you're like a junior engineer, you work like 1, 2, 3 years. And in those three years there's like maybe like a handful of moments where like you really learn something.And then a bunch of other days where like you're not really progressing.Felix: Yeah.Alessio: I think now we can use AI and these models to actually like shortcut these careers and almost like simulate the early years of your work and like just make them like super dense and like these learnings, it's like, hey, we're working on this feature, which is like a distributed system and you need to learn this thing that might take three months at a company.And so you take three months here, it's like we're just simulating the whole thing. It's actually not a real thing. And in one week we kind of speed run through the whole thing and you kind of learn your lesson from there. And we kind of repeat that in like one year. You basically get like three years worth of like projects and experience.Yeah. I think it's harder for like things like sales or for things like, you know, marketing because you don't really have a way to get the feedback loop. But I think a lot of it, it sounds kind of silly, it's like you're making the new effect job, but it's almost like you go to college, right? People pay to learn how to do it, and this might feel similar where it's like, hey, we have the.Jane Street Simulator is like, you wanna come work at Jane Street? We'll just put you in the simulator for like three months.Felix: Wow.Alessio: And you'll come out of it. It's like, you know, I'm ready.Felix: So there, there is an aspect here. I'm not an expert enough to like actually know what, what is going to happen to marketing or legal or finance, right?Like, I don't work in those jobs and I, I don't think I should talk about them, but I am an engineer and I think I have a pretty good idea of what engineering is like. And I think one thing we're sort of seeing is that as a company and also as, as the public, we're like deeply worried about entry level, but we're also seeing more senior engineers accelerate it.If like they're more productive. They, they actually increase the value they provide. And the thing that I'm thinking about a lot is the fact that even before all of this happened, um, I've always had a lot of respect for the University of Waterloo and the, the new grads that have joined my teams as from coming from the University of Waterloo always felt like.More ready than new grads will like literally spend their entire time at the university regardless of how good, but never actually had to work inside an environment where you have to ship things that eventually will be used by users. And I'm, I'm, I'm German. I like initially went to German University and I think the, the, the like information systems programs, there tend to be very theoretical, right?Like I often give people the example of like trying

Parker Kligerman and Landon Cassill break down the latest in NASCAR and IndyCar, focusing on the impact of increased horsepower and tire wear in the Phoenix Cup race, Ryan Blaney's strategic win, and the evolving points system's pressure on teams. They debate the merits of a formal NASCAR licensing system, discuss the influence of manufacturers and hybrid tech in F1, and celebrate IndyCar's bold new DC street race. Leave us a voicemail! https://moneylap.com Or email us! friends@themoneylap.com Timestamps: 00:00 - Intro 02:02 - NASCAR Phoenix Recap & Horsepower Discussion 05:29 - Tire Wear, Race Dynamics, and Blaney's Win 11:12 - Corey Day, Young Driver Jealousy & Industry Dynamics 15:31 - SVG's Performance & Early Season Points Importance 16:20 - Points System Impact on Viewership Engagement 27:02 - Minor League Hockey Marketing Tangent 28:01 - O'Reilly Series Recap & Austin Hill Interview 30:55 - NASCAR Entry & Licensing Debate (Round 2) 35:57 - Proposed NASCAR Licensing System 44:14 - Challenges & Incentives for Implementing Licensing 49:38 - Legal & Antitrust Concerns with Licensing 51:23 - Where Should Licensing Start? 53:11 - Joe Gibbs Racing Private Investigator Story 54:47 - F1 2026 Rules & Qualifying Observations 56:19 - F1 Race Analysis & Manufacturer Influence 1:01:40 - OEMs' Power in Motorsports 1:06:28 - Should Racing Be About Speed or Technology? 1:07:48 - Fan Demand vs. Manufacturer Marketing 1:12:13 - Motorsports' Environmental Role & Entertainment Value 1:14:26 - F1 Car Performance & Cadillac's Struggles 1:17:32 - IndyCar Phoenix Recap & Freedom 250 Announcement 1:19:13 - Freedom 250 Track Layout & Free Admission 1:22:04 - Arlington GP & IndyCar Qualifying Format 1:23:30 - Weekend Picks: NASCAR, IndyCar, F1 1:27:25 - Listener Questions & Show Wrap-Up 1:29:01 - Outro (Timestamps are a rough timing and may require a little scrubbing to find the start of the topic) The Money Lap is the ultimate motorsport show (not a podcast) with Parker Kligerman and Landon Cassill professional racecar drivers and hilarious hosts taking you through the world of motorsports. Covering NASCAR, F1, Indycar, and more, they'll provide the scoop, gossip, laughs, and stories from the racing biz. With over 2400 unique products currently in stock, Spoiler Diecast boasts one of the largest inventories in the industry. We are NASCAR focused, offering a wide range of diecast and apparel options. But that's not all. We've expanded our catalog to include diecast for dirt/sprint cars, Indycar, and F1. As passionate racing fans ourselves, we're constantly growing our offerings to cater to different forms of racing. Use promo code "moneylap" for free shipping for orders over $20. https://www.spoilerdiecast.com/ Copyright 2026, Pixel Racing, LLC. All Rights Reserved.

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

Buckle up, it's time to go for a ride on the Dirty Thirty Express! In just 30 mins, you'll see, hear, and feel the very best Dirty Mo Media has to offer from this week. This one is locked, loaded, and ready to rip. Dale Jr. starts us off with a conversation around the NOAPS driver making a lot of waves recently: Corey Day. He describes the conversation he had with the young racer, how the team dynamics work between JRM and Hendrick Motorsports, and what he sees happening moving forward with Day. Next up, Denny Hamlin talks about the wreck he didn't realize he caused, which resulted in Connor Zilisch going for (another) spin in COTA's turn one. He goes on to praise the driver of the No. 88 and says SVG might not have it so easy on the road courses this year, thanks to his new teammate. In another supercharged segment, Karsyn Elledge describes her point of view from the volatile CARS Tour victory lane. The short track racing world took notice of the moment and learned a valuable lesson: you DON'T mess with the Elledge sisters. Over on Bless Your 'Hardt this week, Dale tells Amy the full story behind Isla saying her first cuss word — and how a small part of him felt so proud. This is a story you're going to want to catch. Lastly, the internet's favorite mullet-having, sleeveless shirt-wearing, helicopter-flying personality stopped by the Arby's studio to talk about his new RCR deal. In this segment, he discusses the noise from the haters, his fans, and what he hopes to accomplish racing in the O'Reilly Auto Parts series. Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

On this week's episode of Rubbin' is Racing, Spider and Large talk with SVG about his weekend on the podium at Circuit of the Americas in Texas, taking home the hardware in the O'Reilly Series Race and finishing P2 in the Cup Race on Sunday. Quigs also joins the show to break down the week's NASCAR headlines. Thanks for listening!

Tyler Reddick is officially on a HEATER.Three races. Three wins. The first 3-for-3 start in NASCAR history - and now the real question is… can he just win them all?In this episode of Stacking Pennies, Corey LaJoie and Ryan Flores break down Tyler Reddick's dominant performance at COTA (Circuit of The Americas), what makes road course racing different in NASCAR, and why right-foot braking might be the secret weapon separating the best from the rest.We dive deep into:Reddick's historic start to the NASCAR seasonCOTA race breakdown (Cup + O'Reilly's)The SVG vs Reddick horsepower debateWhy mechanical grip matters more than peak horsepowerDario Franchitti's return at 52 years oldFord's driver development concernsEli Tomac's 8th Daytona Supercross win — and the trophy that knocked his tooth outSnow racing in Big Sky, MontanaPhoenix Raceway preview (tire wear + strategy)F1 season kickoff and Cadillac's debutFrom NASCAR Cup Series strategy to Supercross chaos to Formula 1 storylines, this week had everything.Gasoline. Rubber. Victory. Let's stack ‘em.Follow: @coreylajoie @skipflores @_stackingpenniesSee Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

As NASCAR embarks on its 77th season of competition, one would think there are no records left within reach of breaking. Tyler Reddick denied that notion today, as he became the first driver in NASCAR history to win the first three races of a season. Our resident NASCAR reporters Jeff Gluck and Jordan Bianchi were on the case, and they reconvened for a new episode of the Teardown to unpack Tyler's historic feat and how he held off none other than SVG to capture the first road course race of the year. Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

Parker Kligerman and Landon Cassill dive into the latest in motorsports, discussing the revival of Speed Channel as a podcast, NASCAR's new All-Star race format at Dover, and the growing importance of data security after a high-profile legal dispute between Joe Gibbs Racing and Spire Motorsports. They highlight emerging young talent like Keelan Harvick, analyze Tyler Reddick's superspeedway wins, and celebrate the rise of authentic personalities such as Carson Hocevar. They also dive into the recent F1 test with Ferrari's unique approach to the post-DRS era. Super Formula Wreck: https://x.com/f1bigdata/status/2026582345164185708?s=46 Leave us a voicemail! https://moneylap.com Or email us! friends@themoneylap.com Timestamps: 00:00 - Intro 06:47 - New NASCAR All-Star Race Format at Dover 08:13 - All-Star Race Format Announced 12:42 - NASCAR Legal Drama: JGR vs. Chris Gabehart 20:18 - Keelan Harvick Signs with Toyota 22:05 - Tyler Reddick's Super Speedway Wins 23:00 - Atlanta's Rise as NASCAR's Best Track 25:02 - Carson Hocevar: NASCAR's New Disruptor 29:59 - The Value of Authenticity in NASCAR 37:33 - Carson Hocevar's Sim Racing & Social Media 39:33 - O'Reilly Series: Ross Chastain vs. Austin Hill 43:21 - Sheldon Creed's Breakthrough Win 44:17 - Truck Series Lacks a New Sponsor 45:07 - Atlanta TV Ratings & O'Reilly Series Growth 47:07 - SVG's Dominance at COTA & Road Course Odds 48:26 - Connor Zilisch's Cup Series Challenge 50:16 - Formula 1: Ferrari's Upside-Down Rear Wing 52:29 - Aston Martin's Struggles & Alonso's Bad Luck 54:08 - Open Wheel News & Race Picks 57:14 - Outro (Timestamps are a rough timing and may require a little scrubbing to find the start of the topic) The Money Lap is the ultimate motorsport show (not a podcast) with Parker Kligerman and Landon Cassill professional racecar drivers and hilarious hosts taking you through the world of motorsports. Covering NASCAR, F1, Indycar, and more, they'll provide the scoop, gossip, laughs, and stories from the racing biz. With over 2400 unique products currently in stock, Spoiler Diecast boasts one of the largest inventories in the industry. We are NASCAR focused, offering a wide range of diecast and apparel options. But that's not all. We've expanded our catalog to include diecast for dirt/sprint cars, Indycar, and F1. As passionate racing fans ourselves, we're constantly growing our offerings to cater to different forms of racing. Use promo code "moneylap" for free shipping for orders over $20. https://www.spoilerdiecast.com/ Copyright 2026, Pixel Racing, LLC. All Rights Reserved.

Dale Earnhardt Jr. is back in the studio after a thrilling weekend in Atlanta for a new edition of Dirty Air. He joins co-host TJ Majors to unpack the high-banks thrills and more: Atlanta continues to be the best ticket of the year Carson Hocevar continues to disrupt Sheldon Creed finally breaks through JR Motorsports day at Atlanta Lee Pulliam gets his shot in the O'Reilly Series NASCourt is back in session During the Ask Jr. portion of the episode, listeners sent in questions regarding: Dale's new 3D printer If you could shoot a liquid out of each fingertip, which five would you choose? Which former Cup driver would Dale like to see compete in a one-off? Which tracks would Dale like to see on iRacing? Keelan Harvick's new Toyota Development deal   Plus, in the Dirty Mo Dough segment, the guys discuss if it's worth betting on SVG this weekend and if the books have it wrong with Zilisch's odds. And, who are some possible top-10 bets? Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

Freddie Kraft, Tommy Baldwin, and Karsyn Elledge are back for another season of Door Bumper Clear, and they're kicking off 2026 with a bang. Veteran motorsports journalist Bob Pockrass joins the crew to break down everything happening in the NASCAR world right now.They dive into the return of the Chase format and debate whether NASCAR made the right call bringing it back. The RAM reality TV show is heating up, and Bob provides an update on Brad Keselowski after his offseason leg injury.In Spot On / Spot Off, we debate:Should the Clash return to Daytona?Is Hendrick Motorsports the title favorite?Which Open cars make the Daytona 500?Who will be the most improved driver in 2026?Plus, a hilarious Reaction Theatre, listener questions in #AskDBC, and Tommy pays his debt in DBC Picks—whether he realizes it or not.Buckle up. It's officially race season.Real fans wear Dirty Mo. Hit the link and join the crew.