Podcasts about Asics

This week on Fuel for the Sole, we're talking about fueling for slow, long runs and how that relationship with fueling shifts in the endurance space. We also answer a listener question on collagen — specifically, which types are actually worth taking as an athlete. And finally, we dig into that study making the rounds claiming daily artificial sweetener intake (about what you'd get from a can of diet soda) is linked to significantly faster cognitive decline compared to lower intake.Want to be featured on the show? Email us (written or an audio file!) at⁠ fuelforthesolepodcast@gmail.com⁠. This episode is fueled by ASICS and RNWY!Head over to⁠ ASICS.com⁠ and sign up for a OneASICS account. It's completely free and when you sign up you will receive 10% off your first purchase. You also gain access to exclusive colorways on ASICS.com, free standard shipping, special birthday month discounts and more. RNWY Complete Protein is a post-run recovery shake we genuinely stand behind. Here's why: built on YESTEIN®, a fermented yeast protein that scores a PDCAAS of 1.0, which is the highest possible protein quality rating. That puts it in the same category as whey but without anyof the dairy. Every serving gives you 25 grams of complete protein containing all nine essential amino acids plus 5 grams of creatine monohydrate and a five-enzyme digestive complex. Get yours at https://rnwy.life/ and use code FEATHERS15 for 15% off your purchase. Disclaimer: This content is not intended to be a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of your physician or other qualified health provider with any questions you may have regarding a medical condition.

Take a trip down memory lane to March 2019 (Ep 71) as Ellie Pashley and Julian Spence recap their marathon PBs from the Nagoya and Lake Biwa Marathons. Listen to the lessons learned in their in-depth recaps.  This Special Re-release Episode is proudly brought to you by Shokz. They have just released the Shokz OpenRun Pro 2 TCS Sydney Marathon presented by ASICS Co-Branded Edition. Only Available at shokz.com.au and Shokz booth at TCS Sydney Marathon Running Show presented by ASICS. Patreon Link: https://www.patreon.com/insiderunningpodcast Opening and Closing Music is Undercover of my Skin by Benny Walker. www.bennywalkermusic.com Join the conversation at: https://www.facebook.com/insiderunningpodcast/ or follow us on Instagram: @insiderunningpodcast

The Megs ran the Falmouth Road Race with Asics while Thomas tapped into his culinary side with some hot dog ramen (sounds delicious). We also dive into the Nike Pegasus Plus 2, which features an all new Air Zoom unit in the forefoot. SUPPORT OUR SPONSORS!LAGOON PILLOWSSleep is training. Lagoon Pillow is built around your sleep position and preferences — so you wake up recovered and ready to run. We use them every night and you should too. Find your perfect pillow at lagoonsleep.com/believe

As the 2026 Abbott World Marathon Majors season returns after its summer break, attention turns to the TCS Sydney Marathon. Joining us on this week's show, we welcome a legend of Australian marathon running. Lisa Weightman is an Olympian, representing Australia at the Beijing, London, Rio and Tokyo Games and has also competed at multiple World Championships and Commonwealth Games. We've also got news from the European Championships in Birmingham, and Martin & Deena share stories from their recent trip to Boulder, Colorado. All this, and more, on the latest episode of Marathon Talk. On this week's show: 00:00 - Intro 00:51 - Martin and Deena tell us about what they have been up to while we've been off 09:48 - European Championships 13:58 - A recap of the Abbott World Marathon Majors series so far 17:33 - TCS Sydney Marathon presented by ASICS race preview 23:00 - Marathon Talk meets Lisa Weightman 57:34 - Wrapping up Links & References: Abbott World Marathon Majors Website | Facebook | Instagram | TikTok Marathon Talk Facebook | Instagram | TikTok Martin Yelling | Instagram Deena Kastor | Instagram Lisa Weightman | Instagram

In today's episode, Karen, Megan, and Rachel cover running on vacation when you're the only one training, swimming as cross training, Strava etiquette, how to approach racing a half during marathon training, and lots more.Megan also opens up about her past struggles with nutrition and fueling, how her relationship with food changed after college, what helped her find a healthier approach, and the advice she has for listeners. The Chicks also share their thoughts on the new stroller mile world record, break down Molly the hamster's viral Strava mileage, and give a few shoe recs._________________Find this week's Zappos recs here:Karen: OOFOS OOmega OOahh SlideRachel: Birkenstock Arizona EVA EssentialsMegan: Saucony Endorphin Speed 5_________________SUPPORT OUR SPONSORZappos is an online retail destination for the best in footwear, offering the selection and expertise runners need to take on each day with confidence. Zappos carries an extensive assortment of performance running shoes, including leading brands like HOKA, Nike, Brooks, New Balance, ASICS, On, and more. ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Check out the latest selection on footwear on Zappos.com or in the Zappos app. ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠_________________CHICK CHAT– Send us your questions at ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠gettingchickedpodcast@gmail.com⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ or DM us on Instagram at ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@gettingchicked⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠YOUR HOSTS– Karen Lesiewicz | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@kare_les on Instagram⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– Rachel DaDamio | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@rdadamio on X⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– Megan Connelly | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@meganmorantwwe on Instagram⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠FOLLOW OUR SHOW– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Subscribe on Apple Podcasts here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow on Spotify here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow the show on Instagram here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

This week on Fuel for the Sole, we dig into the new caffeine guidelines, quality (and fast) post-run protein sources, how to fuel a night run, and our take on the best cost-effective bulk buys for an active lifestyle at Costco, BJ's, and Sam's Club. Want to be featured on the show? Email us (written or an audio file!) at⁠ fuelforthesolepodcast@gmail.com⁠. This episode is fueled by ASICS and RNWY!Head over to⁠ ASICS.com⁠ and sign up for a OneASICS account. It's completely free and when you sign up you will receive 10% off your first purchase. You also gain access to exclusive colorways on ASICS.com, free standard shipping, special birthday month discounts and more.RNWY Complete Protein is a post-run recovery shake we genuinely stand behind. Here's why: built on YESTEIN®, a fermented yeast protein that scores a PDCAAS of 1.0, which is the highest possible protein quality rating. That puts it in the same category as whey but without any of the dairy. Every serving gives you 25 grams of complete protein containing all nine essential amino acids plus 5 grams of creatine monohydrate and a five-enzyme digestive complex. Get yours at https://rnwy.life/ and use code FEATHERS15 for 15% off your purchase. Disclaimer: This content is not intended to be a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of your physician or other qualified health provider with any questions you may have regarding a medical condition.

I det tvåhundrafyrtiosjunde avsnittet av ”Maratonlabbet - en podcast om löpning” pratar vi med Hanna Lindholm som vid 46 års ålder är bättre än någonsin och laddar just nu inför EM på maraton.  Vi tar reda på hur Hanna har lagt upp sin specifika maratonträning inför EM, vilka nyckelpass hon har kört och hur hon tänker kring formtoppning. Hon pratar också om hur hon har använt sig av värmeträning och en ny produkt med broccoligroddar (Brocqo). Hanna delar även med sig av sina bästa råd till motionärer som satsar mot maraton.   Det blir dessutom inblick i Eriks träning mot Köpenhamn halvmaraton - han har bland annat tävlat i veteran-SM på Hofvallen i Östersund, både på 5000 och 10000 meter. Johan ligger i hårdträning för Lidingöloppet och är lyrisk efter att ha sprungit halva Kia Fjällmaraton över ett soligt Ottfjället.   Följ Maratonlabbet under den nionde säsongen för att lära er mer om löpning och för att se om Johan Forsstedt och Erik Olofsson klarar sina smala mål på 10 kilometer, halvmaraton, Lidingöloppet, maraton och ultralöpning. Avsnittet är gjort i samarbete med Asics, Craft och Lidingöloppet.

Dr Charissa Ho on Holistic Training, Running Longevity & Life as a Mum of Six | Women's Running Collective This week on the Women's Running Collective, Hayles and Jussie are talking about something we probably all need a little more of in our running lives: doing less, but doing it better. The girls kick things off with a recap of their City2Surf experience, where they decided to take the pressure off, forget about pace and simply run for fun. After a chaotic escape from Bondi (because apparently getting out of Bondi after City2Surf is its own endurance event

  The Shoe Geeks take this interview with Damion Perry, who joins them from Boston and is the Senior Product Line Manager at Puma.   This Special Episode is proudly brought to you by Shokz. They have just released the Shokz OpenRun Pro 2 TCS Sydney Marathon presented by ASICS Co-Branded Edition. Only Available at shokz.com.au and Shokz booth at TCS Sydney Marathon Running Show presented by ASICS. Patreon Link: https://www.patreon.com/insiderunningpodcast Opening and Closing Music is Undercover of my Skin by Benny Walker. www.bennywalkermusic.com Join the conversation at: https://www.facebook.com/insiderunningpodcast/ or follow us on Instagram: @insiderunningpodcast

It's just Karen and Rachel this week! The two get into plenty of marathon talk, life updates, and a conversation about the emotional side of injury recovery.They recap Karen's apartment move, Rachel's trip back to Notre Dame for a wedding, and why they both signed up for the McKirdy Micro Marathon. They also break down early morning workout routines, pre-run fueling, how to modify workouts without changing their purpose, and why laying everything out the night before might be the ultimate marathon training tip.Plus, Rachel shares the biggest milestone of her injury recovery so far (her first completely pain-free day after 12 weeks away from running!) and the two answer a listener question about the mental side of long-term injuries, offering advice, perspective, and encouragement for anyone navigating a setback of their own._________________Find this week's Zappos recs here:Karen: HOKA Mach X 3Rachel: The North Face Back-To-Berkeley Hiking Boots_________________SUPPORT OUR SPONSORZappos is an online retail destination for the best in footwear, offering the selection and expertise runners need to take on each day with confidence. Zappos carries an extensive assortment of performance running shoes, including leading brands like HOKA, Nike, Brooks, New Balance, ASICS, On, and more. ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Check out the latest selection on footwear on Zappos.com or in the Zappos app. ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠_________________CHICK CHAT– Send us your questions at ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠gettingchickedpodcast@gmail.com⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ or DM us on Instagram at ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@gettingchicked⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠YOUR HOSTS– Karen Lesiewicz | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@kare_les on Instagram⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– Rachel DaDamio | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@rdadamio on X⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– Megan Connelly | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@meganmorantwwe on Instagram⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠FOLLOW OUR SHOW– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Subscribe on Apple Podcasts here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow on Spotify here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow the show on Instagram here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

Watch the full episode on YouTube:We first covered Baseten last year when DeepSeek mania was at peak hype. Now they have raised a monster $13B round and become one of the new cohort of AI Infra decacorns that are (with Nvidia, Intel, and the semis complex) chief beneficiaries of the Inference Inflection. We return to Baseten at the peak of the 2026 edition of Open Weights debate. Ali has published a viral breakdown of Kimi K3:And since you last saw him, Philip has spoken at AI Engineer and written the definitive book on Inference Engineering spotted all over SF:Three years ago, inference engineering barely existed as a category.Today, it is one of the most critical disciplines in AI. Inference engineering inherently tackles a different question than standard model training: “How do you turn those weights from training into a product that is fast, reliable, and affordable at scale?” Focusing on these creates an entirely new optimization problem.In one recent GLM-5.2 experiment, quantizing more of the model actually preserved its benchmark quality while increasing throughput by 20%, because the errors introduced in different layers could cancel each other out.Inference is no longer just the final step after training. It is becoming its own engineering discipline, with its own research problems, infrastructure, and increasingly specialized roles.In this episode, Baseten's Philip Kiely and Ali Taha join swyx and Vibhu to explain what actually happens after a new open model is released and what it takes to turn “we generated a token” into a fast, reliable, production-ready API.We go deep on cache-aware routing, disaggregated prefill and decode, quantization, speculative decoding, KV-cache movement, model parallelism, GPU kernels, and the race to make frontier models up to 10× faster. Philip and Ali explain why inference optimizations can still produce gains of 20%, 100%, or even 200%; how quantization errors can cancel one another out; why identical weights can behave differently across clusters; and how Baseten grafted a Kimi vision encoder onto GLM-5.2 without changing the underlying language model.The conversation then expands beyond LLMs into NVIDIA Dynamo, mega kernels, Rubin, AI-specific chips, local inference, video generation, diffusion versus autoregressive models, and the enormous compute barrier to generating coherent long-form video. Finally, we explore the convergence of training and inference, continual learning through persistent KV cache, and the emerging loop where models help optimize the infrastructure that runs them.We discuss:* What happens when a 200,000-token request enters an inference system* Cache-aware routing and reusing previously computed KV cache* Why prefill and decode are increasingly handled by different GPUs* When dedicated deployments become cheaper and more reliable than shared APIs* How speculative decoding uses a smaller model to accelerate a larger one* Tool calling, structured outputs, and what LLMs actually do* What it takes to support a new open model on day zero* Grafting Kimi's vision encoder onto GLM-5.2* Retrofitting inefficient model layers with components from other architectures* Why models sometimes collapse into repeating the same token* How hardware, kernels, and race conditions create nondeterministic failures* Preserving model fidelity while making inference faster* How quantization errors can cancel each other out* Why inference optimizations still deliver gains of 20%, 100%, and 200%* How optimized serving can make a model up to 10× faster* NVIDIA Dynamo, KV-aware routing, and distributed model serving* Speculative decoding the speculative decoder* Why local AI is about making models less dumb while data-center AI is about making them less slow* Tensor, expert, and pipeline parallelism across GPUs* Hardware-aware model design, auto-tuning, and the case against mega kernels* Rubin and why inference is becoming a systems problem* Whether modern GPUs are evolving into programmable AI ASICs* Why enormous models like Kimi K3 require GB300-class hardware* Why open-source video generation still trails Veo, Kling, and other closed models* The quadratic attention bottleneck behind long-form AI video* Autoregressive video, real-time generation, and compounding quality drift* Why future video systems may combine autoregressive and diffusion architectures* Training for inference and inference for training* Continuous post-training, deployment, evaluation, and improvement loops* How GLM-5.2 helped optimize the kernels serving GLM-5.2 itself* Why faster networking could unlock dramatically faster decoding* Continual learning, KV-cache compaction, and persistent model memoryShow Notes* How to build a day-0 API for Kimi K3* 22580: From GPT2 to Kimi3, ExplainedPhilip Kiely* LinkedIn: https://www.linkedin.com/in/philipkiely* X: https://x.com/philipkiely* Inference Engineering: https://www.baseten.co/inference-engineering/Ali Taha* LinkedIn: https://www.linkedin.com/in/aliestaha/* X: https://x.com/waterloointernTimestamps00:00:00 Introduction and the 200K-Token Prompt00:03:18 Dedicated Deployments, Speculative Decoding, and Tool Calling00:11:26 Launching Production-Ready Open Models00:19:06 Model Retrofits, Failure Modes, and Nondeterminism00:28:22 Quantization and Canceling Errors00:32:15 The Race to 10× Faster Inference00:40:48 Dynamo, Speculation, and Local vs. Data-Center AI00:50:18 Model Parallelism, Auto-Tuning, and Mega Kernels01:00:55 Rubin, GPUs vs. ASICs, and Custom AI Chips01:10:03 Giant Models and the Limits of GPU Memory01:12:42 AI Video, Quadratic Attention, and Autoregressive Generation01:21:47 Audio, Images, and Diffusion Models01:27:32 Training, Self-Optimizing Models, and Continual Learning01:40:06 Closing ThoughtsTranscriptIntroduction: Baseten, Waterloo Intern, and Inference EngineeringSwyx [00:00:00]: Okay, we're here in the studio with Philip, old friend from Inference Engineering, the book, as well as Baseten and everything that you've done, you and I have done before, as well as Ali. Welcome.Ali [00:00:15]: Pleasure to meet you.Swyx [00:00:15]: Waterloo intern.Ali [00:00:16]: Waterloo intern, always.Swyx [00:00:17]: When did you get “Waterloo intern” as a handle?Ali [00:00:19]: As a handle? Oh.Ali [00:00:20]: I think the rebranding happened mid-March. When I saw it was open, I was like, “I have to take it. Up for grabs.”Philip [00:00:26]: The problem is that Ali is really good at his job and is not gonna be an intern much longer.Philip [00:00:30]: So we have to figure out who's gonna get the handle.Ali [00:00:33]: Well, I'll pass the torch over to the next intern.Swyx [00:00:34]: Oh, okay. It can be, like, you just pass it to another Waterloo grad.Ali [00:00:37]: To another Waterloo intern. No, bruh.Philip [00:00:39]: Yeah.Ali [00:00:39]: Intern.Swyx [00:00:40]: Intern, yeah.Ali [00:00:40]: And no.Philip [00:00:41]: You gotta get an intern from Waterloo.Ali [00:00:42]: Yeah, I've gotta get an intern from Waterloo.Swyx [00:00:44]: Right.Ali [00:00:44]: But they have to follow the path.Swyx [00:00:45]: Oh, it could, but it could come from Baseten, so it's like whoever Baseten gets from Waterloo.Ali [00:00:48]: Right.Swyx [00:00:49]: Has the title of Waterloo.Ali [00:00:50]: It stays in the ecosystem.Philip [00:00:51]: Exactly.Ali [00:00:52]: Halfway through the internship, you either get it or you're out.Philip [00:00:55]: You should also do, like, a big graduation ceremony where you change the handle.Ali [00:00:59]: Just say it.Philip [00:00:59]: For everybody.Swyx [00:01:00]: You guys are good at ceremonies, clearly. We had a nice launch of the book, very successful. But before we get into all that, I wanna start off with a fun question for you. Okay, you're an expert inference engineer. What happens when I send a long query, say two hundred thousand tokens into Baseten's inference? What's the process of query through GPU model routing, balancing, all that? What is all the stuff that we don't think about?Long Context Requests, KV Cache, and Cache-Aware RoutingPhilip [00:01:26]: With a long query specifically, the first thing that I'm gonna ask is, “Have you sent me this query before, or at least part of it?” and I really hope you have, because it's gonna be a lot easier for me and a lot cheaper for you. So the first thing that we're gonna look at is some cache-aware routing, where we're going to see, we probably have a number of instances, a number of replicas up serving whatever model you're hitting. We want to send this one to something with, number one, available prefill workers, and number two, ideally some cached input already there so that we can skip prefill on at least part of these two hundred thousand tokens. If you're doing two hundred thousand tokens, it's probably coding or a multi-turn agent or something where you would expect to have that cached. If you don't, we're gonna have to send it to a prefill worker. We've at least on certain models disaggregated prefill and decode, so you're going to have one set of GPUs that's solely going to process the input, create the KV cache, and get you your first token, and then that's going to be passed over to a separate set of GPUs, which is going to run decode. We're going to iteratively make those tokens. We're probably going to have some speculator model in front of that. I'm going to assume that you're doing coding, and because of that, our speculator model, which assumes you're doing coding, is gonna have a high draft token acceptance rate. If I'm wrong and you're asking me to summarize every Harry Potter book, it's gonna be slower. And then we stream that output to you and account for it, charge you, a couple of pennies and say, “Hey, would you like to send another one?”Swyx [00:03:04]: Except Baseten doesn't charge by pennies.Philip [00:03:07]: Well, yeah, we charge. I'm assuming that we're talking about the public model APIs. If you are setting up a dedicated deployment, then yeah, it's not pennies.Public APIs vs. Dedicated DeploymentsSwyx [00:03:18]: Yeah, one of the key differentiators when I was talking with Baseten initially was that people who want very high volume just need to rent by the box, ‘cause then it's up to you to figure out how to saturate the box.Ali [00:03:31]: And more often than not, it's, like, way cheaper if you're pushing, like, millions of tokens per hour, if you just pay per hour instead of pay per token.Philip [00:03:37]: Yeah, they do. I think that we've increasingly seen a lot of demand for the pay per token APIs, just because everyone wants to try open models, and then once they find a use case that's really sticky, then they move over to dedicated.Swyx [00:03:51]: Is there a best practice on when it's time to swap over?Philip [00:03:54]: Couple reasons. Yeah, reliability, that's a big one, right?Ali [00:03:57]: Like, if they have a very specific use case, they want you to train something specifically for them, like they want their own spec dec, for instance, for their own traffic.Swyx [00:04:04]: Spec dec is speculative decoding.Speculative Decoding and Custom SpeculatorsAli [00:04:05]: Speculative decoding, yeah.Swyx [00:04:07]: You have to explain.Ali [00:04:07]: Sorry. Like, speculative decoding is like, if you have a huge model, right? And so the model is going to be generating one token at a time every single turn, every single forward pass. So we attach, like, this little, like, parasite, like this layer that goes on top of the model, and this model just has to predict. It does three very fast autoregressive forward passes, and it will predict, like, three certain tokens, and then you do one forward stage over the entire original model in order to see if those predictions were correct or not, and then you accept them or you reject them. Now, this draft model is traffic specific, so if you, like, Philip said, if you're summarizing Harry Potter books, I can train exclusively that draft model on Harry Potter books, and I can guarantee you that I'm gonna accept the three tokens every single time. And so with that case, I increase your decode speed. I wouldn't be able to provide this to you if you're a shared endpointSwyx [00:04:53]: YeahAli [00:04:53]: ‘cause I have no idea if you're doing Harry Potter, if you're doing coding, if you're doing English. We don't know. Also, there was a thing in the book that mentioned that if they really cared about a specific threshold, chapter four, I think. Do you remember that?Philip [00:05:06]: Yeah. The things that you can do is you can set a specific, like, batch sizing, a specific, like, parallelism strategy if you're trying to optimize for, like, throughput versus latency. You can. Maybe a NVFP4 quant doesn't pass your benchmarks and you wanna run a model at higher precision, you could do that. There's just a bunch of reasons why you might wanna have your own endpoint and the biggest one, of course, just being, like, you don't have to deal with someone else doing a hundred million tokens of benchmarking traffic at the endpoint when you happen to be trying to serve your users.Swyx [00:05:40]: Yeah. I think one thing that is. That is a classic journey. Like, it's people is asking the, what happens when you type Google into the browser. Tool calling, is that just, you're generating JSON or is there more complication beyond that?Tool Calling, JSON, and Structured OutputsAli [00:05:58]: Certain customers that we have, they have their own post-trained models, and so they demand a tool calling that's not just, like parse a file or go find the weather. It's something that's very specific and you have to do post-training on this. And if the post-training on the model is not good or if the quantization after the post-training to get the inference to be fast, the model will struggle reading the JSON file and reading the tool calling. But it doesn't require its own like sandbox. It's not like it's going to use that tool calling to like escape a sandbox or like it doesn't have to be contained. It can just be a normal dedicated deployment. The challenge with tool calling more and more seems to be that the companies want certain tool calling which is a very sensitive thing to train. And because you're dealing with all of the JSON outputs, if it doesn't like close the end of the request in a very certain manner, you end up with a model that did the tool calling and like the thinking and so as a result of that, it didn't see the result and just hallucinated the result as it decoded. That seems to be the most challenging thing with tool calling, not really the sandboxes model.Philip [00:06:56]: Yeah, that's a challenge on the training side and then on the inference side, there's work that you can do to scope the possible output. So we published this at this point close to two years ago, the solution to this problem which is you make a state machine and you use that to constrain the output to a specific format. So this is the structured output problem. If you remember backSwyx [00:07:27]: Yeah, the specific grammar is,Philip [00:07:29]: Yeah, exactlySwyx [00:07:30]: GML had this thing.Philip [00:07:31]: Yeah. So it's like the old-school “make sure this is only JSON”, return only JSON orSwyx [00:07:38]: YeahPhilip [00:07:38]: Grandma's gonna die type of prompts.Swyx [00:07:39]: Is it BNF grammar? At some point OpenAI had released a thing that was like, yeah, if you want to constrain your output, write BNF grammar, back as NOR.Philip [00:07:47]: In our inference system, it's just a specified output format. And you get the guarantee that your output's gonna be structured along that format. And so applying that to tool calls can like help cut down on. You can still call the wrong tool or call no tool. It doesn't solve the certainty problem but it at least solves the output structuring problemSwyx [00:08:10]: YeahPhilip [00:08:10]: Within tool calls.Swyx [00:08:12]: And MCP is just another form of tool, right.Philip [00:08:14]: Yeah, exactly.Swyx [00:08:15]: As far as there's no special thing there.Philip [00:08:16]: The thing I'm always like explaining to people is the LLM is not capable of doing anything. It's only capable of making suggestions of what to do and then if those suggestions are formatted in a certain way and applied to a system that knows what to do with them, then an action occurs.Swyx [00:08:32]: Yeah. Part of the fun stuff is, this is solved outside of tool calling too. Like in an agent loop if the output is not correct or you're right, like reasoning, tool calling was done in the reasoning trace, just be like, “Oh, I don't know what to do. Let me just try again.” And it might get there after a few tries. And on your point of training, sometimes this is harder in smaller models, so you don't have the same exact quality outputAli [00:08:56]: Right.Swyx [00:08:57]: When you just swap from a big model, right?Ali [00:08:59]: Yeah. I will say that, before, I think we need to go back to inference engineering proper.Ali [00:09:04]: But, I had expected that something would replace JSON because it's hard to stream JSON ‘cause JSON must be complete and you must have open and close brackets and everything. So it's hard to parse something or validate something while it's being streamed. So people invented all sorts of things that are like, I forget the name of some of these alternatives, but it's something like TOML, something like YAML. But JSON seems to be dominant still.Philip [00:09:30]: The JSON outputs aren't that long, right? Like you could have a long-- ‘cause tool calls also contain the arguments in them and perhaps for a certain tool you might pass like a very long argument. But my impression of the median tool call is that it's a relatively small number of tokens, right? So I would expect that speculators are generally fairly good at something as formatted as JSON. And so you would have like a pretty fast decode step there and that the streaming wouldn't be as valuable, but maybe I'm wrong about that.Ali [00:10:02]: I think you're also bounded by the software or that the model is gonna integrate with if the software is built with JSON for the tool calls or if the company that you'- if your customer says that this is how our software works and our tools are interfaced with JSON, you can ask them to like, change their software and say like, “Yeah, this is gonna be better for the model.” but like with the right training shouldn't be that much of a difference. Also more profitable if it outputs more tokens probably.Swyx [00:10:25]: Depends on your business model.Swyx [00:10:27]: It really depends. But I will say that, as a writer with like experience a lot with generated output, I do try to move from text to JSON text which is very long JSON, right? Like there's paragraphs in every field because I'm trying to structure it, right?Philip [00:10:44]: Right.Swyx [00:10:44]: I want you to first make factual statements, then make opinions then make bullet point summaries, have dates, have entity references have your sources for references, all these things. Anyway, so these are things that like I think people who really experiment with structural output have to really care about. But, let's, let's recurse up the stack a little bit. Before we started recording, you mentioned something really cool, which is that there's a lot of engineering that-- inference engineering that goes on when a new model provider releases a new model, right? So let's call it GLM-5.2, Kimi K3. I had previously assumed, especially if it's like, well, GLM 5 to 5.1 to GLM-5.2, like that you've supported them before. Is it that much work?What It Takes to Support a New Open ModelAli [00:11:26]: It's a lot of work.Swyx [00:11:28]: Yeah. Okay. So like, a lot of people, all you guys, right whenever a new model launch like, people rush to say like, “Oh, Hugging Face supports this, Fireworks supports this, Spacetime supports this,” and I'm like, “Yeah, of course we support it.” But what goes into that? What goes intoPhilip [00:11:40]: I think it's more than just support it too, right? It benefits the consumer a lot. Like I think it was with Kimi K2.5 or GLM-5.2 the latest, there was an inference war, right? X provider is at 90 tokens a second. The next day we're at 150. The nextSwyx [00:11:55]: I kinda kicked that off with the GLM-5.2.Swyx [00:11:58]: I wrote a Twitter article about. It got like half a million views,Ali [00:12:02]: Based on being numberSwyx [00:12:03]: YeahAli [00:12:04]: Or it's for something else.Swyx [00:12:05]: Yeah. Which,Ali [00:12:06]: Oh my GodSwyx [00:12:07]: Which then got everyone really excited about, hey, how can we, bend tracks a little bit further and,Philip [00:12:14]: There's a difference between support the model, as in I can make a token out of this model, and support a model, as in I have a production-ready API from this model.Philip [00:12:26]: Getting to the point of I can make a token out of this model is not that hard because generally the, open source inference engines, vLLM, SGLang of the world oftentimes even receive weights ahead of time, maintainers do, or the people making the model merge PRs to ensure support. So you generally can, just get it working on the standard open source stack without too much pain in most cases. The challenge is, every inference company is gonna have own proprietary stack. Some open source components, some in-house stuff. And for any arbitrary model, there's going to be some new stuff. Sometimes you get lucky, like K, two five to two six was, like, pretty similar.Quantization, Speculators, and Production ReadinessAli [00:13:16]: Yeah. It was pure continued post-trainingPhilip [00:13:18]: YeahAli [00:13:18]: If I remember correctly.Philip [00:13:19]: Even in those cases, there's still stuff you have to do. You have to redo the quantization work. You're taking the model from. Generally, these models are not released in NVFP4, and we want them to be in NVFP4 for maximum Blackwell compatibility. So we have to perform that quantization, and, calibrate the quantization to make sure that we're not causing any regression in the model's intelligence. And then we also have to train the speculator, as we've talked about. Generally, we have. We have ZDR, zero data retention on our model APIs, so we don't know exactly the traffic that people are sending us, but we know what's popular. We know that coding use cases are popular. We know that agents, agentic use cases are popular. So we can get public data sets that are representative of that traffic and train general speculators. Now, with speculators today, you need to train the speculator using the base model itself because you're getting hidden states out of the model from running inference on these specific prompts, and that is the training data you use to create the speculator. So there's that process which you need the real model weights for. And then there's of course just the process of, standing up all the infrastructure behind it, loading all this stuff, testing it. And then when there's a new model with a newer architecture, I think that, like, the DeepSeek models tend to be the most challenging as they have, like, the most novel architectural stuff going on, model after model. But every new model has something. Kimi K2 had. Oh, sorry, GLM-5.2 hadAli [00:14:53]: Sparse attention.Philip [00:14:54]: Yeah,Ali [00:14:54]: YeahPhilip [00:14:54]: the DSA.Ali [00:14:55]: Right. Which is brought from DeepSeek.Philip [00:14:57]: Yeah. AndAli [00:14:59]: So you can copy-paste then?Philip [00:15:01]: It kindAli [00:15:01]: I don't know how this works.Philip [00:15:02]: So, like we had to, like, build support for that into our runtime. And you're right, like it is really interesting the way that all of these open source labs borrow from each other. For example, like GLM-5.2 doesn't have vision. So something that, Haley, a guy on our team, if we could take a look at this, he, like, grafted the Kimi vision encoder onto GLM-5.2.Retrofitting Vision into GLM-5.2Ali [00:15:27]: We'll be training the projector.Philip [00:15:28]: Exactly. So if you think about, like, the encoder, there's the encoder, which is the part that looks at the image and turns it into latent information, and then there's the projector which likeAli [00:15:38]: You can say latent space. It's okay.Philip [00:15:41]: And then there's the projector that maps it onto, the model itself, and then there's the model weights. You don't wanna mess with the model weights because you run a chance of making the model dumber at something else for the purpose of giving it vision. So instead, Haley started with just a projector, which is only a handful of millions of parameters.Ali [00:16:02]: That would be, yeah.Philip [00:16:02]: Yeah.Ali [00:16:03]: Can you show the training one?Ali [00:16:04]: Like the way it groksPhilip [00:16:05]: YeahAli [00:16:06]: Very interesting.Philip [00:16:06]: And maybeAli [00:16:07]: That right therePhilip [00:16:07]: Maybe Ali, you should take it from here. You've got a betterAli [00:16:10]: Ooh, double the sandPhilip [00:16:11]: Understanding of this than I do.Ali [00:16:11]: Yeah. You can see, like, he. The way he trained this is really cool. At the beginning, he was training it using just like, “Here's a picture of a mountain. Can you describe what's in this mountain?” And that caused it just like the first, learning walls. Like here you can see this all we're trying to teach it is to translate the encoded. Like it's already taken the encoder from Kimi K. It's taken the image. It'Philip [00:16:31]: Yeah. FrozenAli [00:16:31]: FrozenPhilip [00:16:32]: With adapter.Ali [00:16:32]: Exactly.Philip [00:16:33]: Yeah.Ali [00:16:33]: So the brain is frozen and the eyes are frozen. It's just we're tryingPhilip [00:16:37]: AlignAli [00:16:38]: Interconnect between the eye and the brain, right? So the projector. And so you take the tokens and then he's like, “Oh, can you describe what's in this image?” And he's like, “Oh, it's a mountain,” or it's a person or it's a human, whatever the case is. But that didn't cause complete understanding. So he changed it such that every image was associated with a data set of questions. Like, does this image have a white male? Does this image have birds in the top corner? Does this image have a scientist in it? All of that stuff. And it would have to answer questions correctly. And using not just training on describing an image, but being able to answer question, another question, answer over time. Like you can see the grokking, which is like genuinely insane, that retrofitting vision into a large LLM can learn to that extent. And even for images that it doesn't perform well on, for instance, if you ask it a picture of like Stephen Hawking, “Who is this?” Maybe it doesn't get it, but it will say something like, “This is Albert Einstein.” Like it still understandsPhilip [00:17:25]: Close enoughAli [00:17:26]: That this is a scientist who is a man who has, some significant achievements, all that stuff. So that's like really cool.Philip [00:17:32]: Yeah. So, we've covered Hao Tian before, who the author of the LLaVA paper that did this, a while ago. And I think that's very foundational work for anyone who hasn't done vision work before.Ali [00:17:41]: Same with the CLIP and MetaCLIP, where you go from just captioning to building out questionsPhilip [00:17:47]: RightAli [00:17:47]: Off the image and how much better you can get performance.Philip [00:17:50]: Right. Right. Right. Yeah. But what's, what's so exciting about this is if you look at a model like this. Now, this is a little bit more of a research project. It's not. It got to 56% on MMLU Pro, I think. So not quite frontier. But if you're running this model, you haven't suffered any loss on your GLM-5.2 quality. If you don't have an image, it'll just behave exactly the way it used to. And ultimatelyAli [00:18:14]: Which in the inference code you literally do not include the other part, right?Philip [00:18:18]: Yeah. You would just skip the encoder if you don't have an image input.Ali [00:18:22]: Okay.Philip [00:18:22]: Just confirming.Philip [00:18:23]: YeahAli [00:18:23]: Does it affect a lot on the overall inference side? Like you're not adding much, you're adding a very small vision encoder. These are typically likePhilip [00:18:30]: They're super fineAli [00:18:31]: Less than a billion parameters, right?Philip [00:18:32]: Yeah. It's, - There's a little bit less standardization among vision encodersSwyx [00:18:37]: YeahPhilip [00:18:37]: So the support matrix can be a little bit, sparser. But overall, yeah, it's a pretty, it's a pretty minor component of the overall system. And ultimately what you get out of the system is all of a sudden you have Kimi Vision, GLM weights, and DeepSeek attention all in one model.Open Source Model Grafting and Franken-MergesPhilip [00:18:56]: And that's, I think, a lot of the power and beauty of open source, is that you can take all of these different components and combine them together into a system that's better than anyoneSwyx [00:19:05]: YeahPhilip [00:19:05]: Can be individually.Swyx [00:19:06]: People used to say that you would also do Franken-merges where you would take likePhilip [00:19:10]: YeahSwyx [00:19:10]: Layers from each model.Swyx [00:19:11]: Does anyone do that anymore?Ali [00:19:13]: Well, to your point previously when you were mentioning like, the work that goes into supporting a model when it first comes out, like GLM-5.2 or MiniMax M3 or whatever the case is. Sometimes you do have to like, you do have to switch out some things. Like, for instance, the MiniMax M3 head uses full attention, and with full attention you end up with this like insane bottleneck in spec dec ‘cause you're doing auto-regressive token generation for three tokens, and you're doing this like N squared over all of the tokens that are in your sequence. Your KV cache is like very large because it's not sparse, it's not top K. So we find it better to like, okay, we're gonna replace this, we're gonna replace this layer with a layer from another model that's using like GQA, for instance. And then just with the right training, you can get it to have the same acceptance rate. So it is very possible to retrofit layers from other models and very much needed. If a layer is like inefficient, the training just becomes the challenge, like how do you ensure that you train it properly? Which again to your earlier point is like the mesh between training and inference. As in like you need very good training in order to do fast inference. That's like, I feel like more and more becoming true.Swyx [00:20:21]: Yeah. Anything else on the support side when you say like get it to fully production ready?Loop Detection, Race Conditions, and Non-DeterminismPhilip [00:20:26]: Yeah. I think that there's also a question of just, we can test a model to a pretty extensive degree, but we're trying to get it out quickly and then you see a bunch of other people test it and you get interesting results. There was an issue with, GLM briefly where we had some like mode collapses where it would just output the same token over and over again for certain prompts on certain temperatures. Like once you expose an endpoint to the real world, there's going to be, so many more varieties of things given to it that you're able to, discover and patch things. So it's not just a, day zero process, it's then like for the first week, for the first month, if a model remains popular, like how do you both fix bugs and then continue to push the envelope on performance?Ali [00:21:21]: What do you mean you don't want your model outputting S?Swyx [00:21:24]: Is there loop detection on that stuff, by the way? It still happens like quite a lot, which is surprising.Ali [00:21:30]: We have like we, in our endpoint, like if a model was to output the same token like four plus times, we just cut the generation. We say like, “Oh, sorry, this-- Like try again,” or like we will reprocess the request. ‘Cause we know then, like if it, like if, yeah, it's four times the same token, it's probably collapsed.Swyx [00:21:45]: Yeah. Is there a way to opt out in case I really want that?Ali [00:21:48]: You want that?Ali [00:21:50]: I think there's a way that we have to handle it. I'm not exactly certain, but I feel like in certain models, like when they output something like you can imagine, like a table for instance, and so they want, they wanna draw like 12 dashes and 12 dashes. Yeah, I think there's a way for that to happen. I think we only do it on certain tokens. Like we exclude certain special characters.Swyx [00:22:07]: Yeah.Ali [00:22:07]: So we only do it on like certain like S is the most common almost. GLM-5.2Swyx [00:22:11]: OhAli [00:22:11]: And I think it was DSV 4 as well. Like you'd just have like looping issues where like you literallySwyx [00:22:17]: ItAli [00:22:17]: Just have like S.Swyx [00:22:18]: Yeah. Is there a special, something special about S? No, just randomlyAli [00:22:21]: It just seems to be the one token involved.Swyx [00:22:23]: Yeah. And it'Philip [00:22:24]: Is thereSwyx [00:22:24]: And it's only temperature 0Ali [00:22:27]: NoSwyx [00:22:27]: Even at other temperaturesAli [00:22:27]: Even at like 0.9 or whatever, it will still, it will still collapse.Swyx [00:22:30]: That's weird, right?Ali [00:22:30]: It's, it is an inference problem to be honest, like a software problem. Like oftentimes, the image you run will-- like NVIDIA will release an image for instance, and if we will upstream the changes from their latest TensorRT-LLM image into our stack, we'll find that it fixes it. Or oftentimes this will only happen in an inference engine that you're using like SGLang. But if you were to switch to vLLM, that isn't the case. So it seems to be like an extremely like deterministic software issue and not really a model issue. It's not like a weights problem. Like I'- we'll say like, “Oh, it's a problem with the quant. We did PTQ wrong,” right? But that isn't, that doesn't make sense because the same weights used with a different inference engine does not repeat the problem. And sometimes it's, the kernels that are being used in the backend have like these very subtle sometimes race conditions, where if you were to use this model hosted on one cluster, you will never get this problem.Swyx [00:23:19]: Oh my God.Ali [00:23:19]: But if you host it on a different cluster, you will. And the reason is the KV cache transfer from a node to node in that one cluster is using a slower interconnect than the node to node in another cluster. So that exposes the race, whereas in another cluster it doesn't. So then you end up just like, okay, this model is not gonna be hosted on this cluster. We're gonna host it on, another cluster because that cluster exposed that problem. But then it ends up with like, okay, is it the software? Is it the model weights or is it the hardware?Swyx [00:23:42]: There is a thing about this with temperature 0 still not being deterministic, right?Ali [00:23:46]: Right.Swyx [00:23:46]: Mostly because of hardware. Even at temperature 0 same model, you won't always get the same output.Swyx [00:23:52]: Even-- But I'm surprised by the race condition one because, I thought PyTorch was a graph that like guarantees that you at least, execute things in the right order.Ali [00:24:02]: Well, yeah, true. Like I'm not, I'm not saying that there is. Like well, you have things like PTL optimizations where like you can start a kernel before the end of the previous kernel, and that's like ‘cause you want to do that because there'sSwyx [00:24:12]: It's like pipeliningAli [00:24:12]: Expense. Exactly.Swyx [00:24:13]: Yeah.Ali [00:24:13]: But it'- But you don't do it cleanly. Like you overlap a little bit of the execution. No, it is very possible that the kernel itself, like that one block that is supposed to be running in this instance of time, that kernel itself has a race condition. For instance, like a missing barrier. Like often if you're designing a kernel and you want it to make it to be very fast, if you don't test it extensively, you'll, you'll have certain threads access data points from registers before they've been written to by other threadsSwyx [00:24:36]: YeahAli [00:24:36]: For example, because like your barrier is wrong or your synchronization was wrong. But yeah, like the testing itself is very difficult in those like, andSwyx [00:24:42]: And there's no like borrow checkerAli [00:24:45]: What does that mean?Swyx [00:24:46]: Like Rust. Like the. If you're trying to have like memory safety It sounds like a comparable problem.Ali [00:24:52]: Well, yes, but you're working in CUDA, right, NVIDIA GPUs. Like- You just need a higher level language like modular Maybe that's what modular is supposed to do. I don't know.Quantization Quality and Vendor FidelityVibhu [00:25:00]: How do you see keeping quality of the model? So you talked about all these steps of, okay, you gotta do quantization, train your own speculative decoderAli [00:25:07]: RightVibhu [00:25:07]: Run on different hardware. Looking at other model providers, okay, you kicked off a inference speed race on the consumer end. What goes into keeping quality the same across them, right? Sure, you can run benchmarksAli [00:25:22]: YeahVibhu [00:25:22]: But, like, how do you determine how much quantization are there standards? What goes intoPhilip [00:25:27]: There's a few things on quality. Most inference optimizations are lossless. KV caching, for example. You are just recomputing or preventing recomputing the same values. Speculation, of course, if a draft token is wrong, it gets rejected. The main lossy optimization is quantization. And that really comes down to, number one, data format, number two, which parts of the model you choose to quantize, which layers, and number three, like doing a lot of calibration on the quantized weights, to ensure that you're preserving all the outliers. There's other tricks that you can do, though. A big one is long context, ‘cause one thing you asked at, right at the beginning is, “Oh, what's gonna happen if I send a 200,000 token request in?” So with a long input sequence, you need to, store a lot more information. You need to process a lot more tokens. And so even if a model has a context of a certain length, you might, as an inference provider, choose to build an API with a shorter context length, and of course a full length one as well. Because if someone doesn't need the full million token context, for example, you can get them better performance. I don't know if that's exactly like quality of the model. The way that I think about quality is to what degree are we faithfully serving the original model? If you think of a golden implementation of a model that performs exactly the way the model is designed to perform, I think of quality as how close are we getting to that, 100% fidelity of the model.Philip [00:27:13]: You can also, of course, think about quality from the training side and how do you push yourself past 100%. But when I think about purely inference optimizations, it's getting faster while staying as close to that 100% fidelity mark as possible. And certainly our standard internally is that, like you should not be able to tell the difference between our API and a, official API. I think Kimi in particular does a good job of vendor benchmarking hereAli [00:27:41]: YesPhilip [00:27:41]: Where they haveAli [00:27:42]: They released an actual vendor benchmark.Philip [00:27:43]: Exactly, yeah.Ali [00:27:44]: ‘Cause they accused, some people, Amazon? There was some provider that was not doing very well on Kimi's benchmark.Philip [00:27:50]: Yeah.Philip [00:27:51]: So, with Reflect we probablyVibhu [00:27:52]: This was a long time ago, right?Philip [00:27:54]: No.Ali [00:27:54]: Yeah, like threeVibhu [00:27:55]: They alsoAli [00:27:55]: Four, five months agoVibhu [00:27:57]: This also happened with, I don't remember which model, but they pulled out quite a few, and then they started a whole chart about this. It might have beenPhilip [00:28:03]: Kimi Vendor Verifier.Ali [00:28:04]: Yeah.Philip [00:28:05]: Yeah.Ali [00:28:05]: Yeah, ‘cause you, ‘cause you'd be pissed, right? Like if you'Philip [00:28:07]: Yeah.Ali [00:28:07]: If like if I'm a consumer and I'm using like Amazon's endpoint for instance, and I've used Kimi and I'm like, “Oh my God, like this is bad,” I'm not gonna say, “Oh, Amazon quantized the model in a bad way.” I'm gonna say, “Oh, Kimi sucks.” Right?Philip [00:28:17]: Yeah.Ali [00:28:17]: So it seems like that makes sense.Philip [00:28:19]: Yeah, they care. They care.Vibhu [00:28:21]: Justifiably.Ali [00:28:21]: Yeah, justifiably.Vibhu [00:28:22]: This is probably a stupid question, but just checking, has anything improved from main quantization?Philip [00:28:28]: Yeah.Vibhu [00:28:28]: Like, is quantization always strictly worse?Ali [00:28:30]: Well technicallyVibhu [00:28:32]: NoAli [00:28:32]: It's a lossy. QuantizationPhilip [00:28:33]: YeahAli [00:28:33]: Is a lossy, it's a lossy implementation.Philip [00:28:36]: Speed improvesVibhu [00:28:36]: Speed improves.Ali [00:28:37]: It the number, likeVibhu [00:28:38]: No, I' always look for inverse scaling laws.Philip [00:28:40]: Yeah.Ali [00:28:40]: Yeah.Vibhu [00:28:40]: This is something I learned from Noam Brown, where like things that normally act in one direction sometimes do.Philip [00:28:45]: Well, technically when you run a benchmark, because these models are deterministic, sometimes your,Ali [00:28:52]: YeahPhilip [00:28:52]: NVFP4 quant is like, two basis points higher than yourAli [00:28:56]: No, it's noise. It's noise.Philip [00:28:57]: Yeah, exactly. I'm like, yeah, it's, it's within. That's why I always say within margin of error.Philip [00:29:01]: And I stopped saying that because everyone assumes that what is, well, within some margin of error, we're barely inside of that to the worst, so we're saying. But yeah, sometimes it's just like, gives you a higher output score. But like Ali said, that's noise. To my knowledge, you're not necessarily making the results better. You're just trying to, again, like keep your fidelity as close to 100% to the original model.Layer Selection, KL Divergence, and Better QuantizationAli [00:29:27]: There is, to your point, research that we did on MP. I don't know if you are able to pullPhilip [00:29:31]: YeahAli [00:29:32]: A tweet we did. One of our research interns, Joshua, I think it's a tweet on how we have 20% better quantized GLM-5.2 than NVIDIA. Essentially what we found throughout like this month research is, okay, quantization is a lossy. It's. You're compressing the data from, occupying 16 bits to occupying, four bits, for instance. And so you're losing some information, and you're trying to minimize that. And so when I say that I'm gonna quantize the model, my job becomes how do I find the layers that I can quantize, and how to find the layers to not. For instance, with image models, I don't quantize modulation layers, and I don't quantize out projections because those two are. Like out projection is what you see as the user. Modulation is what the model sees or understands. Right, exactly. And so to his paper, do you have the. It doesn't have the. Yeah. It's a long paper. I don't know if I can findVibhu [00:30:25]: If there's a part to search or it's probably in the thread.Ali [00:30:28]: It's probably in the thread.Vibhu [00:30:29]: Yeah.Ali [00:30:29]: But the long and the short is it is very possible that quantizing more of the model makes the results. Like if I have a model that I quantize layers one, five, and 10, and another model where I only quantize layers one and It is possible that the model in which I quantized more information is going to perform better because the quantization errors have canceled out. And so what Joshua showed in his mathematical proof where he had like a verifier in, is that you can predict which layers are going to have quantization errors that will cancel out with each other, and you choose to quantize those layers. And so the result of doing this mathematical quantization is you end up with a model that's 20% more quantized than another provider, so you get 20% more throughput of it because there's more layers than running an NVFP4, and your quality is better than that other quant because the layers that you chose to quantize have their errors cancel out, like one layer skewed to the right one layer skewed to the left, one layer skewed to the right. Your final logits distribution is more similar to the original distribution of the model, so you have better fidelity. And so the way we proved this was with KL divergence. So instead of just scoring on the benchmarks, we scored the KL divergence between the logit distribution of the quantized model and the logit distribution of the original full precision model, and we showed that with this technique we get. If your probability distribution on the logits which token it wants to select is more of the same as the original model, you're probably gonna end up staying true to the original model. So yeah, so it seems like previously before this, it seemed like the industry was, well, the more you quantize, the worse it's gonna be, ‘cause the more loss you introduce. That's not exactly, not necessarily true. So yeah, doesn't improve it, but can cancel out.Philip [00:31:57]: I think it might be this, but reminds me a good bit about pruning where you can prune off certain layers.Philip [00:32:03]: But very interesting. Didn't know this was a whole paper you guys put out.Ali [00:32:06]: It's. Fun fact, it was originally 72 pages, this paper, and then we decidedPhilip [00:32:11]: WowAli [00:32:11]: We can't tell. We couldn't release it. So it's now 45.Swyx [00:32:15]: Still 39 pages, so very substantive. We talked about evals and all these things and, like what's possible in terms of speedup? Like it's like probably like the numberInference Speedups and BenchmarkingSwyx [00:32:25]: Thing that people do wanna care about, and it's something that you wrote about in your post. Like official API is 70 tokens per second, and you push it up to 90. Is that like a normal thing?Philip [00:32:36]: So what's cool about working in inference, the reason that I think inference is going to be a useful place to do engineering for a long time, is that if you look at highly optimized domains like, say, finance, if you're in finance, you measure how much better you got in basis points. It's like, “Oh, I got five basis points better, like twentieth of 1% better,” that's huge news because everything is so optimized. When we publish optimizations, it's 20%, it's 100% it's 200%. So there's still probably like a lot further to go, honestly. Like you'll, you'll know that inference is pretty much solved when researchers start publishing about how they got 1% faster at something.Swyx [00:33:19]: Which by the way, because I am from the finance background, in the ‘70s, that was the margin at the time. When you did quantitative finance research, you would findAli [00:33:27]: And like 20%, tens of percent.Swyx [00:33:29]: That's. Yes.Philip [00:33:29]: Yeah.Swyx [00:33:30]: And now it'Philip [00:33:31]: Tiny fractionsSwyx [00:33:32]: For those people interested, look up Andrew Lo's paper. He had a really interesting illustration of quant, stat arb, distribution, narrowing down from like those kinds of 20% differences in the ‘70s, down to nothing today, which is very cool.Philip [00:33:48]: Exactly, and we're at the beginning of the same type of thing. Now benchmarking is hard. I think anyone will tell you that, and benchmarking provider speeds is hard because there's so many variables that go into it. What hardware are you using? How much load do you have on the system? What's the exact nature of the prompts and input and output sequence lengths? All that stuff. But overall, when you start stacking these improvements, you're looking at multiples. You can look at it. The most common form, of course, is TPS, tokens per second, which is bad naming by us in the industry, ‘cause there's two tokens per second. There's tokens per second, the throughput number, and the latency number.Ali [00:34:31]: TTMT, yeah.Philip [00:34:32]: Like total tokens per second out of the, out of the GPU as a throughput number. Most people only care about tokens per second as the latency number, which we should call ITL, intertoken latency, but we don't.Philip [00:34:44]: Anyway, so you can imagine a standard API without many optimizations for a 1 trillion parameter model operating somewhere in the 30 to 50 tokens per second range for reasonable traffic profile. And we generally see the goal of, pushing to 10X that. But, not necessarily day zero, but by stacking enough optimizations, if you have, say like four optimizations, each of which doubles performance. Or sorry, three optimizations, each of which doubles performance, then you stack that up, that's an 8X gain. That's the order of magnitude that we're working with in this space. We're trying to make things substantially faster, not just go from like 70 to 90.Swyx [00:35:38]: Are you saying you've. You have done that?Philip [00:35:40]: So let's say you have as a reasonable baseline, 30 or 40 tokens per second. You can achieve 10X that. So like on GLM-5.2, if you run it unquantized, perhaps on H100s even, and you're just using an off-the-shelf inference engine with no particular optimizations, no speculator, nothing extra around like KV routing, no disaggregation, you're, you're probably, yeah, looking at that like 30 to 40. You think that's like a reasonable baseline?Swyx [00:36:12]: Right. Right.Philip [00:36:12]: To get to something like 10X, there's a lot of trade-offs that you're making. If we're running at more like a 300, 400 tokens per second range, you are using the best hardware possible. You have a optimized speculator. You have done all of your quantization work. You are Seeing a pretty high cache hit rate. You are running with a reasonably small batch size and a parallelism configuration that is tuned for latency versus throughput, but it is possible. So the spreads that you see if you, like, go on artificial analysis or you go on OpenRouter and you look at, the worst provider to the best provider, oftentimes can hit that range. 10X is of course very aggressive. It's oftentimes maybe more of a four to six times improvement. But that's the performance that makes us really excited, is when we can get these huge gains, not just go from 70 to 90 tokens.Stacking Optimizations: NVFP4, Speculation, and DisaggregationAli [00:37:19]: It's also, like, hardware dependent. Like, ifPhilip [00:37:20]: YeahAli [00:37:20]: If you have a thing where you're serving it on just, like, a node of H100s and then you throw, like, you shard the model across, like, four nodes of B200s. Like, you can definitely increase the speed with just throwing more hardware at it. Like, normalizing for the same exact hardware and the same number of GPUs.Philip [00:37:35]: Yeah. Then you're looking at, like, a two to 4X improvementAli [00:37:38]: Right. RightPhilip [00:37:38]: Depending on the inference optimizations. So yeah, it's. Some of it's, what's the call, and some of it's who's the driver.Vibhu [00:37:46]: If you break down the two to 4X, say the example is run GLM-5.2Ali [00:37:51]: YeahVibhu [00:37:51]: On B200sAli [00:37:53]: YeahVibhu [00:37:53]: Single node, right? What's, like, the cost trade-off for effort to get, like, the last bit of juice out versus what should people just think of, right?Ali [00:38:01]: Spectre quantization. Yeah.Vibhu [00:38:03]: Spectre quantization.Ali [00:38:04]: That's, that's, that's like 95%. LikeVibhu [00:38:06]: And how far does that get you? And how easy is that for the average person to do? So say right I wanna throw the weights of GLM-5.2 on a node of B200s, how easy is it to find speculative decoder- decoder model or already quantized model? How much work goes into it?Philip [00:38:23]: If you're doing it up front, it's quite a lot of work. If you're doing it today, there's going to be people who have published things that you can just, you can just grab some NVFP4 weights. You can grab a speculator. Yeah, if we're thinking about, like, what are the 2Xs we're stacking, going from, BF16 to NVFP4 is, it's not quite a 2X, right? It's like. I think it's about, like, 30 to 40%, from 16 to 8, and then another 30 to 40% multiplied from, 8 to 4. So that doesn't quite get you a 2X, but, like, roughly a 2X. Speculator, roughly a 2X. Disagg on top of that if you're able to get enough hardware and put enough traffic through it, another roughly a 2X. And then you add in some, double-digit percent increase from having just a better runtime with, the latest kernels and stuff behind it. And that's how it stacks up.Ali [00:39:21]: YeahPhilip [00:39:21]: So building each of those, like, building the, quantized weights is, for someone who really knows what they're doing, hours to days of work. Building the speculator, again, like, hours to days of work. And the, disagg setup, hours to days. Well okay, but like once you haveAli [00:39:39]: Once set up. Once set up. YeahPhilip [00:39:40]: Yeah, getting disagg working for the first time, I'm saying, of course, is very difficult.Philip [00:39:44]: The marginal implementationAli [00:39:48]: Like, if you're just grabbing, like if you are a person, like just a normal consumer who has access to, like, a node of B200s and you're wondering, “How can I just host it myself?” You don't need to quantize the model yourself. There's always gonna be, like, an open source quantized checkpoint. NVIDIA's gonna push one out if no one else does. You. Usually, the providers will have their own spec dec that they've trained as well. You don't need to train your own spec dec. You can just use that as well.Philip [00:40:09]: Yeah. Like, GLM-5.2 has its own MTP.Ali [00:40:13]: Right. Right.Vibhu [00:40:14]: What's multi token prediction?Philip [00:40:15]: Yes.Ali [00:40:16]: I'm justVibhu [00:40:16]: Can you explain that?Ali [00:40:16]: I'm just an expert.Ali [00:40:18]: I can do it for you in case I get it wrong?Vibhu [00:40:20]: No.Vibhu [00:40:21]: Yeah, you should correct if we're wrong, but their multi-token prediction can be used for self-speculative decoding.Ali [00:40:27]: I'm not sure. I'm not gonna correct that.Vibhu [00:40:28]: Okay. I'm semi-confident in thatAli [00:40:30]: Okay. YeahVibhu [00:40:30]: But someone can check. But it's useful to paint the story of, okay, not just the average person, but say a company wants to switch from serverless inference I wanna throw this up on. I wanna rent some GPUs, throw it up. These are the steps you take to do significantly faster than just put it behind vLLM.Ali [00:40:48]: Right.Vibhu [00:40:49]: I was waiting for a mention of Dynamo.Vibhu [00:40:51]: I feel like, that's supposed to be the baseline that you measure against.Dynamo, KV Routing, and Disaggregation ToolkitsPhilip [00:40:55]: I would think of Dynamo as less of a box system and more of a toolkit for building with. So when we talk about doing aware routing, when we talk about doing KV offloading, when we talk about doing, PD disaggregation, Dynamo fundamentally is. By the way, Dynamo is an open source library from NVIDIA.Ali [00:41:17]: We've done a pod with KylePhilip [00:41:18]: OkayAli [00:41:19]: Kyle Cranin.Philip [00:41:19]: Cool. So then your listeners know then that it supports all the different inference frameworks. And it is multi hardware, which is interesting.Ali [00:41:28]: But it's just a router, it's not like an optimizer layer.Philip [00:41:30]: Yeah. All it does, like, what Dynamo is good at, it is a library for moving information around your cluster, around your hardware. So if you have, KV cache on one place and you need it to be somewhere else, Dynamo coordinates NIXL for you to move that around.Philip [00:41:49]: That doesn't mean that, like, out of the box, you just say, “Pip install Dynamo,” and then you get, like, a massive performance speed up. It's more of a developer toolkit.Ali [00:42:01]: Yeah. I would have said it would. It comes with a set of defaults that you can then swap out.Philip [00:42:06]: It does. If the industry at large, I think, was, like, rolling out all of these deployments, standard, then I think it would be, like, a credible baseline. But, we've got to, we've got to benchmark against, like, what we're seeing in the wild.Speculative Decoding Methods: Medusa, EAGLE, n-Gram, and Spec-SpecVibhu [00:42:23]: I did wanna talk a little bit more about PD disagg, because that is probably, like, number three after quantized and speculative decoding. In your book though, I was just gonna pull out the book.Philip [00:42:31]: Yeah.Vibhu [00:42:32]: Like section 522 on Medusa, 523 on EAGLEPhilip [00:42:35]: YeahVibhu [00:42:36]: 524 on gram.Philip [00:42:37]: It's 55, would be disaggregationAli [00:42:42]: Yeah. Well, no, I just wanted to dwell a little bitPhilip [00:42:44]: YeahAli [00:42:44]: The other. Like, so what do you choose to include? What do you choose to not to include? Because there was all these other techniques.Philip [00:42:51]: Yeah.Ali [00:42:51]: Are these still relevant? Because I think they came out, like, a year and a half ago maybe.Vibhu [00:42:55]: Medusa is quite old.Philip [00:42:56]: Yeah, Medusa's old.Ali [00:42:58]: It was old.Vibhu [00:42:58]: But is it in the book as a good, here'sPhilip [00:43:01]: BaselineVibhu [00:43:01]: Baseline vanilla understand it?Philip [00:43:02]: Like you should know this.Vibhu [00:43:03]: Like I read the paper, I'm like, “ it makes so much sense.”Philip [00:43:05]: Yeah.Philip [00:43:05]: So with the book, I had a couple goals. One was to give people just a working vocabulary for the space as a whole, and the other was to give them some intuition about how each of these techniques works. As I mentioned in my AI Engineer talk, which is the first public addendum to this, the speculation space has moved much faster than everything else. So yeah, even at the time that I wrote the book Medusa, I very much included as a way for people to understand how the space evolved rather than what the most modern technique is. And now of course, there's DFlash, dSpark. There's, there's newer techniques even than EAGLE, although EAGLE is still very commonly used.Ali [00:43:51]: SpecSpecta.Philip [00:43:52]: Yes. Speculative decoding.Vibhu [00:43:54]: What canAli [00:43:56]: Oh, it's a paper by Tri Dao and it's like, it's doing speculative decodingVibhu [00:44:00]: HuhAli [00:44:01]: For the speculative decoder.Philip [00:44:02]: Oh, in spec- oh my God.Ali [00:44:02]: It's literally just an another. It's like, yeah, that's the most simple way to explain it, and it seems like he got trivial speed ups there. But it seems that the complexity with training, it's almost like in our mind at least, it's almost as complex as training GANs. Like it's like a very delicate balance and oftentimes you, it's just but yeah, it's literally speculative decoding on speculative decoding.Vibhu [00:44:21]: Speculative.Ali [00:44:22]: Yeah. We saw this paper.Vibhu [00:44:24]: It's interesting, right?Ali [00:44:24]: Yeah.Vibhu [00:44:24]: I wouldn't even expect it to be very particular to train, I wouldAli [00:44:29]: Right.Vibhu [00:44:29]: The naive part of me is like, okay, train speculative decoder.Ali [00:44:32]: But like, and it makes sense, like the whole idea of speculative decoding is you. It's like, it's like almost like the iPhone auto predict version but for a normal model, right? Like you're just, you're just, generating three tokens and you're like, okay, I'll do prefill on them. And so you save those three turns for your original model. Now your speculative decoder is doing three turns of auto regression, so why not just have an even smaller model?Ali [00:44:53]: The other question there is what are the size of speculators? So say forPhilip [00:44:58]: Right. It's like a billion parameters.Ali [00:45:01]: Like for MiniMax, it's. Yeah. It's like one layer. It's like one 60th of the original model usually.Philip [00:45:06]: Yeah. I think we should do a paper when we get back to the office.Philip [00:45:10]: SpeculativeAli [00:45:11]: SpeculativePhilip [00:45:11]: Decoding.Ali [00:45:13]: No, it's, it does seem like how, when do you stop? But then it also seems like if you're able to train spec-spec decode for instance, right? Like if you're able to have a small model that is accurately predicts what the intermediate speculator is gonna predict, that is able to predict what the original target model's gonna predict, then why not just use that smallest model directly, right?Vibhu [00:45:34]: Yeah. This isAli [00:45:35]: Like it seems likeVibhu [00:45:35]: Adjacent to the routing problem.Ali [00:45:36]: Right.Vibhu [00:45:36]: Yeah.Ali [00:45:36]: Right.Philip [00:45:37]: The thing with speculators is one of the practical constraints on using them is that you do have to run a small model on the same hardware that you're running the big model on. There is a orchestration and resource competition problem inherent in that, and that is one of the constraints on speculation in general, is that draft tokens cost resources to create and cost software complexity to manage. And so if you have like infinitely recursive speculators, you add in quite a bit of that complexity on the actual implementation within the inference engine as well, not just in the training process.Vibhu [00:46:17]: I was gonna say, I would wonder if you could do similar, like distillation and pruning of, it's the same thing, it's just a model. Can we not just distill a lot of the weights, quantize the speculator, out of my domain? The question that also comes up is, this is all for big server workloads, right? How much of this applies to, say I have this MacBook, I wanna run Gemma really efficiently. Similar problems, not the same?Local AI vs. Data Center InferencePhilip [00:46:45]: Pretty different. I talked to Selo, about this on his podcast a couple weeks ago. The difference between inference engineering for the data center and for production workloads versus inference engineering for local AI, is that we start with fundamentally like different constraints and different goals. With local AI, it's how do I fit this model onto my hardware and then make it less dumb? And with data center influence, it's how do I load this model and then make it less slow? And we care about less dumb, and they care about less slow. But the local AI inference engineering ecosystem, I think has a lot for us to learn from in the data center space. They are experts in various forms of quantization, including dynamic quantization that we just don't touch, in the pruning, in the distillation, in the, layer removal. There'Ali [00:47:42]: Layer removal matters less.Philip [00:47:43]: Yeah. There'Ali [00:47:44]: No one loves pruning really.Philip [00:47:45]: Yeah. Well, but the, but they doVibhu [00:47:46]: Which is surprising, right? But that's, that's a whole different thingPhilip [00:47:48]: Just to fit something on the laptop.Ali [00:47:50]: Right.Philip [00:47:50]: So yeah, it's a, it's an interesting, it's an interesting space. Not necessarily that like their techniques make sense for us to do in the data center, because we have different resources and different goals, but more that the process as well as the openness of that field is something to, admire.Ali [00:48:12]: Yeah. Like to your point, like, certain optimizations that would. Like for instance, Turbo Quantum Sharper, like it made such huge hype on that and we did like a whole deep dive on Twitter and like said, what is it? How does it work? Why is it good or not? And it took off and it was implemented on local devices because your memory bandwidth is so slow on like a MacBook, for instance. But try putting the same thing on like an NVIDIA GPU on a B200 Turbo quant would not be. Like, it would not be used. Like, NVIDIA - Like, NVIDIA made it clear that this is not a good optimization, and we've seen it firsthand where the overhead of doing dequantization, quantization of, in the kernel itself with turbo quant kernel, each end is much slower than the time that you save from doing the bandwidth. ‘Cause on the B200s, you have like 3.5 terabytes per second. You don't need decrease the storage that much. You don't need to do, FP4 KV cache. You don't need to use a requant. There's, there's, there's better optimizations to be made. But on Edge devices, it's extremely important, it's extremely useful. So, seems to be, like, different optimizations there, but then they're all uniquely combined with like all you wanna quantize the model, you wanna do speculative decoding, like certain common prefixes with bothPhilip [00:49:18]: Principles.Ali [00:49:19]: Yeah, exactly. Exactly. Exactly.Philip [00:49:20]: They also do a lot of work on, model parallelism, especially over, heterogeneous topology, where you have, some sparks and they are wired together with, Ethernet, DGX sparks.Ali [00:49:35]: Yeah, this is the Exo Labs guys.Philip [00:49:36]: Yeah. You have, a nu

Sydney Marathon 2026 Survival Guide: Everything You Need to Know Before Race Day | Women's Running Collective This week on the Women's Running Collective, Hayles and Jussie are getting excited because Sydney Marathon is almost here! Whether you're tackling your first marathon or chasing a shiny new PB, this episode is your ultimate race week survival guide. Before diving into all things Sydney Marathon, the girls catch up on recent racing, training and share a few very honest (and very funny!) stories about the glamorous realities of being female runners, including pelvic floors, Harbour 10 mishaps and why carrying spare shorts might not be the worst idea. From there, they break down everything you need to know before marathon weekend. They cover the course, start times, aid stations, pacers, race morning logistics, the expo, carb loading, transport, bag drop, sustainability initiatives and the brand-new Motion Festival taking over Circular Quay. If you're feeling nervous, excited, overwhelmed, or all three....this episode is packed with practical advice to help you feel calm, prepared and ready to enjoy one of the most iconic marathons in the world. This episode is proudly sponsored by ASICS and the new GEL-KAYANO™ 33 the shoe designed to deliver soft, stable comfort on every run. Timestamps 00:00 – ASICS Sponsor Shoutout 00:34 – Podcast Catch-Up & Banter 01:18 – Race Day TMI Stories (Yes… we went there

All the Chicks are finally back together! In today's episode, Rachel shares an update on her injury recovery, the mental challenges of being sidelined, and how she's basically become a full-time swimmer. Megan is thriving in marathon training, discovering the joy of stroller runs with her daughter, and finally feeling like herself again after a breakthrough workout. Karen is back on the track after her own injury setback and learning the value of holding back even when you're feeling strong.Plus, the Chicks dive into a new study showing that men are nearly twice as likely as women to "hit the wall" in the marathon. They break down the science and some of their thoughts.They also answer a listener question about being ghosted by an "inclusive" run club, and debate what makes someone look like a serious runner (Garmin vs. Apple Watch, spikes vs. super shoes, gels vs. chews)._________________Find this week's Zappos recs here:Megan: Saucony Triumph 23Karen: Hoka Cielo X1 2.0Rachel: Eberjay Frida - The Whip Stitch Cami and Shorts Set_________________SUPPORT OUR SPONSORZappos is an online retail destination for the best in footwear, offering the selection and expertise runners need to take on each day with confidence. Zappos carries an extensive assortment of performance running shoes, including leading brands like HOKA, Nike, Brooks, New Balance, ASICS, On, and more. ⁠⁠⁠⁠⁠⁠⁠⁠⁠Check out the latest selection on footwear on Zappos.com or in the Zappos app. ⁠⁠⁠⁠⁠⁠⁠⁠⁠_________________CHICK CHAT– Send us your questions at ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠gettingchickedpodcast@gmail.com⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ or DM us on Instagram at ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@gettingchicked⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠YOUR HOSTS– Karen Lesiewicz | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@kare_les on Instagram⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– Rachel DaDamio | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@rdadamio on X⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– Megan Connelly | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@meganmorantwwe on Instagram⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠FOLLOW OUR SHOW– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Subscribe on Apple Podcasts here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow on Spotify here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow the show on Instagram here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

Alex, Reese, and Taylor talk about what they are obsessed with in the month of July. Everything from minivans, to horses, to stack heights was fair game. They wrap up their conversations with early imperessions of the upcoming Asics Metafuji Trail 2.Guest: Reese chats with Dr. Jason Tso and Malene Lindholm who are conducting a study at Stanford that's focused on common genetic markers for endurance performance.SUPPORT OUR SPONSORS:Näak Nutrition: The Drop Listeners can get 15% off any Näak products by using code BITR15. Näak is a nutrition brand the leverages natural ingredients and research backed formulas to help athletes perform. They have a host of products like gels, drink, mixes, broths, bars, and recovery fuel. Their highest performance Boost line doubles down on the carbs for high-performance fuel that's also gut-friendly. Go to http://naak.com to explore and purchase.Lagoon: Sleep is one of the most underrated training components. We've been fans of Lagoon for years and use their custom pillows nightly to support a great night of sleep and, of course, our running. Go to http://lagoonsleep.com/believe to take a quick quiz to find the best pillow for you. Get 15% off your purchase by using code BELIEVE

En este programa te traigo una charla con Edu Merino, técnico de producto de Asics grabada el 2 de junio de 2026, y que no he publicado antes a causa de las fechas de embargo.Hablamos de: -Metafuji Trail 2, el modelo de competición con placa de carbono y 250€ que cambia por completo respecto a su primera versión.-Fuji Lite 7, una versión continuista en suela y mediasuela que recibe un upper mucho más alineado con el resto de la zapatilla. 150€-Blazeblast, el modelo de gravel que no existía en el catálogo de Asics, si bien es cierto que habían modelos "TR" que de alguna manera, suplían esa carencia hasta ahora.Contacto:juan@ellaboratoriodejuan.com

This week on Fuel for the Sole, we tackle several listener questions. We get into how much water you actually need each day — and whether you might be overdoing it. We're digging into what's behind those post-run headaches and what you can do to prevent them. We're talking race day logistics — how to carry all your hydration and nutrition when it counts most. And finally, gummies versus powders — do collagen and creatine gummies actually deliver the same results? Want to be featured on the show? Email us (written or an audio file!) at⁠ fuelforthesolepodcast@gmail.com⁠. This episode is fueled by ASICS and RNWY!Head over to⁠ ASICS.com⁠ and sign up for a OneASICS account. It's completely free and when you sign up you will receive 10% off your first purchase. You also gain access to exclusive colorways on ASICS.com, free standard shipping, special birthday month discounts and more.RNWY Complete Protein is a post-run recovery shake we genuinely stand behind. Here's why: built on YESTEIN®, a fermented yeast protein that scores a PDCAAS of 1.0, which is the highest possible protein quality rating. That puts it in the same category as whey but without any of the dairy. Every serving gives you 25 grams of complete protein containing all nine essential amino acids plus 5 grams of creatine monohydrate and a five-enzyme digestive complex. Get yours at https://rnwy.life/ and use code FEATHERS15 for 15% off your purchase. Disclaimer: This content is not intended to be a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of your physician or other qualified health provider with any questions you may have regarding a medical condition.

Leo Fan breaks down why the real bottleneck in AI isn't model intelligence but a persistent GPU shortage driving up inference costs, even as open-source models from China close the gap. He also unpacks the financialization of compute and why some believe it could become one of the largest derivatives markets in the world.Leo Fan is the Founder of Cysic, a full-stack compute network turning GPUs, ASICs, and spare hardware into verifiable AI infrastructure, and a Cornell CS PhD researcher in zero-knowledge systems and AI.The Rollup is where the leaders of digital assets and finance converge. Live from the financial capital of the world.Timestamps00:00 Intro04:18 Kimi K2 Shocks Compute Demand06:39 GPU Shortage Drives Inference Costs11:34 Engineering Around Chip Gaps18:23 Compute Financialization20:48 Earning Yield From Spare Compute23:20 Compute Markets FutureGuest Socials:Leo Fan X: https://x.com/leofanxiongCysic X: https://x.com/cysic_xyzCysic Website: https://cysic.xyz/ Partners: Better than Banks. Transparent capital efficiency earning the highest yields in DeFi. Learn more here: https://infinifi.xyz/---1inch - Simple experience. Smart execution. Trading built to scale. It's time to bring the world onchain. https://1inch.com/---Dinari - Over 230 1:1 backed tokenized stocks, ETFs & more with dividends. US-based SEC transfer agent. Available on 5+ chains & via API. https://dinari.com/---Relay is the fastest and most reliable way to swap any token on any chain. Learn more here: https://relay.link/bridge---Zama is an open source cryptography company that builds state-of-the-art Fully Homomorphic Encryption (FHE) solutions for blockchain.Learn more here: https://www.zama.org/---Trezor is the creator of the first-ever hardware wallet. Securing crypto for 2M+ users worldwide. 100% open source. Learn more here: https://affil.trezor.io/aff_c?offer_i...---

Plus, American Express posted higher second quarter profit and sales thanks to higher card member spending. And Nike is giving up its share of the lifestyle sneaker marker to refocus on running shoes. Alex Ossola hosts. Sign up for WSJ's free What's News newsletter. An artificial-intelligence tool assisted in the making of this episode by creating summaries that were based on Wall Street Journal reporting and reviewed and adapted by an editor. Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

Tommie Runz started running in 2018, a year after choosing sobriety, and began documenting the journey simply because it felt good to share progress and get encouragement. Seven years later, he's built an audience of over 30,000 through nothing but consistency and honesty — no viral moments, no big follower jumps, just a steady climb built entirely on trust. In this conversation, Tommie and Aaron pick up where they left off after a live panel at TrailCon, digging into what it actually looks like to build a career as an athlete-creator without compromising who you are. Tommie breaks down why he's turned down "ambassador" deals that undervalue creators, how relationships with brands often take years rather than emails to develop, and the moment he realized his content needed to sound exactly like him or it wasn't worth doing at all. Second Nature is supported by Popfly: Popfly for Creators: https://popf.ly/secondnaturecreators Popfly for Brands: https://popf.ly/secondnaturebrands Show Notes: Tommie Runz: https://www.tommierunz.com/ Tommie on Instagram: https://www.instagram.com/Tommie_Runz Tommie on YouTube: https://www.youtube.com/@Tommie_Runz PR Project (Podcast): https://www.youtube.com/c/PRProject/videos Asics: https://www.asics.com/ Mack Baker (Asics): https://www.linkedin.com/in/mack-baker-b6218717/ Cosign Creatives: https://cosignmag.com/cosign-creative-agency/ Tommie Runz Show (Podcast): https://podcasts.apple.com/us/podcast/the-tommie-runz-show/id1538233660 Broken Arrow: https://www.brokenarrowskyrace.com/ Tommie on Freetrail: https://www.youtube.com/watch?v=q7lJd4t12a8 TrailCon: https://www.trailconference.com BPC - Brand, Product, Content: Currently: https://currentlyrunning.com/ Best Running Podcasts: https://bestrunningpodcasts.com/ Precision Fuel & Hydration: https://www.precisionhydration.com/ Aaronnomics: https://www.instagram.com/aaronnomics/ Join us on LinkedIn: https://www.linkedin.com/company/second-nature-media Meet us on Slack: https://www.launchpass.com/second-nature Follow us on Instagram: https://www.instagram.com/secondnature.media Subscribe to our newsletter: https://www.secondnature.media Subscribe to the YouTube channel: https://www.youtube.com/@secondnaturemedia

AI is no longer just a race to train smarter models. As AI moves into production, the bottleneck is increasingly inference: how fast models can generate tokens, use tools, reason, verify, and act. In this episode of the MAD Podcast, Matt Turck sits down with Andrew Feldman, co-founder and CEO of Cerebras, to explain why fast inference may define the next era of AI.Cerebras is known for building a chip the size of a silicon wafer. But this conversation is not just about one company or one chip. It is a deep dive into the AI infrastructure stack: GPUs, ASICs, memory, HBM, SRAM, data centers, power, TSMC, AWS, OpenAI, agents, reasoning models, and why speed changes what AI products can become. Andrew explains why “tokens per second per user” matters, why generating a single word can require moving the equivalent of 100 HD movies through memory, why agents amplify latency, why GPUs struggle with certain inference workloads, and why fast AI may eventually reshape SaaS itself.This is a reference conversation on fast inference, AI chips, and the next compute bottleneck.(00:00) Cold open & Intro(01:31) Why speed became the AI bottleneck(02:32) Tokens per second per user, explained(03:16) AI's broadband moment and the Netflix analogy(04:35) The AI chip landscape: GPUs, TPUs, Trainium, ASICs(06:36) What is an ASIC?(08:08) Nvidia, Groq, and the fast inference war(09:16) OpenAI, Broadcom, and specialized silicon(12:10) China, power, and sovereign AI infrastructure(15:05) Is the AI infrastructure boom a bubble?(18:56) The hidden bottlenecks: HBM, CoWoS, and 3nm(22:57) Why agents are creating CPU demand(25:36) Andrew Feldman's path from SeaMicro to Cerebras(26:13) Why Cerebras bet on AI in 2016(31:14) SRAM vs. HBM: why inference is a memory problem(33:19) What wafer-scale computing actually means(34:28) The deep-tech “Everest” problem(36:07) The moment the first Cerebras system worked(36:49) Ringing the bell and surviving deep tech(39:08) How a giant chip handles failure(41:22) Why GPUs struggle with decode(42:17) Prefill vs. decode explained(44:01) The “100 HD movies” problem in AI inference(45:04) How fast inference changes RL and training(48:08) Reasoning models and why they cost more compute(50:08) Verification, guardrails, and small models checking big models(52:37) Multimodal AI and the path to video(53:51) Cerebras' business model: hardware, cloud, and API(55:14) OpenAI's 750MW inference deal(55:36) Why data centers are measured in megawatts(58:01) AWS Trainium + Cerebras decode(59:29) Fast tokens as a cloud product(01:00:52) Is CUDA still a moat?(01:03:53) How TSMC helped Cerebras build the giant chip(01:07:41) Why nobody cared in 2020(01:08:15) Why chip supply chains are hard to diversify(01:09:54) Why today's AI models will be the worst you ever use(01:10:38) What fast AI could do to SaaS

In today's episode, Megan and Karen dive into one of the biggest moments in running history. They unpack Josh Kerr's mile world record, why his confidence paid off, and what makes the mile such a universally beloved event.Megan also shares stories from an action-packed weekend at Fanatics Fest, including judging WWE superstar entrances, seeing Noah Lyles compete, and unexpectedly meeting Justin Bieber. Karen celebrates a milestone with her iron levels, reflects on attending a race she was originally supposed to run, and the two discuss how to adapt marathon training when life gets hectic.Plus: post-marathon shoe recommendations, ideal workout schedules, Justin Bieber nostalgia, and why sometimes running less is actually the smartest training decision._________________Find this week's Zappos recs here:Megan: Nike Pegasus 41Karen: Hoka Clifton 11_________________SUPPORT OUR SPONSORZappos is an online retail destination for the best in footwear, offering the selection and expertise runners need to take on each day with confidence. Zappos carries an extensive assortment of performance running shoes, including leading brands like HOKA, Nike, Brooks, New Balance, ASICS, On, and more. ⁠⁠⁠⁠⁠⁠⁠⁠Check out the latest selection on footwear on Zappos.com or in the Zappos app. ⁠⁠⁠⁠⁠⁠⁠⁠_________________CHICK CHAT– Send us your questions at ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠gettingchickedpodcast@gmail.com⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ or DM us on Instagram at ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@gettingchicked⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠YOUR HOSTS– Karen Lesiewicz | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@kare_les on Instagram⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– Rachel DaDamio | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@rdadamio on X⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– Megan Connelly | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@meganmorantwwe on Instagram⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠FOLLOW OUR SHOW– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Subscribe on Apple Podcasts here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow on Spotify here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow the show on Instagram here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

Emma Grace Hurley talks about gaining confidence after finding success this season, Zaxby's signature sauce, excitement for her fall races, Asics running shoes, how gratitude allows her to have fun in the sport, what's on her music playlist, 2000's Disney TV, and more!Episode link in bio.If you're looking for the best nutritional product on the planet, look no further than Noogs! Use the discount code LacticAcid15, or use the link https://www.noogsnutrition.com/discount/LacticAcid15 Follow Emma Grace on IG: https://www.instagram.com/emmagracehurley/Be sure to follow Lactic Acid on the following platforms:  YouTube: Lactic Acid Podcast Twitter: Lacticacid_pod Instagram: Lacticacidpodcast Substack: LacticacidpodcastIf you're loving the show, please subscribe and leave a rating and review on Apple Podcasts, and share it with your friends and family!

Meia-Maratona de Jundiai - https://cnoar.run/MeiadeJundiai2026Use o cupom CORRIDANOAR10 para ter 10% de desconto na sua inscriçãoNeste episódio do CNA News, trazemos as novas datas e mudanças importantes da New Balance 42K de Porto Alegre. Além disso, comentamos sobre a Asics assumir o patrocínio da Maratona de Paris, os detalhes do percurso da inédita Meia Maratona de Jundiaí, a edição limitada do gel da Dobro em parceria com a Nike, as novas medalhas da Maratona de Aracaju e o comunicado oficial sobre os problemas enfrentados pelos corredores na Jipa City Marathon.- Introdução do programa (00:00:00)- Novas datas da New Balance 42K Porto Alegre (00:01:45)- Asics na Maratona de Paris (00:04:36)- Detalhes da Meia Maratona de Jundiaí (00:05:39)- Gel Dobro em parceria com a Nike (00:07:55)- As medalhas da Maratona de Aracaju (00:08:52)- Pronunciamento sobre as falhas da Jipa City Marathon e comentários da audiência (00:09:40)Nossos cupons e links - https://cnoar.run/cuponsO Corrida no Ar News é produzido diariamente.

How much do we really know about how our clothes and shoes are made? Or even where? While the latter is routinely included on care labels, that's often the end of the story, at least the one the brands want to tell you. Despite years of campaigning by groups like Fashion Revolution, Labour Behind the Label and Clean Clothes Campaign, many of us still have no idea who made our clothes and under what conditions.Did you even know the Philippines is an important garment producer for brands like Lulu Lemon, and until recently, Adidas? In 2023, when a factory in Cebu supplying Adidas closed, 4000 workers lost their jobs. How about the stories of union busting linked to factory in Cambodia that's a major supplier to ASICS? Or the closure of another facility in Vietnam making Nike shoes that left thousands of workers without severance pay?Niki Gamara is CCC's South East Asia Urgent Appeals Co-Ordinator, working with those needing quick support in areas where violations are happening. In this vivid, warm conversation we talk about everything from how the history of colonisation echoes in the present to what I should do with my sneakers now that I know more about what goes in behind the scenes...Find links and further reading at thewardrobecrisis.comSupport the show on Substack - wardrobecrisis.substack.comTell us what you think. Find Clare on Instagram @mrspress Hosted on Acast. See acast.com/privacy for more information.

Every firm competing for talent is saying the same things. Great culture. Exciting projects. Competitive benefits. And candidates can't tell any of you apart. That's the problem James Ellis has built a career solving. In this episode, James breaks down what employer brand actually is (hint: not a campaign, not a vibe, not a careers page redesign) and how midsized companies can build a brand that wins talent without outspending bigger competitors. We get into why most employer brand work is theater, what candidates actually believe about your firm, and how to change what recruiters say and hiring managers reinforce. This one is for AEC firm leaders, TA and HR professionals, and anyone tired of posting jobs into the void and wondering why the right people never apply. About James Ellis: James Ellis is the founder of Employer Brand Labs, where he builds choosable employer brands for mid-market companies in 3 to 5 weeks. He's built employer brands at Webflow, Roku, ASICS, and Telecare over more than 13 years, and he's the bestselling author of Becoming Choosable and Talent Chooses You. Based in Chicago, James describes his stage presence as equal parts strategist and friendly arsonist. Find him at employerbrandlabs.com and on LinkedIn at linkedin.com/in/thewarfortalent. What We Cover: Introduction and James's background building employer brands at Webflow, Roku, and ASICS Why most companies don't have a hiring problem, they have a differentiation problem What "employer brand theater" looks like and why it fails How midsized firms can compete for talent without outspending the giants What it means to be a "choosable" employer How employer brand shows up in job posts, outreach, career sites, and interviews Why you can rent attention but you can't rent trust Where to find James + closing thoughts Key Takeaways: Employer brand is a system, not a campaign. It changes what candidates believe, what recruiters say, and what hiring managers reinforce. If your job posts could belong to any of your competitors, candidates have no reason to choose you. Midsized firms win talent through clarity and differentiation, not budget. You can't scale a business faster than you can hire the right people. Employer brand work should be usable Monday morning, not next quarter. Resources + Links: Employer Brand Labs: https://www.employerbrandlabs.com James on LinkedIn: http://linkedin.com/in/thewarfortalent Newsletter: https://employerbrandheadlines.com Books, videos, podcasts, and articles: http://www.EB-AF.com Becoming Choosable and Talent Chooses You by James Ellis  

Big life updates in today's episode! Rachel shares her engagement story and everything that made the proposal so memorable, while Megan catches everyone up on her recent move, meeting a new training partner, and some of the races she has coming up on her schedule. The two also discuss track etiquette for newer runners, share their takes on running with sunglasses and whether or not you should race with a watch, and thoughts on evolving as a runner post-college.Plus: Tips on balancing training, work, and motherhood when time is limited._________________Find this week's Zappos recs here:Megan: Flynn 5050 Shield SunglassesRachel: Women's Vanquisher 2.0 Mirrored Goggles_________________SUPPORT OUR SPONSORZappos is an online retail destination for the best in footwear, offering the selection and expertise runners need to take on each day with confidence. Zappos carries an extensive assortment of performance running shoes, including leading brands like HOKA, Nike, Brooks, New Balance, ASICS, On, and more. ⁠⁠⁠⁠⁠⁠⁠Check out the latest selection on footwear on Zappos.com or in the Zappos app. ⁠⁠⁠⁠⁠⁠⁠_________________CHICK CHAT– Send us your questions at ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠gettingchickedpodcast@gmail.com⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ or DM us on Instagram at ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@gettingchicked⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠YOUR HOSTS– Karen Lesiewicz | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@kare_les on Instagram⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– Rachel DaDamio | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@rdadamio on X⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– Megan Connelly | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@meganmorantwwe on Instagram⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠FOLLOW OUR SHOW– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Subscribe on Apple Podcasts here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow on Spotify here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow the show on Instagram here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

This week on Fuel for the Sole, we're diving into broccoli juice shots — aka Nomio — since it's been all over our feeds lately. We also get into Lactate 60 gels and whether we should all be taking them, break down what actually qualifies as a heavy sweat race, and tackle the most important question of all: how do you fuel a Taco Bell 50K? Interested in Meghann's Group classes? Sign up here: https://www.featherstonenutrition.com/groupcoaching/ Want to be featured on the show? Email us (written or an audio file!) at⁠ fuelforthesolepodcast@gmail.com⁠. This episode is fueled by ASICS and RNWY!Head over to⁠ ASICS.com⁠ and sign up for a OneASICS account. It's completely free and when you sign up you will receive 10% off your first purchase. You also gain access to exclusive colorways on ASICS.com, free standard shipping, special birthday month discounts and more.RNWY Complete Protein is a post-run recovery shake we genuinely stand behind. Here's why: built on YESTEIN®, a fermented yeast protein that scores a PDCAAS of 1.0, which is thehighest possible protein quality rating. That puts it in the same category as whey but without anyof the dairy. Every serving gives you 25 grams of complete protein containing all nine essential amino acids plus 5 grams of creatine monohydrate and a five-enzyme digestive complex. Get yours at https://rnwy.life/ and use code FEATHERS15 for 15% off your purchase. Disclaimer: This content is not intended to be a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of your physician or other qualified health provider with any questions you may have regarding a medical condition.

For decades, the world's top soccer players laced up boots made from the skins of wild kangaroos. Manufacturers claimed kangaroo leather offered unmatched performance, and millions of kangaroos were commercially killed across Australia each year to supply the global athletic footwear industry. That story has changed dramatically. In this episode of the Animal Wellness Podcast, host Joseph Grove examines one of the most successful corporate animal-protection campaigns of recent years: the effort to eliminate kangaroo leather from elite soccer. Joining the program are Wayne Pacelle, president of the Center for a Humane Economy, and Ryan Luterman-Sevel, director of social media and the campaign's resident numbers guy. Ryan's detailed research tracked every player at the 2026 FIFA World Cup, documenting which boots they wore throughout the tournament. The results were striking. Just four years after kangaroo leather was already beginning to decline, only one player initially appeared to be wearing kangaroo-leather boots at the 2026 World Cup—and by the tournament's later rounds, even that player had switched to synthetic footwear. The conversation explores: Why kangaroo leather became the industry standard for elite soccer boots. How synthetic materials now outperform traditional leather in many respects. The six-year Kangaroos Are Not Shoes campaign and the strategy behind it. Why major brands including Nike, adidas, Puma, New Balance, ASICS, Mizuno and Diadora moved away from kangaroo leather. How consumer pressure, corporate engagement and legislative advocacy combined to change an entire marketplace. What the disappearance of kangaroo leather at the World Cup means for wildlife conservation and animal welfare. What lessons this campaign offers for future efforts to replace animal-derived products with humane alternatives. The episode also discusses the science of modern performance materials, the myths surrounding kangaroo leather, and how sustained advocacy can produce measurable, global change—even within industries long considered resistant to reform. Whether you're a soccer fan, an advocate for wildlife, or simply interested in how campaigns influence major corporations, this episode offers an inside look at how persistence, data and strategic advocacy helped transform one of the world's most recognizable sporting traditions. Guests Wayne Pacelle President, Center for a Humane Economy and Animal Wellness Action Ryan Luterman-Sevel Director of Social Media, Center for a Humane Economy and Animal Wellness Action Learn More Center for a Humane Economy Animal Wellness Action Kangaroos Are Not Shoes campaign Subscribe If you enjoyed this episode, please subscribe, leave a review, and share it with friends and colleagues. Your support helps us continue bringing you conversations about the people and campaigns advancing animal protection around the world. The Animal Wellness podcast is produced by Animal Wellness Action and the Center for a Humane Economy. It focuses on improving the lives of animals in the United States and abroad through legislation and by influencing businesses to create a more humane economy. The show is hosted by veteran journalist and animal-advocate Joseph Grove.    www.animalwellnessaction.org www.centerforahumaneeconomy.org   Facebook: https://www.facebook.com/AnimalWellnessAction Facebook: https://www.facebook.com/centerforahumaneeconomy/ Twitter: https://twitter.com/AWAction_News Twitter: https://twitter.com/TheHumaneCenter   Instagram: https://www.instagram.com/animalwellnessaction/ Instagram: https://www.instagram.com/centerforahumaneeconomy/ LinkedIn: https://www.linkedin.com/company/animal-wellness-action/    YouTube: https://www.youtube.com/channel/UCI_6FxM4hD6oS5VSUwsCnNQ 

Meet your new Australian Record holder in the marathon!!!! Haftu Strintzos ran 2:06:20 on the Gold Coast last Sunday to break Andy Buchanan's previous record by two seconds. In case you missed it, this episode recorded in 2025 is essential listening and gives context to Haftu's incredible result over the weekend.  -- Haftu Strintzos spent the first years of his life as a shepherd in mountainous Tigray in northern Ethiopia. He cared for sheep and cows and played hopscotch (the Tigrayan version) with the other shepherds. Now an Asics-sponsored athlete, with his sights on representing Australia in the marathon, Haftu has the most incredible story brimming with resilience and perspective. But to understand how he got from A to B, you'll just have to listen to this episode. Haftu talks about some defining moments of his athletic career so far, including running for Villanova University in the US, finishing first Australian across the line at the World Athletics Cross Country Championships in Serbia, winning the 10,000m at the 2024 Oceania Athletics Championships and achieving silver in the 5,000m. After his half marathon debut in Melbourne last year (62:24), Haftu followed up with a blinder in Marugame in Japan, where he ran 60:36 and asserted himself as a real contender on the roads. Unfortunately, Haftu's marathon debut was foiled by an injury that popped up just before Hamburg Marathon earlier this year. We discuss how he's dealing with that injury setback, how training has changed since he transitioned to Adam Didyk's Team Tempo and what Haftu's big goals for the future look like. -- Run With It acknowledges the Wadawurrung People, the Traditional Owners of the land on which this podcast is recorded, and pays our respects to Elders past and present. -- Follow us on Instagram: @haftustrintz @runwithit.pod @elisebeacom -- Intro/outro music by Dan Beacom Graphic design by Kate Scheer

Welcome back to another episode of Private Conversations! This week on Private Conversations, we're breaking down the biggest upcoming sneaker releases and why Nike may be losing its grip on the sneaker industry. We dive into how brands like New Balance, ASICS, HOKA, On-Cloud, and Solomon are gaining momentum while Nike shifted away from major retailers in favor of a direct-to-consumer strategy.  We also put Gilberto's viral Birria Balls and Hot Cheetos Burritos to the test, tell some unforgettable Kanye West concert and SXSW stories, and Larry delivers an all-time rant about Pokémon fans, scalpers, and why people keep accusing sneaker stores of ruining the hobby. In this episode we discuss: • The hottest upcoming sneaker releases • Is Nike losing the sneaker war? • Why running brands are dominating right now • Kanye West concert memories & SXSW stories • Trying Gilberto's viral Birria Balls & Hot Cheetos Burritos • Larry vs. Pokémon fans • Sneakers, food, stories, and plenty of chaos   New episodes every week.   SUBSCRIBE TO THE CHANNEL ► https://www.youtube.com/@prvt.selection   LISTEN ON: APPLE PODCASTS: https://podcasts.apple.com/us/podcast/private-conversations/id1641605422?ign-itscg=30200S&ign-itsct=podcast_box_promote_link SPOTIFY: https://open.spotify.com/show/5wnDrQiUCPcUErprdaBX2b  ALL PLATFORMS: https://linktr.ee/PrivateSelection   ADD US ON INSTAGRAM: https://www.instagram.com/prvt.selection/   ALL OF OUR SOCIALS: https://linktr.ee/PrivateSelection Follow the Hosts: Ian (@masterchefian) Full Fit Larry (@fullfitlarry) Scotty (@beammmeupscotty) _________________________________________________________________ #PrivateConversations #Sneakers #Streetwear #Podcast

Marvell (NASDAQ: MRVL) stock has surged since Jensen Huang called it the next trillion-dollar company — we ran a reverse DCF on the Q1 FY2027 earnings to see if the rally is justified.Marvell just posted record Q1 fiscal 2027 results, with revenue up 28% year-over-year to $2.4 billion and guidance pointing to 35% growth next quarter. As a fabless chip designer and IP licenser, Marvell is riding two major tailwinds: hyperscaler demand for custom AI chips (ASICs and XPUs) and networking systems that interconnect GPUs across data centers, including a growing partnership with NVIDIA via NVLink.We break down the earnings report, the CFO transition to Dan Durn (formerly of Adobe and Applied Materials), the balance sheet impact of the Celestial AI acquisition, and rising share dilution from recent deals. Then we run a reverse discounted cash flow analysis on Marvell at its current price to determine what growth rate is already priced in, and whether the semiconductor cycle and AI infrastructure buildout can realistically support it.If you're weighing whether Marvell is still a buy after this rally, or looking for better value elsewhere in the semiconductor supply chain, this one's for you.Semi Insider members get access to our full research platform and tools, plus deeper research as it happens. Join at chipstockinvestor.com.Get 15% off your Fiscal.ai membership with our link: fiscal.ai/csiContent in this video is for general information or entertainment only and is not specific or individual investment advice. Forecasts and information presented may not develop as predicted and there is no guarantee any strategies presented will be successful. All investing involves risk, and you could lose some or all of your principal.CSI doesn't own shares of Marvell.

In today's episode, Karen, Megan, and Rachel catch up on all things training, injuries, and life lately before diving into a round of listener questions.Rachel shares how she's added swimming into her recovery from injury and why she's unexpectedly fallen in love with it. Megan gives an update on the chaos of moving and how she's balancing it with the rest of her life. The Chicks also chat about the importance of taking rest days and break down a recent study on minimum mileage recommended to successfully run a marathon and how cross training can help make up for lower running volume.Plus, they answer your questions, including:- Spring/summer marathons to target if you're racing CIM (or another fall/winter marathon)- How to find a running coach who's the right fit_________________Find this week's Zappos recs here:Megan: Saucony Endorphin Pro 4Karen:⁠ Crocs Brooklyn Low WedgesRachel: Nike Bold Color Block V-Back One Piece_________________SUPPORT OUR SPONSORZappos is an online retail destination for the best in footwear, offering the selection and expertise runners need to take on each day with confidence. Zappos carries an extensive assortment of performance running shoes, including leading brands like HOKA, Nike, Brooks, New Balance, ASICS, On, and more. ⁠⁠⁠⁠⁠⁠Check out the latest selection on footwear on Zappos.com or in the Zappos app. ⁠⁠⁠⁠⁠⁠_________________CHICK CHAT– Send us your questions at ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠gettingchickedpodcast@gmail.com⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ or DM us on Instagram at ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@gettingchicked⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠YOUR HOSTS– Karen Lesiewicz | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@kare_les on Instagram⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– Rachel DaDamio | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@rdadamio on X⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– Megan Connelly | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@meganmorantwwe on Instagram⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠FOLLOW OUR SHOW– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Subscribe on Apple Podcasts here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow on Spotify here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow the show on Instagram here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

Marty sits down with Tyler Stevens and Dylan Seib to discuss their playbook for integrating Bitcoin miners into home and commercial heating systems, monetizing excess solar instead of selling it back to the grid, and building open source control systems that turn industrial ASICs into useful home appliances. Download The Home Mining Playbook here: https://www.tftc.io/home-mining-energy-playbook Tyler on X: https://x.com/tylerkstevens Dylan on X: https://x.com/tronsington Exergy: https://exergyheat.com/ STACK SATS hat: https://tftcmerch.io/ Our newsletter: https://www.tftc.io/bitcoin-brief/ TFTC Elite (Ad-free & Discord): https://www.tftc.io/#/portal/signup/ Discord: https://discord.gg/yHGkvYxdqT Opportunity Cost Extension: https://www.opportunitycost.app/ Shoutout to our sponsors: Bitkey https://bitkey.world/ Aven https://www.aven.com/bitcoin CrowdHealth https://www.joincrowdhealth.com/tftc Unchained https://unchained.com/tftc/ Lygos https://lygos.finance/ Salt of the Earth: https://drinksote.com/tftc Join the TFTC Movement: Main YT Channel https://www.youtube.com/c/TFTC21/videos Clips YT Channel https://www.youtube.com/channel/UCUQcW3jxfQfEUS8kqR5pJtQ Website https://tftc.io/ Newsletter tftc.io/bitcoin-brief/ Twitter https://twitter.com/tftc21 Instagram https://www.instagram.com/tftc.io/ Nostr https://primal.net/tftc Follow Marty Bent: Twitter https://twitter.com/martybent Nostr https://primal.net/martybent Newsletter https://tftc.io/martys-bent/ Podcast https://www.tftc.io/tag/podcasts/

This week on Fuel for the Sole, we're diving into your questions. Is potassium something you actually need to supplement - and if so, how? Does cooking with protein powder destroy its effectiveness? What should your Vitamin D levels really look like? And as temperatures start climbing, we're tackling rapid fire hydration questions you need heading into summer. Consider this your warm-weather episode. See also: Hydration Maxxing.Interested in Meghann's Group classes? Sign up here: https://www.featherstonenutrition.com/groupcoaching/ Want to be featured on the show? Email us (written or an audio file!) at⁠ fuelforthesolepodcast@gmail.com⁠. This episode is fueled by ASICS and RNWY!Head over to⁠ ASICS.com⁠ and sign up for a OneASICS account. It's completely free and when you sign up you will receive 10% off your first purchase. You also gain access to exclusive colorways on ASICS.com, free standard shipping, special birthday month discounts and more. RNWY Complete Protein is a post-run recovery shake we genuinely stand behind. Here's why: built on YESTEIN®, a fermented yeast protein that scores a PDCAAS of 1.0, which is the highest possible protein quality rating. That puts it in the same category as whey but without any of the dairy. Every serving gives you 25 grams of complete protein containing all nine essential amino acids plus 5 grams of creatine monohydrate and a five-enzyme digestive complex. Get yours at https://rnwy.life/ and use code FEATHERS15 for 15% off your purchase. Disclaimer: This content is not intended to be a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of your physician or other qualified health provider with any questions you may have regarding a medical condition.

We're back with our recaps from race weekend in Duluth! The guys had a blast in the North Country and they share their best memories, the highs and lows of race day, and learnings for the next marathon. Thanks to ASICS and Columbus Running Company for supporting our Road to Grandma's Marathon series! Have you enjoyed our spring marathon training diary? Please consider leaving a 5-star review on Spotify / Apple Podcasts secondsflatpodcast@gmail.com columbusrunning.com

In today's episode, Karen and Rachel break down the London Marathon's announcement that it will expand to a two-day event beginning in 2027. They discuss the new format, what it could mean for the race and its participants, and share their thoughts on the major change. Karen also talks about buying a road bike and diving into the world of cycling, while Rachel shares an update on her injury recovery. Plus, the Chicks share their favorite marathon spectating tips and explain how to cheer for more than one pro when your favorites are all racing at the same time._________________Find this week's Zappos recs here:Karen:⁠ Nike Pegasus 41Rachel: Feetures Elite Ultra Light Tab Socks_________________SUPPORT OUR SPONSORZappos is an online retail destination for the best in footwear, offering the selection and expertise runners need to take on each day with confidence. Zappos carries an extensive assortment of performance running shoes, including leading brands like HOKA, Nike, Brooks, New Balance, ASICS, On, and more. ⁠⁠⁠⁠⁠Check out the latest selection on footwear on Zappos.com or in the Zappos app. ⁠⁠⁠⁠⁠_________________CHICK CHAT– Send us your questions at ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠gettingchickedpodcast@gmail.com⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ or DM us on Instagram at ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@gettingchicked⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠YOUR HOSTS– Karen Lesiewicz | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@kare_les on Instagram⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– Rachel DaDamio | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@rdadamio on X⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– Megan Connelly | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@meganmorantwwe on Instagram⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠FOLLOW OUR SHOW– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Subscribe on Apple Podcasts here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow on Spotify here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow the show on Instagram here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

In this episode, we sat down with Skot and Ryan to unpack Ryan's trip to BTC++ Nairobi, where he represented the 256 Foundation and shared our open-source mining mission with builders from across Africa. Ryan talked about the incredible energy of the local Bitcoin community, the real-world use of Lightning and mobile payments across borders, and why Africa offers such a powerful glimpse into Bitcoin's practical value. We also dug into the strong interest in open-source mining, from Ryan's main-stage talk on the 256 Foundation's mining stack to the many conversations he had with developers excited to contribute, experiment, and build without the barriers of closed hardware and firmware.We also went deep on Ryan's hands-on mining workshop, where attendees learned Bitcoin mining from first principles, CPU-mined on a classroom Signet, assembled Bitaxes, and watched the network shift as ASICs came online. From there, we explored what Ryan saw at Gridless's biomass-powered mining site in Kenya, the technical realities of balancing power generation with mining load, and promising local projects like BitShaka and Juakali. Throughout the conversation, one theme kept coming up: open-source mining is becoming a practical path for education, experimentation, decentralization, and entirely new energy use cases—and the momentum behind Mugena and the broader 256 Foundation mission is clearly growing.

{ "@context": "https://schema.org", "@graph": [ { "@type": "PodcastEpisode", "name": "The Nike Cautionary Tale: What Happens When Leadership Loses Touch With Its Customers", "description": "Tom Dupree and analyst Michael Dawahare examine Nike's dramatic decline — from dominant global brand to a stock trading near 10-year lows — and draw clear parallels to retirement portfolio management.", "url": "https://dupreefinancial.com/blog/nike-cautionary-tale-leadership-lessons-retirement-investing", "datePublished": "2025-06-11", "inLanguage": "en-US", "partOfSeries": { "@type": "PodcastSeries", "name": "The Tom Dupree Show", "url": "https://dupreefinancial.com" }, "author": { "@type": "Person", "name": "Tom Dupree" }, "publisher": { "@type": "Organization", "name": "Dupree Financial Group", "url": "https://dupreefinancial.com", "telephone": "859-233-0400", "address": { "@type": "PostalAddress", "addressLocality": "Lexington", "addressRegion": "KY", "addressCountry": "US" } } }, { "@type": "FAQPage", "mainEntity": [ { "@type": "Question", "name": "What caused Nike's stock to fall from $180 to around $44?", "acceptedAnswer": { "@type": "Answer", "text": "Nike's decline was driven primarily by a strategic pivot under CEO John Donahoe, who took over in 2020 and aggressively reduced the company's reliance on wholesale partners like Foot Locker and specialty running stores in favor of a direct-to-consumer digital model. This freed up shelf space for competitors like HOKA and On Cloud, whose products consumers tried, preferred, and stayed with. Nike also took its eye off technical product innovation — the foundation of the brand — and the combination proved very difficult to reverse." } }, { "@type": "Question", "name": "What leadership lessons can retirement investors take from Nike's decline?", "acceptedAnswer": { "@type": "Answer", "text": "The Nike story illustrates several principles that apply directly to managing retirement assets: proven strategies should not be abandoned in favor of untested new models; losing touch with core fundamentals — in business or in a portfolio — creates compounding damage over time; and when someone tells you the old approach is outdated, the right question is always whether the new approach has been tested and who benefits from your belief in it." } }, { "@type": "Question", "name": "Why did Nike's wholesale withdrawal strategy fail?", "acceptedAnswer": { "@type": "Answer", "text": "Nike believed consumers would migrate online and that eliminating wholesale intermediaries would improve margins. What actually happened was that the vacated shelf space went to competitors — HOKA, On Cloud, New Balance, ASICS, and Brooks — who used it to earn consumer loyalty. Once runners found a shoe they loved from another brand, they did not switch back. Nike also lost the critical feedback loop that specialty running retailers provided, making it slower to detect that its technical product was falling behind." } }, { "@type": "Question", "name": "Who is Elliott Hill and can he turn Nike around?", "acceptedAnswer": { "@type": "Answer", "text": "Elliott Hill replaced John Donahoe as Nike CEO in September 2024. Unlike his predecessor, Hill spent his entire career at Nike, starting at the lowest rungs and earning his way up — giving him deep institutional knowledge of the business. He is widely regarded as credible and clear-eyed. However, nearly two years into his tenure, Nike has not yet been able to regain meaningful traction, illustrating how much harder recovery is than the original damage." } }, { "@type": "Question", "name": "What is Dupree Financial Group's investment approach for retirement income?", "acceptedAnswer": { "@type": "Answer", "text": "Dupree Financial Group is a fee-only, fiduciary SEC-registered RIA based in Lexington, Kentucky. The firm builds retirement income strategies around dividend-paying, income-generating separately managed accounts — with no products sold, no commissions, and no conflicts of interest. They specialize in helping adults 50 and older build portfolios designed to generate income that can keep pace with inflation over time." } } ] } ] } The Nike Cautionary Tale: What Happens When Leadership Loses Touch With Its Customers The Tom Dupree Show | Dupree Financial Group | dupreefinancial.com | 859-233-0400 Nike spent decades building one of the most recognized brands on the planet — the Swoosh, the Air Jordan, high-heat basketball shoes that consumers lined up for, and a presence in every major sporting goods retailer in the world. Then, in 2020, the company handed its future to a CEO who believed physical retail was a dying model, and what followed became a business school study in how quickly a great company can lose its way. In this episode of The Tom Dupree Show, host Tom Dupree and analyst Michael Dawahare walk through the full arc of Nike’s rise and decline — from its origins in a track coach’s garage to a stock that traded at $180 and has since fallen to around $44. They examine the strategic decisions that caused the damage, the board failures that let it compound, and the hard-won lesson that consumer loyalty, once transferred to a competitor, is almost impossible to reclaim. And for anyone managing retirement assets, the parallels are direct: proven strategies should not be abandoned for untested ones, fundamentals matter more than narratives, and the cost of a foundational error can take years to undo. You cannot put your own lenses on the lenses of your customer — you have to ask how they see the world, not how you see it. — Tom Dupree How Nike Built the Brand — and What It Was Actually Built On Nike was founded on performance athletics. Phil Knight, a runner at the University of Oregon, partnered with legendary track coach Bill Bowerman — who famously experimented with a waffle iron to create better running soles — and built a company that stood for technical innovation and athletic credibility. The brand’s cultural ascent accelerated in 1984 with the signing of Michael Jordan, and from there, Nike became what everyone knows: the dominant force in athletic footwear and apparel, consistently ranked among the world’s most recognized brands. At its peak, Nike operated across multiple business lines — high-heat basketball, lifestyle and streetwear, performance running, and endorsement deals with some of the most iconic athletes in the world. Its Jordan Brand alone eventually grew to represent 25–30% of total business. But that success carried a hidden fragility: the Jordan Brand was built on a generational talent, and there was no clear plan for what would carry that brand forward once Jordan’s cultural relevance inevitably faded with younger consumers. The 2020 CEO Transition and the Fatal Pivot When Nike’s board appointed John Donahoe as CEO in 2020, it elevated someone who had served on the board since 2014 and who had an exceptional track record — at eBay and ServiceNow. But his entire professional background was in direct-to-consumer digital commerce, and he arrived at Nike with a conviction that physical retail distribution was a slowly melting ice cube. His plan: reduce Nike’s dependence on wholesale partners — Foot Locker, Dick’s Sporting Goods, specialty running retailers — and shift the business toward a pure direct-to-consumer model. Margins would improve by eliminating the distribution layer. And the consumer, Donahoe believed, would simply find Nike on their phone rather than in a store. The pandemic made it look like a genius. Physical retail was disrupted, Nike’s direct channels surged, the stock reached all-time highs around $180, and the board was enthusiastic. Beneath the surface, the strategy was already creating irreversible damage. The Shelf Space Problem — and the Competitors Who Said Thank You When Nike told its wholesale partners they would be receiving significantly less product going forward, those partners did not fight back. They simply filled the space with someone else. HOKA — already a credible running brand — accelerated its growth dramatically. On Cloud, a Swiss performance running brand, began one of the most remarkable growth runs in the industry, expanding into running, tennis, golf, and multiple other categories simultaneously. New Balance, ASICS, and Brooks also claimed their share of the newly available retail real estate. The consumer who walked into a Foot Locker or Dick’s and encountered a wall of Nike was now encountering a much more competitive set of choices. They tried the alternatives. Many of them preferred what they found. And once a runner builds loyalty to a particular shoe platform — especially in a category where consumers replace their shoes every 90 days — that loyalty is remarkably durable. Nike also lost something less tangible but equally important: the feedback loop. Specialty running retailers were the ground-level intelligence network that told Nike week by week what runners wanted, what was working, and where the product needed to improve. When Nike walked away from that channel, it walked away from its early warning system. The Board Failure — and the Groupthink That Let It Happen One of the most striking aspects of the Nike story is not that one CEO had a flawed conviction — that happens — but that an entire board of accomplished executives approved and sustained a strategy that was, in hindsight, obviously misaligned with how Nike’s business actually worked. By some accounts, Tim Cook of Apple was on that board during part of this period. It is difficult to imagine Cook making an analogous argument that Apple did not need its retail stores. The dynamic Tom and Michael describe is familiar to anyone who studies large organizations: board members are generally reluctant to challenge a CEO too forcefully, because the social and professional cost of being the dissenter is real. The result is groupthink — a board that validates a strategy long past the point where the data should have prompted hard questions. By late 2022 and into 2023, the numbers made it undeniable. Nike attempted to reverse course, reaching back out to wholesale partners and offering them premium product. The response was polite — and firm. Retailers were glad to take the high-demand items that consumers queued for. The rest of Nike’s moderate catalog? They had already replaced it, and they were satisfied with what they had. Where Nike Stands Today The board replaced Donahoe with Elliott Hill in September 2024. Hill’s story is genuinely different from his predecessor’s: he started in a Nike stockroom and built his entire career inside the company, earning credibility at every level. He speaks clearly and credibly about what went wrong and what needs to happen. And nearly two years into his tenure, Nike’s stock remains near $44 — roughly 75% below its peak —, and the company has not yet found its footing. In running — the category that gave Nike its identity — the brand no longer consistently appears in the top 10 for preferred shoes among dedicated runners. In China, sales are down 20–30% in recent quarters. On Cloud continues to grow at roughly 50% per quarter. The chart, as Tom notes throughout this episode, always tells the story: if a real recovery is underway, you will see it in the price action. The current chart does not yet show that. What This Means for Your Retirement Portfolio Tom closes this episode with a point that connects the Nike story directly to retirement investing: when someone tells you that a proven model is outdated — that index funds are so last century, or that some new product captures market upside without any downside — the right questions are always the same. What is the process? Has it been tested across different market conditions? And who benefits when you believe in it? The investor who abandons a sound income strategy during a period of volatility, convinced by a compelling narrative, is making the same error Donahoe made. The fundamentals that built something durable do not become wrong because someone new arrived with a different set of lenses. Key Takeaways Know what your business — or portfolio — is actually built on. The moment Nike shifted focus from technical performance products, competitors filled the gap. Investors face the same risk when strategies drift from the principles that made them work. Never surrender your shelf space. Giving up distribution is almost impossible to reverse. The same principle applies when investors abandon a proven income strategy during volatility — re-entry is rarely seamless. Leadership bias is one of the most expensive mistakes in business. Donahoe was an outstanding digital executive who ran a physical consumer company through a digital lens. Bias in a CEO or a portfolio manager costs real money. Boards exist to prevent catastrophic decisions. Most don’t. Nike’s board approved a strategy that effectively fired its wholesale customer base. Institutional oversight is only as good as the willingness to ask uncomfortable questions. Consumer loyalty, once transferred, is remarkably sticky. Runners who found HOKA or On Cloud did not come back. When you give a customer a reason to try something else, and they love it, you may have lost them permanently. Recovery from a foundational strategic error takes far longer than the error itself. The damage from a few years of bad decisions can take a decade to undo — in business and in retirement portfolios. Proven strategies deserve skepticism about replacement, not abandonment. When a new model sounds compelling, the questions are always: what’s the process, has it been tested, and who benefits from your belief in it? Frequently Asked Questions What caused Nike’s stock to fall from $180 to around $44? Nike’s decline was driven primarily by a strategic pivot under CEO John Donahoe, who took over in 2020 and aggressively reduced the company’s reliance on wholesale partners in favor of a direct-to-consumer digital model. This freed up shelf space for competitors like HOKA and On Cloud, whose products consumers tried, preferred, and stayed with. Nike also lost focus on technical product innovation — the foundation of the brand — and the combination proved very difficult to reverse. What leadership lessons can retirement investors take from Nike’s decline? The Nike story illustrates several principles that apply directly to managing retirement assets: proven strategies should not be abandoned in favor of untested new models; losing touch with core fundamentals creates compounding damage; and when someone tells you the old approach is outdated, the right question is always whether the new approach has been tested and who benefits from your belief in it. Why did Nike’s wholesale withdrawal strategy fail? Nike believed consumers would migrate online and that eliminating wholesale intermediaries would improve margins. What actually happened was that vacated shelf space went to competitors — HOKA, On Cloud, New Balance, ASICS, and Brooks — who earned consumer loyalty through it. Once runners found a shoe they preferred, they did not switch back. Nike also lost the critical feedback loop that specialty running retailers provided. Who is Elliott Hill and can he turn Nike around? Elliott Hill replaced John Donahoe as Nike CEO in September 2024. Unlike his predecessor, Hill spent his entire career at Nike, starting at the lowest rungs and earning his way up. He is widely regarded as credible and clear-eyed about the challenges. However, nearly two years into his tenure, Nike has not yet regained meaningful traction — illustrating how much harder recovery is than the original damage. What is Dupree Financial Group’s investment approach for retirement income? Dupree Financial Group is a fee-only, fiduciary SEC-registered RIA based in Lexington, Kentucky. The firm builds retirement income strategies around dividend-paying, income-generating separately managed accounts — with no products sold, no commissions, and no conflicts of interest. They specialize in helping adults 50 and older build portfolios designed to generate income that can keep pace with inflation over time. Schedule a Complimentary Portfolio Review If you’re not sure whether your portfolio is built on the same principles Nike abandoned — proven strategy, staying close to what works, and never losing sight of the fundamentals — we’ll take a look. No charge. No pressure. Just an honest conversation about what you own and whether it’s working for you. Call: 859-233-0400  |  Visit: dupreefinancial.com Dupree Financial Group is a Registered Investment Adviser (RIA) registered with the U.S. Securities and Exchange Commission. Registration does not imply a certain level of skill or training. The information presented on this podcast is for educational purposes only and should not be construed as personalized investment advice. Past performance is not indicative of future results. Investing involves risk, including the potential loss of principal. Please consult a qualified financial professional before making investment decisions. The post Nike’s Fall: Leadership Lessons for Retirement Investors appeared first on Dupree Financial.

In today's episode, Rachel takes us down a rabbit hole of family running lore, including the story of her grandfather, Terry McDermott, who brought home Olympic gold and silver medals in speed skating. She also shares a much more encouraging injury update and explains why pelvic floor therapy has been helpful in her recovery journey. Meanwhile, Karen is inching ever closer to being fully healthy again, while Megan is deep in the trenches of moving.The Chicks also break down a few fun questions: Is running a half marathon at a bachelorette party an iconic idea or a friendship-ending one? How would they survive the Taco Bell 50K Challenge? And which Hogwarts house would each type of runner belong in?Plus: Where are the best places to do hill workouts in and around Chicago?_________________Find this week's shoe recs here:Megan: Paige Cameron Wide Leg JeansKaren:⁠ Hoka Skyward Laceless ShoesRachel: ⁠Franco Sarto Pura Slingback Shoes_________________SUPPORT OUR SPONSORZappos is an online retail destination for the best in footwear, offering the selection and expertise runners need to take on each day with confidence. Zappos carries an extensive assortment of performance running shoes, including leading brands like HOKA, Nike, Brooks, New Balance, ASICS, On, and more. ⁠⁠⁠⁠Check out the latest selection on footwear on Zappos.com or in the Zappos app. ⁠⁠⁠⁠_________________CHICK CHAT– Send us your questions at ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠gettingchickedpodcast@gmail.com⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ or DM us on Instagram at ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@gettingchicked⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠YOUR HOSTS– Karen Lesiewicz | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@kare_les on Instagram⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– Rachel DaDamio | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@rdadamio on X⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– Megan Connelly | ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠@meganmorantwwe on Instagram⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠FOLLOW OUR SHOW– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Subscribe on Apple Podcasts here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow on Spotify here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠– ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Follow the show on Instagram here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

This week on Fuel for the Sole, we're tackling a bunch of your questions. We cover everything from waking up hungry in the middle of the night to whether you should be supplementing with Vitamin D, to managing race-day anxiety and its effect on your gut — plus, we break down what Isomaltulose (brand name Palatinose) actually is and whether it's worth your attention. We also off the rails, per usual. Want to be featured on the show? Email us (written or an audio file!) at⁠ fuelforthesolepodcast@gmail.com⁠. This episode is fueled by ASICS and RNWY!Head over to⁠ ASICS.com⁠ and sign up for a OneASICS account. It's completely free and when you sign up you will receive 10% off your first purchase. You also gain access to exclusive colorways on ASICS.com, free standard shipping, special birthday month discounts and more.RNWY Complete Protein is a post-run recovery shake we genuinely stand behind. Here's why: built on YESTEIN®, a fermented yeast protein that scores a PDCAAS of 1.0, which is thehighest possible protein quality rating. That puts it in the same category as whey but without anyof the dairy. Every serving gives you 25 grams of complete protein containing all nine essential amino acids plus 5 grams of creatine monohydrate and a five-enzyme digestive complex. Get yours at https://rnwy.life/ and use code FEATHERS15 for 15% off your purchase. Disclaimer: This content is not intended to be a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of your physician or other qualified health provider with any questions you may have regarding a medical condition.

Semiconductors have moved from the background of the technology stack to the center of the AI economy. What used to be a specialized industry discussed mostly by engineers and investors is now shaping the speed, cost, and strategic direction of modern computing.In this episode of TechSurge, host Michael Marks speaks with Stacy Rasgon, Managing Director and Senior Analyst covering U.S. semiconductors and semiconductor capital equipment at Bernstein Research. Stacy has spent years analyzing the chip industry across cycles, but argues that the current moment feels different in scale: AI demand has created an unprecedented scramble for compute, memory pricing has surged, and companies across the stack are being forced to rethink capacity, architecture, and capital allocation.The conversation explains the 4 different kinds of semiconductor cycles—supply, inventory, product, and demand — and why Stacy believes the industry is currently in a demand cycle of unusual magnitude. The discussion also unpacks the distinction between DRAM and NAND, why high-bandwidth memory is becoming strategically central to AI systems, and how the physical realities of wafer capacity and silicon area are constraining supply in ways the broader market often misses.Stacy and Michael also discuss the hardware economics behind the current boom, with Michael pressing Stacy on why compute remains so scarce and how companies are improving performance through packaging and system design. Michael then moves the conversation beyond market headlines to the core business questions: who is actually paying for this compute, which use cases are generating real revenue, and whether AI spending is creating durable economic value or simply shifting costs elsewhere. Together, these questions highlight two of the episode's clearest insights: coding may be one of the earliest AI applications with meaningful willingness to pay, and inference, not training, is the real test of whether the current buildout becomes a lasting business or just another expensive wave of infrastructure.Stacy explains the concentration of power among the major wafer fabrication equipment players, the rise of ASICs as a meaningful share of AI silicon, Broadcom's rapidly expanding AI opportunity, and the growing role of Chinese companies as new entrants, especially in memory and semiconductor equipment. Along the way, the conversation asks the defining question facing the sector: is this just another semiconductor upswing, or the first true supercycle the industry has seen? Stacy believes that this might be the biggest supercycle he has seen in his career.Sign up for our newsletter at techsurgepodcast.com for updates on upcoming TechSurge Live Summits and future episodes.Links:Stacy Rasgon on LinkedIn: https://www.linkedin.com/in/stacy-rasgon-6924963Bernstein: https://www.alliancebernstein.com/corporate/en/home.htmlReferences Mentioned During the DiscussionNVIDIA Blackwell Platform: https://www.nvidia.com/en-us/data-center/blackwell-platform/High Bandwidth Memory (HBM) overview from Micron: https://www.micron.com/products/memory/hbmDRAM overview from IBM: https://www.ibm.com/think/topics/dramNAND flash overview from IBM: https://www.ibm.com/think/topics/nand-flash-memoryFurther ReadingMcKinsey on the semiconductor industry outlook: https://www.mckinsey.com/industries/semiconductors/our-insights/the-semiconductor-industry-in-2025Semiconductor Industry Association: 2025 State of the U.S. Semiconductor Industry: https://www.semiconductors.orgNVIDIA on the Blackwell architecture and AI infrastructure roadmap: https://www.nvidia.com/en-us/data-center/blackwell-platform/Broadcom AI investor materials and infrastructure commentary: https://investors.broadcom.comASML on lithography and advanced chip manufacturing: https://www.asml.com/en/technologyMicron on HBM and AI memory demand: https://www.micron.com/products/memory/hbmChapters[00:00:00] — Highlights[00:00:26] — Welcome to  the Episode[00:01:29] — Meet Stacy Rasgon[00:02:01] — Is This the First Real Semiconductor Supercycle?[00:05:33] — Inside the Strongest Memory Cycle in History [00:09:14] — Can Innovation Keep Up With AI Demand?[00:11:33] — Chiplets, Blackwell, and the New Economics of Compute [00:12:37] — What Could Signal the Cycle Is Slowing[00:14:26] — Vertical Integration at the Hyperscales [00:16:36] — The Difference between Apple and Meta[00:17:15] — What is Vertical Integration Being Done For?[00:18:15] — Will other bottlenecks develop as This Progresses? [00:21:13] — Oligopoly Pricing in the Market[00:22:22] — Any New Entrants into Memory?[00:23:46] — Why the Industry Must Pivot From Training to Inference[00:25:10] — Agentic Coding and the First Real AI Revenues[00:26:57] — Groq, Low-Latency Inference, and What GPUs Cannot Do Alone[00:29:28] —-Could The Smaller Companies All be Bought Up ?[00:30:19] — Why Semiconductor Equipment Matters More Than Ever [00:31:00] — How Semiconductor Equipment is Affected by the Cycle[00:32:55] — A Long Upcycle for Semiconductor Equipment Guys?[00:33:13] — The Big Five and the Rise of Chinese Equipment Players[00:34:24] — The Effects of Geopolitics[00:35:02] — Broadcom's Quiet AI Breakout[00:40:46] — ASICs vs GPUs and the Next Wave of Custom Chips[00:41:06] — Intel, Foundry Strategy, and the Long Turnaround[00:46:46] —-The Risks the Market May Still Be Underestimating[00:49:32] — Where Startups Still Have Room to Win[00:50:39] — What the Semiconductor Industry Could Look Like Next Year

Nathan, Matt, and David play a round of This or That, pitting mainline trainers against their premium counterparts to decide which they'd actually pick. They work through head-to-head matchups across several major brands — Asics, Brooks, Saucony, Hoka, Puma, and On — weighing the real-world differences in ride, value, and who each shoe is really for.We're thrilled to announce our apparel collaboration with Rabbit! The collection includes the EZ Tee SS, EZ Tee LS, and a unisex Go-to Hoodie. Pre-sale is open thru June 17th, with gear shipping the week of July 6th. Check it out at https://www.runinrabbit.com/collections/doctors-of-running. Note that the monthly discount code cannot be applied to collab items.Rabbit is the presenting partner of our podcast. You can use code DORJUNE10 to get 10% off your entire order of $50.00 or more. Note that the code is limited to one use per customer and can't be combined with other discounts. The code is active from 1st of every month to last day at 11:59PM PST, but don't worry because we'll be bringing you a new code every month. Shop now at https://www.runinrabbit.com.Our In For Testing segment is fueled by Skratch Labs! Get 20% off your first order from Skratch with code: DOCTORSOFRUNNING! https://www.skratchlabs.comChapters0:00 - Intro0:31 - Rabbit X DOR gear!3:29 - In for Testing: Powered by Skratch Labs23:24 - This or That: Asics Novablast 6 or Superblast 3?34:12 - Brooks Glycerin 23 or Glycerin Max 239:06 - Saucony Ride 19 or Paramount Max44:36 - Triumph 24 or Paramount Max48:40 - Hoka Clifton 10 or Hoka Skyward X 251:24 - Puma Velocity Nitro 4 or Magmax 254:30 - On Cloudmonster 3 or Cloudmonster 3 Hyper1:00:08 - Wrap-up

Phil makes his final decision about racing in Duluth, Travis hits two of his best sessions of the block, and Blake leaves for a beach holiday -- he's irreplaceable, but we bring in a certified bad boy as guest star. Before the training talk we discuss a listener question about the significance of using heart rate on easy days. We've almost made it to race day! Thanks for listening throughout the spring build, and thanks to ASICS and Columbus Running Company for supporting this series. secondsflatpodcast@gmail.com columbusrunning.com

This week on Fuel for the Sole, we're tackling listener questions - and naturally, going off the rails along the way. We share an update on RNWY landing at Whole Foods, the races we have on our calendars, whether you actually need more sodium in the summer heat, why some BPN gels come with a daily limit, and why you can probably skip the carb load before your next 10K.Want to be featured on the show? Email us (written or an audio file!) at⁠ fuelforthesolepodcast@gmail.com⁠. This episode is fueled by ASICS and RNWY!Head over to⁠ ASICS.com⁠ and sign up for a OneASICS account. It's completely free and when you sign up you will receive 10% off your first purchase. You also gain access to exclusive colorways on ASICS.com, free standard shipping, special birthday month discounts and more.RNWY Complete Protein is a post-run recovery shake we genuinely stand behind. Here's why: built on YESTEIN®, a fermented yeast protein that scores a PDCAAS of 1.0, which is the highest possible protein quality rating. That puts it in the same category as whey but without anyof the dairy. Every serving gives you 25 grams of complete protein containing all nine essential amino acids plus 5 grams of creatine monohydrate and a five-enzyme digestive complex. Get yours at https://rnwy.life/ and use code FEATHERS15 for 15% off your purchase. Disclaimer: This content is not intended to be a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of your physician or other qualified health provider with any questions you may have regarding a medical condition.

20 days to go to Grandma's Marathon! Blake hits his peak week, Phil navigates a sore foot, and Travis consumes prodigious amounts of ice cream. Thanks to ASICS and Columbus Running Company for making it possible! secondsflatpodcast@gmail.com columbusrunning.com

“By the time we get there, I don't think we'll leave any stone unturned for the first one. There's still room to grow, but I do think I'll be very ready.”My guest for today's episode is Emma Grace Hurley: an ASICS athlete and one of the most consistent American road racers of the last two years. She trains under Andrew and Amy Begley at Heartland Track Club in Indianapolis, and in 2026 she has already set the American Record at 8K (24:29 at the Shamrock Shuffle), won the USATF 10-Mile title at Cherry Blossom, won the 25K title at the Gate River Run and finished second at the USATF 5K Championships in her own city, running 15:00 flat to miss the sub-15 barrier by four-tenths of a second.She is also, as of this week, officially confirmed as one of the scoring members of the U.S. half marathon team for Copenhagen — one of the three athletes who were misdirected in the closing mile of the USATF Half Marathon Championships in Atlanta in March. World Athletics granted a special exception that will allow seven American women to compete, with Jess McClain, Emma Grace, and Ednah Kurgat as the scoring athletes alongside Weini Kelati. The top three official finishers — Molly Born, Carrie Ellwood, and Annie Rodenfels — will make their international debuts as non-scoring athletes.What makes Emma Grace one of the more interesting stories in American distance running right now is the shape of her career. She graduated from Furman in 2020 with a 15:57 5K personal best, quit running entirely, took a client associate job at JP Morgan, and did not think she was coming back to the sport. She is now a 15:00 road 5K runner, an 8K American record holder, a national 10-mile champion, and a two-event Worlds qualifier. She has not run a marathon yet — it's happening this fall.In this conversation, recorded in Brooklyn, we get into all of it: what it actually took to bounce back after Atlanta and immediately set a national record three weeks later, why she doesn't love the track but is a 15-flat road 5K runner, the Cherry Blossom 10-mile where she lost the overall by one second to a woman who finished seventh in the 10,000m at the Tokyo Olympics, the moment she finally felt like the long slow build was paying off, and what scares her most about the marathon block ahead.____________Host: Chris Chavez | ⁠⁠⁠@chris_j_chavez⁠Guest: Emma Grace Hurley | @emmagracehurleyProduced by: Jasmine Fehr |⁠ ⁠⁠⁠@jasminefehr⁠____________SUPPORT OUR SPONSORSXENDURANCE: Xendurance Protein is designed specifically to help your body recover, rebuild, and get stronger after training. It combines four different types of protein, so your body gets both fast absorbing protein for immediate recovery and slower release protein to support muscle repair over time. ⁠⁠⁠⁠⁠⁠⁠Check it out at Xendurance.com and use code CITIUS for 25% off your first order.⁠⁠⁠⁠⁠VELOUS: VELOUS makes recovery footwear designed to help runners bounce back faster between sessions. Their sandals feature Tri-Motion™ Technology: a technical three-density foam system and contoured footbed engineered to cushion impact, support your arches, and help your toes stretch and relax on every step. Run. Recover. Repeat. with VELOUS! ⁠⁠⁠⁠⁠Get 20% off your VELOUS order with code CITIUSMAG20 at checkout including FREE Shipping!⁠⁠⁠⁠⁠OLIPOP: Raspberry Sherbet is a limited-edition, nostalgic new flavor that blends tangy raspberry with creamy vanilla. Every can of Olipop contains their Olismart blend, which includes ingredients designed to support digestive health and help feed your gut microbiome. If you haven't had tried Olipop yet, grab a can and see what the hype is all about!⁠⁠ ⁠⁠⁠⁠⁠⁠Head to DrinkOlipop.com and use code CITIUS25 at checkout to get 25% off your orders.⁠⁠

We're inside a month to Grandma's Marathon! We open this week with a discussion of the ASICS Megablast and Superblast 3. Then it's a dive into our training weeks. Phil stretches his long run to 2 hours, Blake goes metric, and Travis tackles his longest run of the block in a monsoon. Thanks to ASICS and Columbus Running Company for supporting this series! secondsflatpodcast@gmail.com columbusrunning.com

It was a heavy week in trail running, to say the least. Katie Schide officially withdraws from Hardrock as her foot injury rehab continues, and Kilian Korth faces season-ending surgery on a peroneus longus tendon tear that took place during this year's Cocodona 250.Then the Cam Hanes situation. After Hanes admitted to using banned peptide BPC 157 in an Instagram thread following his 2:39 Eugene Marathon, Sage Canaday filed a USADA tip. We break down the ethics of doping enforcement below the pro tier and what Cam's outsized influence on the sport means for any resolution.Plus: Rachel Entrekin's new multi-year Norda deal through 2029, Rachel Drake's record-shattering FKT on the West Grandeur Ascent, Will Peterson ending his Appalachian Trail FKT attempt at the Mason-Dixon line, ASICS opening a year-round UTMB training base in Les Houches, results from Leavenworth Trailfest and the Golden Trail World Series, plus a Twisted Fork Trail Festival preview.Partners:Precision Fuel and Hydration - use code SINGLETRACK at checkout for 15% off your next orderNorda - check out the 005: the lightest, fastest, most stable trail racing shoe ever madeRaide - Making equipment for efficient human-powered movement in the mountains Janji - premium trail running apparelSupport the show

Merch - https://nonmembersshop.com/Happy National Wine Day! We are trying out a new podcast intro and struggling through this episode as Erin nurses a massive hangover after drinking a little too much at a surprise 50th birthday party at her sister's B&B. She also recaps the struggle of trying to leave the party while her 7-year-old decided to become a "party girl" and perform magic tricks with doorway streamers.We then dive into a heated rant about the disrespect of neighbors blasting bass music late at night when you have sleeping kids, and Erin reveals her passive aggressive revenge tactic: sending the kids outside early in the morning to aggressively ring their bicycle bells. In fitness news, Erin gives an exciting week six update on her "Pull-Up Revolution." She finally felt the right muscles activate, got her head to the bar, and used her newfound strength to casually lift a heavy shelving system into Dan's truck at Lowe's. We also review a brilliant new ASICS marketing campaign that shows "before and after" photos of runners taken just 15 minutes apart, highlighting that the mental sanity you get from a workout is the real transformation.For "Tea Time," we unpack the messy internet feud between a runner/musician named Zach and DJ Diplo. Diplo sparked massive outrage by claiming he no longer needs to pay human artists because he can just use AI, leading to a bizarre comment section war where Diplo punched down and insulted musicians as "degenerate alcoholics". We also debate a hilarious act of spite at a major PGA golf tournament in Philly, where a homeowner built a massive platform in their backyard just to peer over the privacy fence and watch the event with their friends.We also tease our upcoming trip to the Enhanced Games in Vegas. We get a terrifying update on the local black bear that has been destroying Erin's trash cans (and ripping off the metal pins).In pop culture, we review the 42 step daily routine of Bryan Johnson, longevity guy. Finally, we cover a disastrous Houston Astros 5K/10K where runners were backed up for over an hour just trying to cross the finish line on the field, and celebrate Canada hosting their very first National Women's Wheelchair Rugby Championship!

This week on Fuel for the Sole, we're breaking down the recent sub-2 hour marathon performances from London, including a closer look at how each athlete fueled their record-breaking efforts. Then, we dive into your listener questions — and this week, it's all about the not-so-glamorous side of racing. From mid-race dizziness to post-race nausea and everything uncomfortable in between, we're tackling your most pressing GI concerns head-on.Want to be featured on the show? Email us (written or an audio file!) at⁠ fuelforthesolepodcast@gmail.com⁠. This episode is fueled by ASICS and RNWY!Head over to⁠ ASICS.com⁠ and sign up for a OneASICS account. It's completely free and when you sign up you will receive 10% off your first purchase. You also gain access to exclusive colorways on ASICS.com, free standard shipping, special birthday month discounts and more.RNWY Complete Protein is a post-run recovery shake we genuinely stand behind. Here's why: built on YESTEIN®, a fermented yeast protein that scores a PDCAAS of 1.0, which is thehighest possible protein quality rating. That puts it in the same category as whey but without anyof the dairy. Every serving gives you 25 grams of complete protein containing all nine essential amino acids plus 5 grams of creatine monohydrate and a five-enzyme digestive complex. Get yours at https://rnwy.life/ and use code FEATHERS15 for 15% off your purchase. Disclaimer: This content is not intended to be a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of your physician or other qualified health provider with any questions you may have regarding a medical condition.