Podcasts about Looping

GSfMO #385 May 21, 2013 “An American Caddie in St. Andrews - Growing Up, Girls, and Looping on the Old Course” is a highly entertaining memoir of a young American's adventures as a caddie at St. Andrews while attending St. Andrews University. Our guest is the author Oliver Horovitz, who after being forced to take a gap year before starting at Harvard, Oliver went to study and work in Scotland. He also created a short documentary that you can still find on his website at oliverhorovitz.com This was originally published as a Members Only episode, so even if you've been listening to our podcast for a long time, you may have never heard this before. Please check out our new and updated website at golfsmarter.com! While there, you'll receive three free gifts when you post an honest review about Golf Smarter the podcast. You can also get free gifts for recording a show opening by clicking on "Record Your Show Open Here!" tab on the right side of the page.  Please take a few minutes to fill out our survey, which will also provide you with a link to Tony Manzoni's video!Follow @golfsmarter on Instagram, X, Facebook, TikTok, YouTube. See our daily highlights and helpful insights from our interviews on the podcast. Thanks so much for checking it out and providing your feedback.     This episode is sponsored by Indeed. Please visit indeed.com/GOLFSMARTER and get a $75 SPONSORED JOB CREDIT. Terms and conditions apply.   This episode is sponsored by HIMS. Start your free online visit today HIMS.com/golfsmarter and received personalized ED treatment options.This episode is also sponsored by SelectQuote. Make sure you get the right life insurance for YOU, for LESS, at selectquote.com/golfsmarter today and get started.

In dieser Folge sind wir zu Dritt, und zwar Martin, Markus und Steffen. Wir starten mit persönlichen Erlebnissen, darunter Markus' Verein, der eine ASK21 gekauft hat, und Martins Erfahrungen mit einem Zero-G-Flieger. Wir Spekulieren natürlich über den Absturz der Azerbaijan Airlines Flight 8432 und jeju air flight 2216. Zum Abschluss wird über einen Sommer in Vilshofen als mögliches CFWU-Treffen nachgedacht.

Con el amigo Maxito querido no podríamos estar más babosos. Nos pegamos una conversa de una tarde completa con dos de las cabezas tras juegos que amamos y que nos han dado decenas de horas de diversión: Pedro Soto y Ferran Renalias. Lacrimosa, On the Origin of Species, y por supuesto la saga 19xx completa pasa por este microscopio, cómo cuajan temáticas y mecánicas, de dónde salen las ideas, por dónde pasan sus vidas personales, y por supuesto hacia dónde apunta Looping de ahora en adelante.

In this episode I go through my team, game 1 and how to loop captaincy and emergencies!#bbl #bblsupercoach Hosted on Acast. See acast.com/privacy for more information.

In this episode I go through the final word on my team, captaincy choices and looping thoughtsGood luck all :)#bbl #bblsupercoach Hosted on Acast. See acast.com/privacy for more information.

In today's episode of the Hardcore Self Help Podcast, I sit down with Pulitzer Prize-winning journalist and best-selling author Charles Duhigg to explore the science of effective communication and its profound impact on our personal and professional lives. Charles shares insights from his latest book, Supercommunicators: Unlock the Secret Language of Connection, delving into how skills like empathy, active listening, and understanding different types of conversations can transform the way we connect with others. Our conversation uncovers the neurological underpinnings of communication, including the concept of neural entrainment and the matching principle. We discuss practical strategies for improving communication in various contexts—from personal relationships to the workplace—and address common pitfalls people face, such as social anxiety and miscommunication. Whether you're looking to enhance your relationships, become a better listener, or navigate tough conversations with ease, this episode is packed with valuable insights to help you on your journey. Chapters: 00:15 — Introduction: Meet Charles Duhigg 03:00 — From Business to Journalism: Charles's Unconventional Path 08:00 — The Power of Storytelling in Communication 11:45 — Understanding the Science Behind Effective Communication 14:00 — The Three Types of Conversations: Practical, Emotional, Social 17:00 — The Matching Principle: Aligning Conversations for Connection 21:00 — Diagnosing and Matching Conversation Types 24:00 — Looping for Understanding: A Technique for Better Listening 28:00 — Common Communication Mistakes and How to Avoid Them 31:00 — Empathy Without Mimicry: Connecting Without Oversharing 34:00 — Real-World Examples: Doctors, Therapists, and Effective Communication 38:00 — Advice for Introverts and Those with Social Anxiety 44:00 — The Power of Asking Questions in Social Settings 47:00 — Overview of 'Supercommunicators' and Its Practical Applications 51:00 — Navigating Tough Conversations: Tips and Strategies 54:00 — A Challenge for Listeners: Reconnecting with Someone 57:30 — Closing Thoughts and Where to Find Charles's Work Hope you find this enlightening conversation as engaging as I did! Feel free to share your thoughts and experiences in the comments below. About the Podcast I'm Dr. Robert Duff, a clinical psychologist and the host of the Hardcore Self Help Podcast. My mission is to break down complex mental health topics into relatable, actionable advice. On this podcast, we dive deep into mental health, personal development, and the strategies that help us thrive. Each episode is a mix of expert interviews, practical tips, and answers to listener questions, all aimed at helping you live a healthier, more fulfilled life. Guest Links: Charles's Latest Book: Supercommunicators: Unlock the Secret Language of Connection — https://www.amazon.com/Supercommunicators-Unlock-Secret-Language-Connection/dp/0593243919 Website: CharlesDuhigg.com — https://www.charlesduhigg.com/ Twitter: @cduhigg — https://twitter.com/cduhigg Connect With Me: Website: duffthepsych.com — https://www.duffthepsych.com/ Instagram: @duffthepsych — https://www.instagram.com/duffthepsych/ YouTube: Dr. Duff's Channel — https://www.youtube.com/c/DuffThePsych #MentalHealth #EffectiveCommunication #CharlesDuhigg #SelfHelp #Supercommunicators #PersonalDevelopment #ListeningSkills #SocialAnxiety

Chat up the gang on social media:    Patrick as the DM - https://twitter.com/professorpfm Matt as Resdyn - https://twitter.com/longfellow_matt Nate as Lindon Longfeather - https://bsky.app/profile/natescottjones.bsky.social Otto as Aetrias Coilbone - https://twitter.com/humanwreckages Tyler as Elias - https://www.tylerscowcroft.com/   Podcast Group: Cast of Many Things - https://twitter.com/castomanythings https://bsky.app/profile/castofmanythings.bsky.social   Email: castofmanythings@gmail.com   Intro Music by Chloe Elliott - https://linktr.ee/clo_withtheflow Podcast art by https://twitter.com/YourDarlingSon Editing by https://twitter.com/humanwreckages Blue Ska by Kevin MacLeod Link: https://incompetech.filmmusic.io/song/3453-blue-ska License: https://filmmusic.io/standard-license   Distant Tension by Kevin MacLeod Link: https://filmmusic.io/song/3661-distant-tension License: https://filmmusic.io/standard-license   Looping by Alpha Hydrae Link: https://freemusicarchive.org/music/Alpha_Hydrae/Peace_Love_Respect_Overdrive/Alpha_Hydrae_-_Alpha_Hydrae_-_Peace_Love_Respect_Overdrive_-_12_Looping License: https://creativecommons.org/publicdomain/zero/1.0/   Snowfall by Steinbruchel  Link: https://freemusicarchive.org/music/Steinbruchel/Summer_Tour_Remix_v1/09_Snowfall/ License: https://creativecommons.org/licenses/by/3.0/us/   2Two by Monplaisir Link: https://freemusicarchive.org/music/Monplaisir/Live__Rencontres_Mondiales_du_Logiciel_Libre_Strasbourg_07072018/Monplaisir_-_Live__Rencontres_Mondiales_du_Logiciel_Libre_Strasbourg_07-07-2018_-_03_2Two License: https://creativecommons.org/publicdomain/zero/1.0/   Masterminds by Monplaisir Link: https://freemusicarchive.org/music/Monplaisir/Best_Of__Pick_Your_Player/Monplaisir_-_Best_Of_-_Pick_Your_Player_-_02_Masterminds/ License: https://creativecommons.org/publicdomain/zero/1.0/   Zapan Marche by Alpha Hydrae Link: https://freemusicarchive.org/music/Monplaisir/Mothlight_OST/Alpha_Hydrae_-_Mothlight_OST_-_20_Zapan_Marche License: https://creativecommons.org/publicdomain/zero/1.0/   Sancho Panza gets a Latte by Kevin MacLeod Link: https://incompetech.filmmusic.io/song/4317-sancho-panza-gets-a-latte License: https://filmmusic.io/standard-license   Too Cool by Kevin MacLeod Link: https://incompetech.filmmusic.io/song/4534-too-cool License: https://filmmusic.io/standard-license  

The athlete pathway for masters is different from other groups. What can clubs and Federations do to enable masters to succeed by changing the structure of our sport. Timestamps 00:40 What is our goal for masters in rowing? Should masters be allowed to leave and rejoin the club? One of the differences compared to youth rowers is that we remain in the sport for a long time. Youth, school, Seniors all have a long term athlete plan for the pathway of their progress. Masters are not the same. Our goal may be to race and achieve high results - but it is not always. The long term development plan is very different. Some join for participation and to learn how to row; others are there all the time, training and racing. Others like the weekend rows and train for fitness, pleasure and friendship - they may also race but on a shorter term horizon leading up to an event. 04:30 Looping in and out of rowing Many masters remain in the sport for a long time. What is possible for you right now? Life stage is important. In your 30s you may have a high pressure job. Or a flexible worker who can train during the working day hours. Some masters retire to row - actively. If you have children, under 14s are different from over 14s and can look after themselves for a time. Care responsibilities for aging parents are also another different group of masters. Our goal is continued participation - can you manage to stay involved on a level suitable for where you are right now? 07:00 Club membership structures don't align If you are required to buy an annual membership and are injured, this makes people decide not to rejoin their rowing club. 07:30 Create enabling structures These allow members to loop in and out of masters rowing participation over time. How can you stay involved while injured? Join social events with the club group. Can memberships be by quarter, term or semester? Groups in rowing clubs - often LTR, fitness, racing groups are common. As a club how to you enable members to move between groups in a way that reflects their life circumstance? How frequently do you re-assess group members? Can people see a pathway so they can see what the next step is for them in their rowing journey? What does it take to move from intermediate to elite racing? 10:00 Long term athlete development for masters How can you make it possible for members to stay involved over the long term in your club? These structures might make masters rowing long-term participant so we can remain engaged with the sport over the ultra-long term. Athlete development needs to be aligned with an individual's goals, skills improvement, not necessarily always-upward movement towards high racing achievement. Masters pathways are not necessarily linear - people can loop into rowing and then step away and loop out for a while. Making this happen is structural, requires a strategy for leaders who are involved in masters rowing. What can you do in your club to help?

First things first: I switched up the order of this podcast, as the part I recorded first – ultimately – felt like it was more appropriate for my ride-or-die Patreon/Locals members, so I cut it out of the top of the episode, and moved it to the end/Part 2. The meat of the matter lies in the analysis of some popular song lyrics, as well as an intro into the Language of Eternity, plus, the latest report from the frontlines of the censorship industrial complex. Yippee.Part 2:danikatz.locals.comwww.patreon.com/danikatzwww.danikatz.comShow notes:Pop music- the power of programming via lyrics and frequencies“Come Down”- lyrical examinationEminem lyrics- noticing low vibe through-line Jay Z- lyrics denigrating womenAwareness of exposure to messaging in songs“Run the World” Beyonce- lyrical repetition 'How old are you?'- being 3D inside the eternity of NowAttack of the Wayback MachineYouTube strike- blocked by Brett WeinsteinChronicling censorship- screenshots Reviewing the inane review process at YouTubeAaron Abke- 'To speak out or to not speak out' when unifying polarities Safeguarding freedom-we have different roles and methods Frustration and messiness of being an honest journalistPropaganda course

La abuela de Jaime, más conocido como Jimbo Safi, siempre le ponía una vela cuando él tenía algún reto, alguna salida importante en bici o alguna carrera. Ese gesto, esa vela, cuidaba, en cierto modo, de Jimbo mientras pedaleaba. Su abuela siempre velaba por Jaime de ese modo. Hace unos días Jaime decidió que su abuela formara parte también de su próximo reto y proyecto: Looping gramps. Jaime le regaló una vela a su abuela, grande, de calidad, 40cm de alto y unos 15cm de diámetro. "Voy a pedalear hasta que se apague la vela". Jaime pilló la bici y se fue, desde Murcia hasta Galícia, pasando por Girona y Aragón. 2156 Km. 9 días recorriendo España y sitios importante para él y su abuela: donde ella nació, dónde conoció con su marido (abuelo de Jaime), entre otros.El proyecto tiene también el objetivo de dar visibilidad a uno de los problemas de nuestra sociedad. La soledad de la gente mayor. Es por ese motivo que en el momento de publicar este episodio todavía se tiene la oportunidad de participar en el sorteo de la bici que usó Jimbo en esta aventura. Los fondos irán a la asociación "Cyling without age" (algo así como ciclismo sin edad) para ayudar a que la gente más mayor pueda volver a sentir el viento en la cara mientras monta en bici o mientras les llevan en bici. Esta es quizá la historia más personal y emotiva que hemos contado desde Gravel Studio. Y no fue en gravel como tal pero hemos querido charlar con Jimbo (siendo él un gran aficionado al gravel) y porque el motivo merecía la pena. Si te ha gustado el episodio, déjanos un comentario y dale a seguir en la app de podcast o en youtube (suscribios que es gratis ;) Y en redes sociales @gravelstudio_ @laucyclecoach @carlosmancera4Nos vemos, nos escuchamos, como siempre, de nuevo, el martes que viene.

Amanda Ripley is a New York Times bestselling author, a Washington Post contributing columnist, and the co-founder of Good Conflict, a media and training company that helps people reimagine conflict. She has written three award-winning, nonfiction books about three very different subjects: High Conflict, The Smartest Kids in the World, and The Unthinkable. In this episode we talk about:The key differences between healthy conflict and high conflictFive key steps for getting out of or avoiding high conflictWhy it's a golden age for so-called conflict entrepreneurs; and how to spot them in your orbit‘Looping' – a key technique that changed Amanda's life (and Dan's)How to set good boundaries while not giving up on peopleOne of the most reliable antidotes to all forms of bias, something called contact theoryThoughts on how to interact with the news and social media during a presidential electionThe very good reasons to avoid humiliating your opponent. She calls humiliation the nuclear bomb of emotionsAnd much moreRelated Episodes:Fight Right: The Science of Healthy Conflict | Drs. John and Julie GottmanHow to Repair the Damage After a Fight | Dr. Becky KennedySign up for Dan's weekly newsletter hereFollow Dan on social: Instagram, TikTokTen Percent Happier online bookstoreSubscribe to our YouTube ChannelOur favorite playlists on: Anxiety, Sleep, Relationships, Most Popular EpisodesFull Shownotes: https://happierapp.com/podcast/tph/amanda-ripley-843Additional Resources:thegoodconflict.comDownload the Ten Percent Happier app today: https://app.tenpercent.com/link/downloadSee Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

The Trek Files goes back into the world of audio for an in-depth discussion about Star Trek: The Motion Picture. Specifically, the many complexities of character dialogue recording and re-recording are the focus for special guest Mike Matessino who was a post-production supervisor on both of TMP's Director's Editions. A memo from Robert Wise about actor ADR kicks off a discussion about the noisy Enterprise bridge, the changes given to Vulcan subtitles over the years, and much more. Document and additional references: "Star Trek" Looping - August 15, 1979 The Trek Files Season 12 on Memory Alpha All episodes and documents: The Trek Files on Memory Alpha Visit the Trekland site for behind-the-scenes access and exclusive merchandise.

The Trek Files goes back into the world of audio for an in-depth discussion about Star Trek: The Motion Picture. Specifically, the many complexities of character dialogue recording and re-recording are the focus for special guest Mike Matessino who was a post-production supervisor on both of TMP's Director's Editions. A memo from Robert Wise about actor ADR kicks off a discussion about the noisy Enterprise bridge, the changes given to Vulcan subtitles over the years, and much more. Document and additional references: "Star Trek" Looping - August 15, 1979 The Trek Files Season 12 on Memory Alpha All episodes and documents: The Trek Files on Memory Alpha Visit the Trekland site for behind-the-scenes access and exclusive merchandise.

The Trek Files goes back into the world of audio for an in-depth discussion about Star Trek: The Motion Picture. Specifically, the many complexities of character dialogue recording and re-recording are the focus for special guest Mike Matessino who was a post-production supervisor on both of TMP's Director's Editions. A memo from Robert Wise about actor ADR kicks off a discussion about the noisy Enterprise bridge, the changes given to Vulcan subtitles over the years, and much more. Document and additional references: "Star Trek" Looping - August 15, 1979 The Trek Files Season 12 on Memory Alpha All episodes and documents: The Trek Files on Memory Alpha Visit the Trekland site for behind-the-scenes access and exclusive merchandise.

In this live recording we produce weekly on Twitter/X, we deep dive into the most promising DeFi yields and primitives. This week, we review all the latest strategies for yield-trading, fixed interest lending, YTs, and liquidity provisions on Pendle Finance. It's packed with all the alpha we need to be Pendle pros! The audio is less optimal in parts so thanks for your patience listening! ------

I'm excited to share a personal story today—one that has layers beyond what it seems. You're definitely going to want to grab a drink, get comfortable, and enjoy. We're talking about boundaries, cookies, and the uncomfy parts of learning our own dysfunction through our relationship dynamics.Only 5 days left to get HTMW Workbook for 50% off!Download my free Shadow Work and Inner Child Guide to get a printable worksheet that you can use again and again!Upcoming Events for Codependency Alchemy

DIE IDEE mit Norbert Grundei ist ein Podcast des NDR. In dieser Folge spricht Dr. Werner Stengel über seine Karriere als Ingenieur und Achterbahn-Pionier. Als Erfinder des modernen Loopings und Konstrukteur zahlreicher weltbekannter Fahrgeschäfte teilt er seine faszinierenden Geschichten und gibt Einblicke in die technologische Entwicklung der Freizeitindustrie. Vom Looping bis zur modernen Hochgeschwindigkeits-Achterbahn – erfahren Sie, wie er mit seinem technischen Know-how und innovativen Ansätzen die Branche revolutionierte. Themen in dieser Episode: - Die Geschichte hinter der ersten Stahlachterbahn Deutschlands - Wie der Looping sicher gemacht wurde - Technische und medizinische Herausforderungen bei Achterbahnen - Persönliche Geschichten und Anekdoten aus der Welt der Schausteller - Achterbahn-Designs und ihre physikalischen Grundlagen Podcast-Tipp: 11KM - der Tagesschau Podcast in der ARD Audiothek, der Audio-App der ARD Streaming-Tipp: SECONDS - in den Trümmern der Katastrophe - in der ARD Mediathek. Danke an N-JOY und Dennis Bangert

In this episode of Podsongs, host Jack Stafford is joined by the band ATLYS to discuss their project inspired by renowned dog trainer Linda Michaels. They delve into the unique, innovative methods of Linda, emphasizing her force-free dog training techniques and the development of the Hierarchy of Dog Needs. The conversation covers the band's classical roots, their evolution, and their boundary-pushing performances. They reveal insights into their creative process, including composing and recording their first original song inspired by Linda's work. Tune in to hear about the guests' dedication to animal welfare, the band's upcoming projects, and the premier of their new canine-inspired track. Stream the song: https://ffm.to/fortheloveofdogsatlys 00:00 Welcome to Podsongs 00:08 Introducing Jinty McTavish and Atlas 00:37 Creating a Masterpiece: The Songwriting Process 01:49 Atlas: Breaking Classical Music Stereotypes 03:16 Life on Cruise Ships and Intensive Training 05:30 The Art of Looping and Live Performances 06:48 Composing the First Original Song 08:13 Inspiration Behind the Song: A Tribute to Animals 09:15 Interview with Linda Michaels: World Famous Dog Trainer 17:23 Linda Michaels' Journey and Philosophy 39:42 Discovering the World of Dog Training 41:00 Hands-On Experience with Dogs 43:59 Memorable Dog Training Stories 46:34 Understanding Dog Behavior and Communication 49:30 The Science Behind Dog Intelligence 53:31 Practical Tips for Dog Owners 01:13:18 Adopting and Fostering Dogs 01:18:16 Resources and Community Support 01:23:37 Conclusion and Future Plans www.donoharmdogtraining.com www.atlysmusic.com // SUPPORT THIS CHANNEL // Newsletter, donations and download the song for €/$1 @ https://podsongs.com // LINKS // Website: https://podsongs.com Podcast episodes: https://podsongs.com/podcast-episodes Songs: https://podsongs.com/music Spotify artist: https://open.spotify.com/artist/32FYyRx1y1ex3jHHAgLMC7?si=4Nv7WW85SbSPZvCsj1o7Ig Spotify playlist: https://open.spotify.com/playlist/6sN1viy82HPiNTVX2YBxpq?si=1b84c2b9bdea4656 // SOCIAL // Twitter: https://twitter.com/podsongs Instagram: https://instagram.com/podsongs Facebook: https://facebook.com/podsongs

Self-care podcast Exploring Judgement and Your Frequency, Being The Observer of Your Mind & Dismantling Looping Behaviors With Guest Elisa Kurylowicz TOPICS:: ** Exploring Judgement and Your Frequency (05:26). ** Being The Observer of Your Mind (42:15). ** Dismantling Looping Behaviors With Guest Elisa Kurylowicz (43:48).   NOTES:: Show notes: amberapproved.ca/podcast/511 Leave me a review at amberapproved.ca/review Email me at info@amberapproved.caSupport the show: Donate Via Stripe or Paypal   Summer Coaching Sale! Save big on Private Coaching and Fall Group Coaching by booking your consultation: https://amberapproved.ca/body-freedom-consultation/    SHOW LINKS: Click below to schedule a 30 minute Complimentary Body Freedom Consultation https://amberapproved.ca/body-freedom-consultation/  Take my free Emotional Eating Quiz here: http://amberapproved.ca/emotional-eating-quiz Listen to Episode 291 about what it's like to work with me here: http://amberapproved.ca/podcast/291/ Follow me on Instagram www.instagram.com/amberromaniuk Youtube Channel: https://www.youtube.com/@amberromaniuk/    About My Guest: Elisa Kurylowicz is a former National athlete for Canada Freestyle, World Cup Gold Medalist and 2x National Champion in the sport of Mogul Skiing.  After she retired from competing, she became a level 4 NCCP Coach, and coached for 12 years at the provincial and Canadian National level.  Elisa was instrumental in creating Canada's long term athlete development model, talent identification program and is Canada's top female coach in Freestyle Skiing to date. Elisa is also a Yoga Teacher, Certified Performance Coach & Intuitive Awareness Specialist who now teaches women self-awareness tools to love their body, business, and love life. She is the founder of Elisa Unfiltered Coaching where she works with women who struggle with relationships, business, body image, burnout, and self-worth.  She teaches them intuitive mindset skills so they can break free from the invisible barriers holding them back, let go of shame, guilt and trauma and begin to live their life by design. She is the creator and host of the Elisa Unfiltered: Living Life Out Loud Podcast, which has over 100,000 downloads and is rated in the top 1% globally. Check out Elisa's Membership: The Your New Era Academy is a group coaching container for women who are done with the old way (self sabotage, burn out doubt, self sacrifice & resentment and rage) and who want to create a new way of unapologetically redesigning their life, health, body, spirituality, wealth, relationship and abundance. Change your mindset, change your life. https://elisaunfilteredcoaching.com/group-coaching/ Instagram: @elisakurylowicz Website: www.elisaunfilteredcoaching.com    Podcast: Elisa Unfiltered: Living Life Out Loud (Available anywhere you stream podcasts or elisaunfilteredcoaching.com/podcast)

Break out your air pump because some underground dragons are phasing through the earth to get us! This week we review another seminal game in the history of video games; Dig Dug is finally here! We also cover Looping by Video Games GmbH and Scorpion by Zaccaria in todays episode!Website -https://historyofvideogamespodcast.comTwitter - https://twitter.com/HistoryofVideo1Email - historyvgpodcast@gmail.comHosts - Ben & WesMusic - Arranged and recorded by BenTransition Music - Track 10 (Second half) from Ben's upcoming Album "Demons"

We listen and talk to your Casio KX-101 submissions!

Join the Music History Project podcast team for a special episode discussing guitar effects and looping. Our guest is musician, songwriter, looper and former music retailer David Jenson. We will highlight a few Oral History interviews related to effects including Mike Porter, Del Casher, Thomas Blug and enjoy David presenting a looping demo!

This podcast hit paid subscribers' inboxes on July 27. It dropped for free subscribers on Aug. 3. To receive future pods as soon as they're live, and to support independent ski journalism, please consider an upgrade to a paid subscription. You can also subscribe to the free tier below:WhoPeter Disch, General Manager of Mount Sunapee, New Hampshire (following this interview, Vail Resorts promoted Disch to Vice President of Mountain Operations at its Heavenly ski area in California; he will start that new position on Aug. 5, 2024; as of July 27, Vail had yet to name the next GM of Sunapee.)Recorded onJune 24, 2024About Mount SunapeeClick here for a mountain stats overviewOwned by: The State of New Hampshire; operated by Vail ResortsLocated in: Newbury, New HampshireYear founded: 1948Pass affiliations:* Epic Pass, Epic Local Pass, Northeast Value Epic Pass: unlimited access* Northeast Midweek Epic Pass: midweek access, including holidaysClosest neighboring (public) ski areas: Pats Peak (:28), Whaleback (:29), Arrowhead (:29), Ragged (:38), Veterans Memorial (:42), Ascutney (:45), Crotched (:48), Quechee (:50), Granite Gorge (:51), McIntyre (:53), Saskadena Six (1:04), Tenney (1:06)Base elevation: 1,233 feetSummit elevation: 2,743 feetVertical drop: 1,510 feetSkiable Acres: 233 acresAverage annual snowfall: 130 inchesTrail count: 67 (29% beginner, 47% intermediate, 24% advanced)Lift count: 8 (2 high-speed quads, 1 fixed-grip quad, 2 triples, 3 conveyors – view Lift Blog's inventory of Mount Sunapee's lift fleet.)History: Read New England Ski History's overview of Mount SunapeeView historic Mount Sunapee trailmaps on skimap.org.Why I interviewed himNew Hampshire state highway 103 gives you nothing. Straight-ish and flattish, lined with trees and the storage-unit detritus of the American outskirts, nothing about the road suggests a ski-area approach. Looping south off the great roundabout-ish junction onto Mt. Sunapee Road still underwhelms. As though you've turned into someone's driveway, or are seeking some obscure historical monument, or simply made a mistake. Because what, really, could be back there to ski?And then you arrive. All at once. A parking lot. The end of the road. The ski area heaves upward on three sides. Lifts all over. The top is up there somewhere. It's not quite Silverton-Telluride smash-into-the-backside-of-a-box-canyon dramatic, but maybe it's as close as you get in New Hampshire, or at least southern New Hampshire, less than two hours north of Boston.But the true awe waits up high. North off the summit, Lake Sunapee dominates the foreground, deep blue-black or white-over-ice in midwinter, like the flat unfinished center of a puzzle made from the hills and forests that rise and roll from all sides. Thirty miles west, across the lowlands where the Connecticut River marks the frontier with Vermont, stands Okemo, interstate-wide highways of white strafing the two-mile face.Then you ski. Sunapee does not measure big but it feels big, an Alpine illusion exploding over the flats. Fifteen hundred vertical feet is plenty of vertical feet, especially when it rolls down the frontside like a waterfall. Glades everywhere, when they're live, which is less often than you'd hope but more often than you'd think. Good runs, cruisers and slashers, a whole separate face for beginners, a 374-vertical-foot ski-area-within-a-ski-area, perfectly spliced from the pitched main mountain.Southern New Hampshire has a lot of ski areas, and a lot of well-run ski areas, but not a lot of truly great pure ski areas. Sunapee, as both an artwork and a plaything, surpasses them all, the ribeye on the grill stacked with hamburgers, a delightful and filling treat.What we talked aboutSunapee enhancements ahead of the 2024-25 winter; a new parking lot incoming; whether Sunapee considered paid parking to resolve its post-Covid, post-Northeast Epic Pass launch backups; the differences in Midwest, West, and Eastern ski cultures; the big threat to Mount Sunapee in the early 1900s; the Mueller family legacy and “The Sunapee Difference”; what it means for Vail Resorts to operate a state-owned ski area; how cash flows from Sunapee to Cannon; Sunapee's masterplan; the long-delayed West Bowl expansion; incredible views from the Sunapee summit; the proposed Sun Bowl-North Peak connection; potential upgrades for the Sunapee Express, North Peak, and Spruce lifts; the South Peak beginner area; why Sunapee built a ski-through lighthouse; why high-speed ropetows rule; the potential for Sunapee night-skiing; whether Sunapee should be unlimited on the Northeast Value Pass (which it currently is); and why Vail's New Hampshire mountains are on the same Epic Day Pass tier as its Midwest ski areas.Why I thought that now was a good time for this interviewShould states own ski areas? And if so, should state agencies run those ski areas, or should they be contracted to private operators?These are fraught questions, especially in New York, where three state-owned ski areas (Whiteface, Gore, and Belleayre) guzzle tens of millions of dollars in new lift, snowmaking, and other infrastructure while competing directly against dozens of tax-paying, family-owned operations spinning Hall double chairs that predate the assassination of JFK. The state agency that operates the three ski areas plus Lake Placid's competition facilities, the Olympic Regional Development Authority (ORDA), reported a $47.3 million operating loss for the fiscal year ending March 30, following a loss of $29.3 million the prior year. Yet there are no serious proposals at the state-government level to even explore what it would mean to contract a private operator to run the facilities.If New York state officials were ever so inspired, they could look 100 miles east, where the State of New Hampshire has run a sort of A-B experiment on its two owned ski areas since the late 1990s. New Hampshire's state parks association has operated Cannon Mountain since North America's first aerial tram opened on the site in 1938. For a long time, the agency operated Mount Sunapee as well. But in 1998, the state leased the ski area to the Mueller family, who had spent the past decade and a half transforming Okemo from a T-bar-clotted dump into one of Vermont's largest and most modern resorts.Twenty-six years later, that arrangement stands: the state owns and operates Cannon, and owns Sunapee but leases it to a private operator (Vail Resorts assumed or renewed the lease when they purchased the Muellers' Triple Peaks company, which included Okemo and Crested Butte, Colorado, in 2018). As part of that contract, a portion of Sunapee's revenues each year funnel into a capital fund for Cannon.So, does this arrangement work? For Vail, for the state, for taxpayers, for Sunapee, and for Cannon? As we consider the future of skiing, these are important questions: to what extent should the state sponsor recreation, especially when that form of recreation competes directly against private, tax-paying businesses who are, essentially, subsidizing their competition? It's tempting to offer a reflexive ideological answer here, but nuance interrupts us at ground-level. Alterra, for instance, leases and operates Winter Park from the City of Denver. Seems logical, but a peak-day walk-up Winter Park lift ticket will cost you around $260 for the 2024-25 winter. Is this a fair one-day entry fee for a city-owned entity?The story of Mount Sunapee, a prominent and busy ski area in a prominent and busy ski state, is an important part of that larger should-government-own-ski-areas conversation. The state seems happy to let Vail run their mountain, but equally happy to continue running Cannon. That's curious, especially in a state with a libertarian streak that often pledges allegiance by hoisting two middle fingers skyward. The one-private-one-public arrangement was a logical experiment that, 26 years later, is starting to feel a bit schizophrenic, illustrative of the broader social and economic complexities of changing who runs a business and how they do that. Is Vail Resorts better at running commercial ski centers than the State of New Hampshire? They sure as hell should be. But are they? And should Sunapee serve as a template for New York and the other states, counties, and cities that own ski areas? To decide if it works, we first have to understand how it works, and we spend a big part of this interview doing exactly that.What I got wrong* When listing the Vail Resorts with paid parking lots, I accidentally slipped Sunapee in place of Mount Snow, Vermont. Only the latter has paid parking.* When asking Disch about Sunapee's masterplan, I accidentally tossed Sunapee into Vail's Peak Resorts acquisition in 2019. But Peak never operated Sunapee. The resort entered Vail's portfolio as part of its acquisition of Triple Peaks – which also included Okemo and Crested Butte – in 2018.* I neglected to elaborate on what a “chondola” lift is. It's a lift that alternates (usually six-person) chairs with (usually eight-person) gondola cabins. The only active such lift in New England is at Sunday River, but Arizona Snowbowl, Northstar, Copper Mountain, and Beaver Creek operate six/eight-passenger chondolas in the American West. Telluride runs a short chondola with four-person chairs and four-person gondola cars.* I said that the six New England states combined covered an area “less than half the size of Colorado.” This is incorrect: the six New England states, combined, cover 71,987 square miles; Colorado is 103,610 square miles.Why you should ski Mount SunapeeSki area rankings are hard. Properly done, they include dozens of inputs, considering every facet of the mountain across the breadth of a season from the point of view of multiple skiers. Sunapee on an empty midweek powder day might be the best day of your life. Sunapee on a Saturday when it hasn't snowed in three weeks but everyone in Boston shows up anyway might be the worst. For this reason, I largely avoid assembling lists of the best or worst this or that and abstain, mostly, from criticizing mountain ops – the urge to let anecdote stand in for observable pattern and truth is strong.So when I do stuff ski areas into a hierarchy, it's generally grounded in what's objective and observable: Cottonwoods snow really is fluffier and more bounteous than almost all other snow; Tahoe resort density really does make it one of the world's great ski centers; Northern Vermont really does deliver far deeper snow and better average conditions than the rest of New England. In that same shaky, room-for-caveats manner, I'm comfortable saying this: Mount Sunapee's South Peak delivers one of the best beginner/novice experiences in the Northeast.Arrive childless and experienced, and it's likely you'll ignore this zone altogether. Which is precisely what makes it so great: almost completely cut off from the main mountain, South Peak is free from high-altitude bombers racing back to the lifts. Three progression carpets offer the perfect ramp-up experience. The 374-vertical-foot quad rises high enough to feel grown-up without stoking the summit lakeview vertigo. The trails are gently tilted but numerous and interesting. Other than potential for an errant turn down Sunnyside toward the Sunapee Express, it's almost impossible to get lost. It's as though someone chopped a mid-sized Midwest ski area from the earth, airlifted it east, and stapled it onto the edge of Sunapee:A few other Northeast ski areas offer this sort of ski-area-within-a-ski-area beginner separation – Burke, Belleayre, Whiteface, and Smugglers' Notch all host expansive standalone beginner zones. But Sunapee's is one of the easiest to access for New England's core Boston market, and, because of the Epic Pass, one of the most affordable.For everyone else, Sunapee's main mountain distills everything that is great and terrible about New England skiing: a respectable vertical drop; a tight, complex, and varied trail network; a detached-from-conditions determination to be outdoors in the worst of it. But also impossible weekend crowds, long snow draughts, a tendency to overgroom even when the snow does fall, and an over-emphasis on driving, with nowhere to stay on-mountain. But even when it's not perfect, which it almost never is, Sunapee is always, objectively, a great natural ski mountain, a fall-line classic, a little outpost of the north suspiciously far south.  Podcast NotesOn Sunapee's masterplan and West Bowl expansionAs a state park, Mount Sunapee is required to submit an updated masterplan every five years. The most transformative piece of this would be the West Bowl expansion, a 1,082-vertical-foot pod running skiers' left off the current summit (right in purple on the map below):The masterplan also proposes upgrades for several of Sunapee's existing lifts, including the Sunapee Express and the Spruce and North Peak triples:On past Storm Skiing Podcasts:Disch mentions a recent podcast that I recorded with Attitash, New Hampshire GM Brandon Schwarz. You can listen to that here. I've also recorded pods with the leaders of a dozen other New Hampshire mountains:* Wildcat GM JD Crichton (May 30, 2024)* Gunstock President & GM Tom Day (April 15, 2024) – now retired* Tenney Mountain GM Dan Egan (April 8, 2024) – no longer works at Tenney* Cranmore President & GM Ben Wilcox (Oct. 16, 2023)* Dartmouth Skiway GM Mark Adamczyk (June 12, 2023)* Granite Gorge GM Keith Kreischer (May 30, 2023)* Loon Mountain President & GM Brian Norton (Nov. 14, 2022)* Pats Peak GM Kris Blomback (Sept. 26, 2022)* Ragged Mountain GM Erik Barnes (April 26, 2022)* Whaleback Mountain Executive Director Jon Hunt (June 16, 2021)* Waterville Valley President & GM Tim Smith (Feb. 22, 2021)* Cannon Mountain GM John DeVivo (Oct. 6, 2020) – now GM at Antelope Butte, WyomingOn New England ski area densityDisch referenced the density of ski areas in New England. With 100 ski areas crammed into six states, this is without question the densest concentration of lift-served skiing in the United States. Here's an inventory:On the Civilian Conservation Corps (CCC)From 1933 to 1942 – the height of the Great Depression – a federal government agency knows as the Civilian Conservation Corps recruited single men between the ages of 18 and 25 to “improve America's public lands, forests, and parks.” Some of this work included the cutting of ski trails on then-virgin mountains, including Mount Sunapee. While the CCC trail is no longer in use on Sunapee, that first project sparked the notion of skiing on the mountain and led to the development of the ski area we know today.On potential Northeast expansions and there being “a bunch that are proposed all over the region”This is by no means an exhaustive list, but a few of the larger Northeast expansions that are creeping toward reality include a new trailpod at Berkshire East:This massive, village-connecting expansion that would completely transform Waterville Valley:The de-facto resurrection of New York's lost Highmount ski area with an expansion from adjacent Belleayre:And the monster proposed Western Territories expansion that could double the size of Sunday River. There's no public map of this one presently available.On high-speed ropetowsI'll keep beating the crap out of this horse until you all realize that I'm right:A high-speed ropetow at Spirit Mountain, Minnesota. Video by Stuart Winchester.On Crotched proximity and night skiingWe talk briefly about past plans for night-skiing on Sunapee, and Disch argues that, while that may have made sense when the Muellers owned the ski area, it's no longer likely since Vail also owns Crotched, which hosts one of New England's largest night-skiing operations less than an hour south. It's a fantastic little operation, a once-abandoned mountain completely rebuilt from the studs by Peak Resorts:On the Epic Day PassHere's another thing I don't plan to stop talking about ever:The Storm explores the world of North American lift-served skiing year-round. Join us.The Storm publishes year-round, and guarantees 100 articles per year. This is article 48/100 in 2024, and number 548 since launching on Oct. 13, 2019. Get full access to The Storm Skiing Journal and Podcast at www.stormskiing.com/subscribe

Discussion of proposed BCH '25 "Targeted VM Limits" upgrade, with prominent BCH developer & CHIP author Jason Dreyzehner. We get into the historical context, rationale, and details of VM Limits. We also discuss BigInts, CashTokens retrospect, LibAuth, ZCEs, Looping and more. Enjoy, and please share your thoughts in the comments. Links:Jason Dreyzehner on Twitter: https://x.com/bitjsonbitjson's blog: https://bitjson.com/ CHIP 2021-05 Targeted Virtual Machine Limits: https://bitcoincashresearch.org/t/chip-2021-05-targeted-virtual-machine-limits/437CHIP 2024-07 BigInt: High-Precision Arithmetic for Bitcoin Cash: https://bitcoincashresearch.org/t/chip-2024-07-bigint-high-precision-arithmetic-for-bitcoin-cash/1356Episode slides: https://docs.google.com/presentation/d/1wLaTFfq4PQ1dfTs2EMsNxGMQOZKZMIpW/edit?usp=sharing&ouid=100290143879929950045&rtpof=true&sd=trueDonations:bitcoincash:qzm59xkz4pkqgpakkpvjcrsffu4gtjxdju7hq6q30hSponsors:Thank you very much to our flipstarter contributors: https://bchpodcastflipstarter.cash/enGeneral Protocols: https://generalprotocols.com and https://bchbull.com Socials:Website: https://www.bitcoincashpodcast.comTimestamps:00:00 Podcast starts00:38 Intro01:50 Jason's intro06:34 Thoughts on ABLA upgrade10:20 VM Limits: overview13:40 VM Limits: rationale17:31 VM Limits: Satoshi's work32:15 Differences among implementations39:26 BTC overflow bug45:00 CHIP: Targeted VM Limits49:35 VM Limits + Big Integers52:28 Big Ints CHIP relation to VM Limits CHIP1:00:18 Benchmarking worst case contracts with LibAuth1:02:24 Timing: 2025 vs 2026 1:10:35 Testing process1:16:55 Zero-Confirmation Escrows (ZCE) and Looping1:20:35 0-confirmations, miner incentives, and finality1:25:10 Loops and UTXO commitments1:34:32 CashTokens1:39:17 Mathieu's Q: Zero knowledge proof verifier?1:42:33 Sidechain necessary for prediction market apps?1:49:29 Jason's message to the community1:51:00 Podcast supporter appreciation1:52:03 Shoutouts and outro#bitcoin #bitcoincash #bch #btc #crypto #cryptocurrency #cbdc ▪️

Our "Story of our Loop" series is back with Michael MacLeod sharing the stories of his two Great Loop trips. After a career in music that included travel around the globe, Michael began the Great Loop and completed it the first time aboard a 22' C-Dory and a second time aboard a 25' C-Dory. Join us to hear what drew Michael to the Great Loop, why his boats were perfect for his style of Looping, what leg he found most challenging, and more. The Great Loop is a 6,000-mile route through interconnected waterways that allows boaters to circumnavigate the eastern U.S. and part of Canada. Learn more at www.greatloop.org.

What is the best insulin pump? Today's guest would be the one to know. Gary Scheiner, author of Think Like a Pancreas, has tried 32 different pumps in his 39 years living with type one. Gary and I chatted about the early days of AID systems, his favorite AID system, looping, and several different pumps, including iLet, Medtronic, Mobi, and Tandem. We also peek into what the future might hold for insulin pumps. This episode is a great resource to help you determine which technology will be the best for YOU. Time Stamps:  (02:28) Keeping Up with Technology Advances(04:18) Gary's 39 Years with Diabetes and 32 Different Pumps (06:27) “It's not the tool, it's the user.”(07:40) “Is there a best pump?” and finding the right one(11:00) The Early Days of AID Systems(13:39) His Favorite Aid System (16:05) Looping (18:44) The Gap Between Health Care & Tools Education(21:57) The iLet Pump(25:26) “I don't like people to start on a pump without learning self-management skills.”(27:45) Medtronic (29:08) Mobi (29:58) Tandem (31:33) The Future of Insulin Pumps(35:16) “What does reclaim your rise mean to you?”What to do now:Follow me @lauren_bongiorno and @riselyhealth on Instagram to stay in the loop when new episodes drop.Learn more about our 1:1 coaching programs HERE.  Learn more about Temp Monitor HERE Buy Temp Monitor HEREFind Gary on Instagram and his book Think Like a Pancreas on Amazon.Disclaimer: Nothing you hear on the Reclaim your Rise podcast should be a substitute for personalized professional medical advice. Please always consult your physician or other medical professional before making any changes to your diet, insulin dosages, or healthcare plan. 

Billy & Jenn talk all-the-things “post wedding day” and then try to wrap their minds around the mental phenomenon of “looping.” WHY do we do it and HOW can we break the cycle of lunacy in our own heads?  _ _ _ _ _Official WebsiteInstagramTwitterFacebookYouTube

In this episode, I reflect on the role of music in my creative process. Looping favorite tracks helps me channel the right emotions into my paintings. Tune in for an inside look at today's inspirations and reflections.

My go-to person in life died 6 months ago. Her memorial is this weekend in Colorado and in true Tina fashion, she requested it be a taco & tequila shindig.    She was hospitalized from a stroke the day I moved into my house, and died 2 days later. She was my best friend for the past 15 years.    I recorded this video on Christmas Eve, exactly 3 weeks from her death. It was 11 pm and quiet. I made the video for myself, to capture my thoughts on how my greatest fear came true which was—if something really good comes into my life, something else gets taken away—and how now I could see that 1) that's not true; life has highs and lows and they are not related, 2) where this fear stems from...my family's past and 3) I responded to this tragic news in an empowering, trusting way that is different from how I behaved in the past. The resilience I now have is a testament to years of identifying my limiting beliefs, discovering their root cause and choosing to not let it derail me.   As I packed for my trip to Colorado to celebrate the gem of a human that Tina was, I thought about what I said in this personal video and how it might resonate with someone. So I decided to post it publicly.   In this episode:    Siblings remembering and interpreting the same experience, differently    How good can you stand it   Generational trauma   Don't play it safe because there's always a chance you can get hurt in life.    Sometimes you just need someone to hear you.    "I was basking in what I loved and at the same time, without me knowing it, my best friend was being rushed to the hospital."   Staying unseen and small and then everyone will be OK; it makes no sense. Looping subconscious beliefs.    Are you trying to protect yourself but it's actually hindering/hurting you?    Just because you get older, doesn't mean you've evolved     I've been working towards completing my coaching certification.    ** To meet my graduation requirement, I need a few more hours of outside coaching practice. So, I'm opening up 4 spots of free coaching. This will be 6 sessions for 4 individuals who would love a safe space to gain clarity and receive guidance on what's their next right step. **   To apply, please fill out this form.  https://forms.gle/xcNU2mxuZMn6Y6tUA   I know summer is filled with fun and your schedule may be all over the place. Not to worry,  I'm confident we can find the time to connect. 

Nehemiah 9:26-31 Thanks to everyone who supports TMBH at patreon.com/thetmbhpodcast You're the reason we can all do this together! Discuss the episode here Music by Jeff Foote

The guys talks bus tours, the Bachelor cult, women's basketball drama, SNL documentaries, amusement parks, and more. To learn more about listener data and our privacy practices visit: https://www.audacyinc.com/privacy-policy Learn more about your ad choices. Visit https://podcastchoices.com/adchoices

When Sally Gates moved from New Zealand to Florida, she was already an accomplished guitar player. Playing live in a metal cover band and the grindcore assassins, Relentless Attrition, she honed her chops in the Aukland scene. A year or so later circa 2008, she had moved to Miami and became the touring bass player in the mighty death metal cosmic destroyers known as Gigan. Touring on the band's seminal album "The Order of the False Eye" --a death metal record full of mind bending tempo changes and otherworldly aural assaults--Sally began her sonic journey in the U.S. with a proverbially sonic bang. But there was only one problem, she wasn't a bass player! Now writing and creating with her axe of choice, Sally's Orbweaver project picked up where Gigan left off--launching the listener to the outer orbits of extreme prog death metal. At the same time, Miami's ever expanding noise scene seeped into her restless improvisatory soul. The fearless artist followed her own path. Landing in Brooklyn's ever expanding instrumental improvisation scene, Sally Gates could not be happier. Ben and Jeff were thus so excited to talk to Sally about her new band TITAN TO TACHYONS. An all instrumental experimental jazz-metal group featuring drummer Kenny Grohowski and two bassists: Trevor Dunn (Mr. Bungle, Fantômas, Tomahawk) and Matt Hollenberg (Cleric, John Zorn). The band's second album "Vonals" is as mesmerizing as explosive--a strain of heavy music they simply can not get enough of!!! So cozy up with a Tired Hands Brewery Eviscerated Pathway of Beauty Double Citra IPA and enjoy! Music from this episode comes from the composition "Neutron Wrangler" from the album vonals. Check out some of Sally's incredible guitar playing here: Looping the Seas of Primus Beethoven Piano Tapping And gorgeous paintings here: https://sallygates.myportfolio.com/

In the latest episode of "Dementia Caregiving for Families," the importance of sharing a loved one's dementia diagnosis is discussed. Keeping the diagnosis a secret can lead to isolation and increased stress for caregivers. It's crucial to start informing others early and often, beginning with close family members and then extending to church leadership, employers, colleagues, neighbors, and authorities. This proactive approach helps build a support network and ensures safety. Recognizing conditions like anosognosia, where the person with dementia cannot see their impairment, is also essential. Private conversations without the person present might be necessary to share important information without causing distress. Effective communication with healthcare providers is another key aspect. Many doctors might dismiss symptoms as normal aging, but true memory loss isn't part of normal aging. Caregivers should prepare a concise list of observations to share with the healthcare team and consider finding a more responsive doctor if needed. Open discussions about dementia help reduce its stigma, fostering understanding and compassion. By sharing experiences and educating others, caregivers can ease their burden and provide better care for their loved ones.   2:26 Importance of Communication in Caregiving 7:08 Early and Frequent Communication Strategy 10:34 Looping in Closest Family and Church Leadership 13:22 Involving Employer, Colleagues, and Neighbors 16:28 Dealing with Lack of Awareness in the Person 19:12 Communicating with Healthcare Providers 23:18 Easing Dementia Care Challenges 27:30 Destigmatizing Dementia Discussion 31:23 Recap: Start Early and Speak Often   Enjoy our podcast? Please take a moment to leave us a review on Apple Podcasts and Spotify —it really supports our show! https://podcasts.apple.com/us/podcast/dementia-caregiving-for-families/id1716187550 Caring for your loved one with dementia doesn't have to be stressful!  Join our next free workshop.  3 Tips How to Avoid Challenging Dementia Behaviors For Christians https://www.dementiacaregivingmadeeasy.com/wsl Join our Facebook Group at: https://www.facebook.com/groups/1301886810018410 Become a Founding Member of Our Exclusive Academy! Only 54 Founding Family Slots Available for Extraordinary Caregivers. https://www.dementiacaregivingmadeeasy.com/start Are You A Christian Dementia Caregiver Struggling To Cope With Caregiving? Get Free Guidance Now! Join the Ask the de-MENTOR" Monthly Fellowship Meeting! https://dementiacaregivingmadeeasy.com/ask

This Episode: Let's talk about the Alex's letter looping system No music, no script, no fancy editing Get straight to pure Japanese between a Canadian Japanese learner and a native Japanese teacher Immerse yourself in Japanese This is the normal speed of a conversation in Japanese. If you think it's fast, there's more space for you to improve.  Alex has been learning Japanese for 6 years without skipping a day, and now he's close to JLPT N1 level (Advanced) You cannot go to Japan, so we bring Japan to you. Imagine you're overhearing this conversation somewhere in Japan. If it's too hard for you, play this in the background to feel like what it's like to be in Japan. --- Send in a voice message: https://podcasters.spotify.com/pod/show/ikinarijapanese/message

The smallest mistake can turn a champ into a chump.1:04: Blown chances: The Pacers and the 49ers3:50: Checking in on OTAs10:15: Is Brock Purdy in the wrong tier in the latest QB ranking?18:31: Looping back on the Pacers and their blown opportunity 20:00: “Inside the NBA” is on the way out24:14: Checking in on the Giants and A's26:14: The Phillies are flying, off to one of the best starts in franchise history See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Mike Love shares his journey as a musician and how he got into live looping. He talks about the importance of being present and connected with the audience during performances. He also discusses the role of meditation in his music and how it helps him stay focused and centered. Michael emphasizes the power of music to bring people together and create a shared experience. In this conversation, Michael Love discusses the importance of physical, spiritual, and mental health in music. He shares how he incorporates warmups, meditation, and fasting into his routine to stay connected to his music and take care of himself. Michael also reflects on the self-destructive tendencies that many musicians experience and the importance of self-care. He talks about the evolution of his music from arranging for a big band to performing with a stripped-down setup and the impact it has had on his songwriting. Michael also shares details about his upcoming album trilogy and tours. Check out Mike's music on the usual streaming platforms and on his website HERE https://mikelovemusic.com/ Keywords music, live looping, pedals, solo gig, meditation, presence, audience connection, music, health, warmups, meditation, fasting, self-care, self-destructive tendencies, songwriting, album trilogy, tours Takeaways Being present and connected with the audience is crucial during performances. Meditation helps Michael stay focused and centered while performing. Music has the power to bring people together and create a shared experience. Physical, spiritual, and mental health are interconnected and important for musicians. Taking care of oneself is crucial for sustained creativity and success in music. Arranging for a big band and performing with a stripped-down setup have influenced Michael's songwriting. Looping and using a loop pedal have allowed Michael to create dynamic live performances. Michael's upcoming album trilogy, starting with 'Leaders,' is a culmination of years of work and collaboration. Chapters 00:00 Introduction and Discovery of Michael Love's Work 01:36 The Start of Michael's Musical Journey 06:38 Expanding the Pedal Board and Experimenting with Effects 10:54 Improving Sound Quality and Control in Live Performances 15:20 The Importance of Presence and Energy in Live Shows 23:59 Incorporating Meditation into Performances 30:49 The Universal Power of Music 32:46 The Importance of Health in Music 36:22 Navigating Self-Destructive Tendencies 42:20 From Big Band Arrangements to Stripped-Down Performances 45:16 The Power of Looping in Live Performances 56:43 Introducing the Album Trilogy: 'Leaders', 'Teachers', and 'Healers' Support The Show And Connect! The Text Chat is back! Hit me up at (503) 751-8577 You can also help out with your gear buying habits by purchasing stuff from Tonemob.com/reverb Tonemob.com/sweetwater or grabbing your guitar/bass strings from Tonemob.com/stringjoy Release your music via DistroKid and save 30% by going to Tonemob.com/distrokid Learn more about your ad choices. Visit megaphone.fm/adchoices

Kip & Insel have completed the Great Loop three times! They share the stories of their Great Loop adventures aboard two different boats including how they've grown as boaters via the many miles they've cruised, tips on how they deal with having a 60 pound dog aboard, advice for those new to Looping, and more. America's Great Loop is the boating adventure of a lifetime! Loopers cruise the 6,000-mile Great Loop route aboard their own boats completing a circumnavigation of the eastern U.S. and part of Canada via mostly protected inland waterways. The Great Loop route follows the Atlantic Intracoastal Waterway, the Chesapeake Bay, and the New York Canals northwards, goes across the Great Lakes, south on the Inland Rivers, and then east Gulf Coast to complete the Loop.

This week Roland have done it, they've added live looping and a synth engine along with a whole host of other features. We'll take a deep dive into what they've added and then we've got an interesting look at the “future” of making music with Udio AI music generation Help Support the Channel: Patreon: https://www.patreon.com/audionautic Thanks to our Patrons who support what we do: Audionauts: Abby, Bendu, David Svrjcek, Josh Wittman, MARO, Mike K Smith, Paul Ledbrook, Matt Donatelli and Stephen Setzepfandt Lars Haur - Audionaut Producer Jonathan Goode - Audionaut Producer Join the conversation:

We are reuniting for the 2nd AI UX demo day in SF on Apr 28. Sign up to demo here! And don't forget tickets for the AI Engineer World's Fair — for early birds who join before keynote announcements!About a year ago there was a lot of buzz around prompt engineering techniques to force structured output. Our friend Simon Willison tweeted a bunch of tips and tricks, but the most iconic one is Riley Goodside making it a matter of life or death:Guardrails (friend of the pod and AI Engineer speaker), Marvin (AI Engineer speaker), and jsonformer had also come out at the time. In June 2023, Jason Liu (today's guest!) open sourced his “OpenAI Function Call and Pydantic Integration Module”, now known as Instructor, which quickly turned prompt engineering black magic into a clean, developer-friendly SDK. A few months later, model providers started to add function calling capabilities to their APIs as well as structured outputs support like “JSON Mode”, which was announced at OpenAI Dev Day (see recap here). In just a handful of months, we went from threatening to kill grandmas to first-class support from the research labs. And yet, Instructor was still downloaded 150,000 times last month. Why?What Instructor looks likeInstructor patches your LLM provider SDKs to offer a new response_model option to which you can pass a structure defined in Pydantic. It currently supports OpenAI, Anthropic, Cohere, and a long tail of models through LiteLLM.What Instructor is forThere are three core use cases to Instructor:* Extracting structured data: Taking an input like an image of a receipt and extracting structured data from it, such as a list of checkout items with their prices, fees, and coupon codes.* Extracting graphs: Identifying nodes and edges in a given input to extract complex entities and their relationships. For example, extracting relationships between characters in a story or dependencies between tasks.* Query understanding: Defining a schema for an API call and using a language model to resolve a request into a more complex one that an embedding could not handle. For example, creating date intervals from queries like “what was the latest thing that happened this week?” to then pass onto a RAG system or similar.Jason called all these different ways of getting data from LLMs “typed responses”: taking strings and turning them into data structures. Structured outputs as a planning toolThe first wave of agents was all about open-ended iteration and planning, with projects like AutoGPT and BabyAGI. Models would come up with a possible list of steps, and start going down the list one by one. It's really easy for them to go down the wrong branch, or get stuck on a single step with no way to intervene.What if these planning steps were returned to us as DAGs using structured output, and then managed as workflows? This also makes it easy to better train model on how to create these plans, as they are much more structured than a bullet point list. Once you have this structure, each piece can be modified individually by different specialized models. You can read some of Jason's experiments here:While LLMs will keep improving (Llama3 just got released as we write this), having a consistent structure for the output will make it a lot easier to swap models in and out. Jason's overall message on how we can move from ReAct loops to more controllable Agent workflows mirrors the “Process” discussion from our Elicit episode:Watch the talkAs a bonus, here's Jason's talk from last year's AI Engineer Summit. He'll also be a speaker at this year's AI Engineer World's Fair!Timestamps* [00:00:00] Introductions* [00:02:23] Early experiments with Generative AI at StitchFix* [00:08:11] Design philosophy behind the Instructor library* [00:11:12] JSON Mode vs Function Calling* [00:12:30] Single vs parallel function calling* [00:14:00] How many functions is too many?* [00:17:39] How to evaluate function calling* [00:20:23] What is Instructor good for?* [00:22:42] The Evolution from Looping to Workflow in AI Engineering* [00:27:03] State of the AI Engineering Stack* [00:28:26] Why Instructor isn't VC backed* [00:31:15] Advice on Pursuing Open Source Projects and Consulting* [00:36:00] The Concept of High Agency and Its Importance* [00:42:44] Prompts as Code and the Structure of AI Inputs and Outputs* [00:44:20] The Emergence of AI Engineering as a Distinct FieldShow notes* Jason on the UWaterloo mafia* Jason on Twitter, LinkedIn, website* Instructor docs* Max Woolf on the potential of Structured Output* swyx on Elo vs Cost* Jason on Anthropic Function Calling* Jason on Rejections, Advice to Young People* Jason on Bad Startup Ideas* Jason on Prompts as Code* Rysana's inversion models* Bryan Bischof's episode* Hamel HusainTranscriptAlessio [00:00:00]: Hey everyone, welcome to the Latent Space Podcast. This is Alessio, partner and CTO at Residence at Decibel Partners, and I'm joined by my co-host Swyx, founder of Smol AI.Swyx [00:00:16]: Hello, we're back in the remote studio with Jason Liu from Instructor. Welcome Jason.Jason [00:00:21]: Hey there. Thanks for having me.Swyx [00:00:23]: Jason, you are extremely famous, so I don't know what I'm going to do introducing you, but you're one of the Waterloo clan. There's like this small cadre of you that's just completely dominating machine learning. Actually, can you list like Waterloo alums that you're like, you know, are just dominating and crushing it right now?Jason [00:00:39]: So like John from like Rysana is doing his inversion models, right? I know like Clive Chen from Waterloo. When I started the data science club, he was one of the guys who were like joining in and just like hanging out in the room. And now he was at Tesla working with Karpathy, now he's at OpenAI, you know.Swyx [00:00:56]: He's in my climbing club.Jason [00:00:58]: Oh, hell yeah. I haven't seen him in like six years now.Swyx [00:01:01]: To get in the social scene in San Francisco, you have to climb. So both in career and in rocks. So you started a data science club at Waterloo, we can talk about that, but then also spent five years at Stitch Fix as an MLE. You pioneered the use of OpenAI's LLMs to increase stylist efficiency. So you must have been like a very, very early user. This was like pretty early on.Jason [00:01:20]: Yeah, I mean, this was like GPT-3, okay. So we actually were using transformers at Stitch Fix before the GPT-3 model. So we were just using transformers for recommendation systems. At that time, I was very skeptical of transformers. I was like, why do we need all this infrastructure? We can just use like matrix factorization. When GPT-2 came out, I fine tuned my own GPT-2 to write like rap lyrics and I was like, okay, this is cute. Okay, I got to go back to my real job, right? Like who cares if I can write a rap lyric? When GPT-3 came out, again, I was very much like, why are we using like a post request to review every comment a person leaves? Like we can just use classical models. So I was very against language models for like the longest time. And then when ChatGPT came out, I basically just wrote a long apology letter to everyone at the company. I was like, hey guys, you know, I was very dismissive of some of this technology. I didn't think it would scale well, and I am wrong. This is incredible. And I immediately just transitioned to go from computer vision recommendation systems to LLMs. But funny enough, now that we have RAG, we're kind of going back to recommendation systems.Swyx [00:02:21]: Yeah, speaking of that, I think Alessio is going to bring up the next one.Alessio [00:02:23]: Yeah, I was going to say, we had Bryan Bischof from Hex on the podcast. Did you overlap at Stitch Fix?Jason [00:02:28]: Yeah, he was like one of my main users of the recommendation frameworks that I had built out at Stitch Fix.Alessio [00:02:32]: Yeah, we talked a lot about RecSys, so it makes sense.Swyx [00:02:36]: So now I have adopted that line, RAG is RecSys. And you know, if you're trying to reinvent new concepts, you should study RecSys first, because you're going to independently reinvent a lot of concepts. So your system was called Flight. It's a recommendation framework with over 80% adoption, servicing 350 million requests every day. Wasn't there something existing at Stitch Fix? Why did you have to write one from scratch?Jason [00:02:56]: No, so I think because at Stitch Fix, a lot of the machine learning engineers and data scientists were writing production code, sort of every team's systems were very bespoke. It's like, this team only needs to do like real time recommendations with small data. So they just have like a fast API app with some like pandas code. This other team has to do a lot more data. So they have some kind of like Spark job that does some batch ETL that does a recommendation. And so what happens is each team writes their code differently. And I have to come in and refactor their code. And I was like, oh man, I'm refactoring four different code bases, four different times. Wouldn't it be better if all the code quality was my fault? Let me just write this framework, force everyone else to use it. And now one person can maintain five different systems, rather than five teams having their own bespoke system. And so it was really a need of just sort of standardizing everything. And then once you do that, you can do observability across the entire pipeline and make large sweeping improvements in this infrastructure, right? If we notice that something is slow, we can detect it on the operator layer. Just hey, hey, like this team, you guys are doing this operation is lowering our latency by like 30%. If you just optimize your Python code here, we can probably make an extra million dollars. So let's jump on a call and figure this out. And then a lot of it was doing all this observability work to figure out what the heck is going on and optimize this system from not only just a code perspective, sort of like harassingly or against saying like, we need to add caching here. We're doing duplicated work here. Let's go clean up the systems. Yep.Swyx [00:04:22]: Got it. One more system that I'm interested in finding out more about is your similarity search system using Clip and GPT-3 embeddings and FIASS, where you saved over $50 million in annual revenue. So of course they all gave all that to you, right?Jason [00:04:34]: No, no, no. I mean, it's not going up and down, but you know, I got a little bit, so I'm pretty happy about that. But there, you know, that was when we were doing fine tuning like ResNets to do image classification. And so a lot of it was given an image, if we could predict the different attributes we have in the merchandising and we can predict the text embeddings of the comments, then we can kind of build a image vector or image embedding that can capture both descriptions of the clothing and sales of the clothing. And then we would use these additional vectors to augment our recommendation system. And so with the recommendation system really was just around like, what are similar items? What are complimentary items? What are items that you would wear in a single outfit? And being able to say on a product page, let me show you like 15, 20 more things. And then what we found was like, hey, when you turn that on, you make a bunch of money.Swyx [00:05:23]: Yeah. So, okay. So you didn't actually use GPT-3 embeddings. You fine tuned your own? Because I was surprised that GPT-3 worked off the shelf.Jason [00:05:30]: Because I mean, at this point we would have 3 million pieces of inventory over like a billion interactions between users and clothes. So any kind of fine tuning would definitely outperform like some off the shelf model.Swyx [00:05:41]: Cool. I'm about to move on from Stitch Fix, but you know, any other like fun stories from the Stitch Fix days that you want to cover?Jason [00:05:46]: No, I think that's basically it. I mean, the biggest one really was the fact that I think for just four years, I was so bearish on language models and just NLP in general. I'm just like, none of this really works. Like, why would I spend time focusing on this? I got to go do the thing that makes money, recommendations, bounding boxes, image classification. Yeah. Now I'm like prompting an image model. I was like, oh man, I was wrong.Swyx [00:06:06]: So my Stitch Fix question would be, you know, I think you have a bit of a drip and I don't, you know, my primary wardrobe is free startup conference t-shirts. Should more technology brothers be using Stitch Fix? What's your fashion advice?Jason [00:06:19]: Oh man, I mean, I'm not a user of Stitch Fix, right? It's like, I enjoy going out and like touching things and putting things on and trying them on. Right. I think Stitch Fix is a place where you kind of go because you want the work offloaded. I really love the clothing I buy where I have to like, when I land in Japan, I'm doing like a 45 minute walk up a giant hill to find this weird denim shop. That's the stuff that really excites me. But I think the bigger thing that's really captured is this idea that narrative matters a lot to human beings. Okay. And I think the recommendation system, that's really hard to capture. It's easy to use AI to sell like a $20 shirt, but it's really hard for AI to sell like a $500 shirt. But people are buying $500 shirts, you know what I mean? There's definitely something that we can't really capture just yet that we probably will figure out how to in the future.Swyx [00:07:07]: Well, it'll probably output in JSON, which is what we're going to turn to next. Then you went on a sabbatical to South Park Commons in New York, which is unusual because it's based on USF.Jason [00:07:17]: Yeah. So basically in 2020, really, I was enjoying working a lot as I was like building a lot of stuff. This is where we were making like the tens of millions of dollars doing stuff. And then I had a hand injury. And so I really couldn't code anymore for like a year, two years. And so I kind of took sort of half of it as medical leave, the other half I became more of like a tech lead, just like making sure the systems were like lights were on. And then when I went to New York, I spent some time there and kind of just like wound down the tech work, you know, did some pottery, did some jujitsu. And after GPD came out, I was like, oh, I clearly need to figure out what is going on here because something feels very magical. I don't understand it. So I spent basically like five months just prompting and playing around with stuff. And then afterwards, it was just my startup friends going like, hey, Jason, you know, my investors want us to have an AI strategy. Can you help us out? And it just snowballed and bore more and more until I was making this my full time job. Yeah, got it.Swyx [00:08:11]: You know, you had YouTube University and a journaling app, you know, a bunch of other explorations. But it seems like the most productive or the best known thing that came out of your time there was Instructor. Yeah.Jason [00:08:22]: Written on the bullet train in Japan. I think at some point, you know, tools like Guardrails and Marvin came out. Those are kind of tools that I use XML and Pytantic to get structured data out. But they really were doing things sort of in the prompt. And these are built with sort of the instruct models in mind. Like I'd already done that in the past. Right. At Stitch Fix, you know, one of the things we did was we would take a request note and turn that into a JSON object that we would use to send it to our search engine. Right. So if you said like, I want to, you know, skinny jeans that were this size, that would turn into JSON that we would send to our internal search APIs. But it always felt kind of gross. A lot of it is just like you read the JSON, you like parse it, you make sure the names are strings and ages are numbers and you do all this like messy stuff. But when function calling came out, it was very much sort of a new way of doing things. Right. Function calling lets you define the schema separate from the data and the instructions. And what this meant was you can kind of have a lot more complex schemas and just map them in Pytantic. And then you can just keep those very separate. And then once you add like methods, you can add validators and all that kind of stuff. The one thing I really had with a lot of these libraries, though, was it was doing a lot of the string formatting themselves, which was fine when it was the instruction to models. You just have a string. But when you have these new chat models, you have these chat messages. And I just didn't really feel like not being able to access that for the developer was sort of a good benefit that they would get. And so I just said, let me write like the most simple SDK around the OpenAI SDK, a simple wrapper on the SDK, just handle the response model a bit and kind of think of myself more like requests than actual framework that people can use. And so the goal is like, hey, like this is something that you can use to build your own framework. But let me just do all the boring stuff that nobody really wants to do. People want to build their own frameworks, but people don't want to build like JSON parsing.Swyx [00:10:08]: And the retrying and all that other stuff.Jason [00:10:10]: Yeah.Swyx [00:10:11]: Right. We had this a little bit of this discussion before the show, but like that design principle of going for being requests rather than being Django. Yeah. So what inspires you there? This has come from a lot of prior pain. Are there other open source projects that inspired your philosophy here? Yeah.Jason [00:10:25]: I mean, I think it would be requests, right? Like, I think it is just the obvious thing you install. If you were going to go make HTTP requests in Python, you would obviously import requests. Maybe if you want to do more async work, there's like future tools, but you don't really even think about installing it. And when you do install it, you don't think of it as like, oh, this is a requests app. Right? Like, no, this is just Python. The bigger question is, like, a lot of people ask questions like, oh, why isn't requests like in the standard library? Yeah. That's how I want my library to feel, right? It's like, oh, if you're going to use the LLM SDKs, you're obviously going to install instructor. And then I think the second question would be like, oh, like, how come instructor doesn't just go into OpenAI, go into Anthropic? Like, if that's the conversation we're having, like, that's where I feel like I've succeeded. Yeah. It's like, yeah, so standard, you may as well just have it in the base libraries.Alessio [00:11:12]: And the shape of the request stayed the same, but initially function calling was maybe equal structure outputs for a lot of people. I think now the models also support like JSON mode and some of these things and, you know, return JSON or my grandma is going to die. All of that stuff is maybe to decide how have you seen that evolution? Like maybe what's the metagame today? Should people just forget about function calling for structure outputs or when is structure output like JSON mode the best versus not? We'd love to get any thoughts given that you do this every day.Jason [00:11:42]: Yeah, I would almost say these are like different implementations of like the real thing we care about is the fact that now we have typed responses to language models. And because we have that type response, my IDE is a little bit happier. I get autocomplete. If I'm using the response wrong, there's a little red squiggly line. Like those are the things I care about in terms of whether or not like JSON mode is better. I usually think it's almost worse unless you want to spend less money on like the prompt tokens that the function call represents, primarily because with JSON mode, you don't actually specify the schema. So sure, like JSON load works, but really, I care a lot more than just the fact that it is JSON, right? I think function calling gives you a tool to specify the fact like, okay, this is a list of objects that I want and each object has a name or an age and I want the age to be above zero and I want to make sure it's parsed correctly. That's where kind of function calling really shines.Alessio [00:12:30]: Any thoughts on single versus parallel function calling? So I did a presentation at our AI in Action Discord channel, and obviously showcase instructor. One of the big things that we have before with single function calling is like when you're trying to extract lists, you have to make these funky like properties that are lists to then actually return all the objects. How do you see the hack being put on the developer's plate versus like more of this stuff just getting better in the model? And I know you tweeted recently about Anthropic, for example, you know, some lists are not lists or strings and there's like all of these discrepancies.Jason [00:13:04]: I almost would prefer it if it was always a single function call. Obviously, there is like the agents workflows that, you know, Instructor doesn't really support that well, but are things that, you know, ought to be done, right? Like you could define, I think maybe like 50 or 60 different functions in a single API call. And, you know, if it was like get the weather or turn the lights on or do something else, it makes a lot of sense to have these parallel function calls. But in terms of an extraction workflow, I definitely think it's probably more helpful to have everything be a single schema, right? Just because you can sort of specify relationships between these entities that you can't do in a parallel function calling, you can have a single chain of thought before you generate a list of results. Like there's like small like API differences, right? Where if it's for parallel function calling, if you do one, like again, really, I really care about how the SDK looks and says, okay, do I always return a list of functions or do you just want to have the actual object back out and you want to have like auto complete over that object? Interesting.Alessio [00:14:00]: What's kind of the cap for like how many function definitions you can put in where it still works well? Do you have any sense on that?Jason [00:14:07]: I mean, for the most part, I haven't really had a need to do anything that's more than six or seven different functions. I think in the documentation, they support way more. I don't even know if there's any good evals that have over like two dozen function calls. I think if you're running into issues where you have like 20 or 50 or 60 function calls, I think you're much better having those specifications saved in a vector database and then have them be retrieved, right? So if there are 30 tools, like you should basically be like ranking them and then using the top K to do selection a little bit better rather than just like shoving like 60 functions into a single. Yeah.Swyx [00:14:40]: Yeah. Well, I mean, so I think this is relevant now because previously I think context limits prevented you from having more than a dozen tools anyway. And now that we have million token context windows, you know, a cloud recently with their new function calling release said they can handle over 250 tools, which is insane to me. That's, that's a lot. You're saying like, you know, you don't think there's many people doing that. I think anyone with a sort of agent like platform where you have a bunch of connectors, they wouldn't run into that problem. Probably you're right that they should use a vector database and kind of rag their tools. I know Zapier has like a few thousand, like 8,000, 9,000 connectors that, you know, obviously don't fit anywhere. So yeah, I mean, I think that would be it unless you need some kind of intelligence that chains things together, which is, I think what Alessio is coming back to, right? Like there's this trend about parallel function calling. I don't know what I think about that. Anthropic's version was, I think they use multiple tools in sequence, but they're not in parallel. I haven't explored this at all. I'm just like throwing this open to you as to like, what do you think about all these new things? Yeah.Jason [00:15:40]: It's like, you know, do we assume that all function calls could happen in any order? In which case, like we either can assume that, or we can assume that like things need to happen in some kind of sequence as a DAG, right? But if it's a DAG, really that's just like one JSON object that is the entire DAG rather than going like, okay, the order of the function that return don't matter. That's definitely just not true in practice, right? Like if I have a thing that's like turn the lights on, like unplug the power, and then like turn the toaster on or something like the order doesn't matter. And it's unclear how well you can describe the importance of that reasoning to a language model yet. I mean, I'm sure you can do it with like good enough prompting, but I just haven't any use cases where the function sequence really matters. Yeah.Alessio [00:16:18]: To me, the most interesting thing is the models are better at picking than your ranking is usually. Like I'm incubating a company around system integration. For example, with one system, there are like 780 endpoints. And if you're actually trying to do vector similarity, it's not that good because the people that wrote the specs didn't have in mind making them like semantically apart. You know, they're kind of like, oh, create this, create this, create this. Versus when you give it to a model, like in Opus, you put them all, it's quite good at picking which ones you should actually run. And I'm curious to see if the model providers actually care about some of those workflows or if the agent companies are actually going to build very good rankers to kind of fill that gap.Jason [00:16:58]: Yeah. My money is on the rankers because you can do those so easily, right? You could just say, well, given the embeddings of my search query and the embeddings of the description, I can just train XGBoost and just make sure that I have very high like MRR, which is like mean reciprocal rank. And so the only objective is to make sure that the tools you use are in the top end filtered. Like that feels super straightforward and you don't have to actually figure out how to fine tune a language model to do tool selection anymore. Yeah. I definitely think that's the case because for the most part, I imagine you either have like less than three tools or more than a thousand. I don't know what kind of company said, oh, thank God we only have like 185 tools and this works perfectly, right? That's right.Alessio [00:17:39]: And before we maybe move on just from this, it was interesting to me, you retweeted this thing about Anthropic function calling and it was Joshua Brown's retweeting some benchmark that it's like, oh my God, Anthropic function calling so good. And then you retweeted it and then you tweeted it later and it's like, it's actually not that good. What's your flow? How do you actually test these things? Because obviously the benchmarks are lying, right? Because the benchmarks say it's good and you said it's bad and I trust you more than the benchmark. How do you think about that? And then how do you evolve it over time?Jason [00:18:09]: It's mostly just client data. I actually have been mostly busy with enough client work that I haven't been able to reproduce public benchmarks. And so I can't even share some of the results in Anthropic. I would just say like in production, we have some pretty interesting schemas where it's like iteratively building lists where we're doing like updates of lists, like we're doing in place updates. So like upserts and inserts. And in those situations we're like, oh yeah, we have a bunch of different parsing errors. Numbers are being returned to strings. We were expecting lists of objects, but we're getting strings that are like the strings of JSON, right? So we had to call JSON parse on individual elements. Overall, I'm like super happy with the Anthropic models compared to the OpenAI models. Sonnet is very cost effective. Haiku is in function calling, it's actually better, but I think they just had to sort of file down the edges a little bit where like our tests pass, but then we actually deployed a production. We got half a percent of traffic having issues where if you ask for JSON, it'll try to talk to you. Or if you use function calling, you know, we'll have like a parse error. And so I think that definitely gonna be things that are fixed in like the upcoming weeks. But in terms of like the reasoning capabilities, man, it's hard to beat like 70% cost reduction, especially when you're building consumer applications, right? If you're building something for consultants or private equity, like you're charging $400, it doesn't really matter if it's a dollar or $2. But for consumer apps, it makes products viable. If you can go from four to Sonnet, you might actually be able to price it better. Yeah.Swyx [00:19:31]: I had this chart about the ELO versus the cost of all the models. And you could put trend graphs on each of those things about like, you know, higher ELO equals higher cost, except for Haiku. Haiku kind of just broke the lines, or the ISO ELOs, if you want to call it. Cool. Before we go too far into your opinions on just the overall ecosystem, I want to make sure that we map out the surface area of Instructor. I would say that most people would be familiar with Instructor from your talks and your tweets and all that. You had the number one talk from the AI Engineer Summit.Jason [00:20:03]: Two Liu. Jason Liu and Jerry Liu. Yeah.Swyx [00:20:06]: Yeah. Until I actually went through your cookbook, I didn't realize the surface area. How would you categorize the use cases? You have LLM self-critique, you have knowledge graphs in here, you have PII data sanitation. How do you characterize to people what is the surface area of Instructor? Yeah.Jason [00:20:23]: This is the part that feels crazy because really the difference is LLMs give you strings and Instructor gives you data structures. And once you get data structures, again, you can do every lead code problem you ever thought of. Right. And so I think there's a couple of really common applications. The first one obviously is extracting structured data. This is just be, okay, well, like I want to put in an image of a receipt. I want to give it back out a list of checkout items with a price and a fee and a coupon code or whatever. That's one application. Another application really is around extracting graphs out. So one of the things we found out about these language models is that not only can you define nodes, it's really good at figuring out what are nodes and what are edges. And so we have a bunch of examples where, you know, not only do I extract that, you know, this happens after that, but also like, okay, these two are dependencies of another task. And you can do, you know, extracting complex entities that have relationships. Given a story, for example, you could extract relationships of families across different characters. This can all be done by defining a graph. The last really big application really is just around query understanding. The idea is that like any API call has some schema and if you can define that schema ahead of time, you can use a language model to resolve a request into a much more complex request. One that an embedding could not do. So for example, I have a really popular post called like rag is more than embeddings. And effectively, you know, if I have a question like this, what was the latest thing that happened this week? That embeds to nothing, right? But really like that query should just be like select all data where the date time is between today and today minus seven days, right? What if I said, how did my writing change between this month and last month? Again, embeddings would do nothing. But really, if you could do like a group by over the month and a summarize, then you could again like do something much more interesting. And so this really just calls out the fact that embeddings really is kind of like the lowest hanging fruit. And using something like instructor can really help produce a data structure. And then you can just use your computer science and reason about the data structure. Maybe you say, okay, well, I'm going to produce a graph where I want to group by each month and then summarize them jointly. You can do that if you know how to define this data structure. Yeah.Swyx [00:22:29]: So you kind of run up against like the LangChains of the world that used to have that. They still do have like the self querying, I think they used to call it when we had Harrison on in our episode. How do you see yourself interacting with the other LLM frameworks in the ecosystem? Yeah.Jason [00:22:42]: I mean, if they use instructor, I think that's totally cool. Again, it's like, it's just Python, right? It's like asking like, oh, how does like Django interact with requests? Well, you just might make a request.get in a Django app, right? But no one would say, I like went off of Django because I'm using requests now. They should be ideally like sort of the wrong comparison in terms of especially like the agent workflows. I think the real goal for me is to go down like the LLM compiler route, which is instead of doing like a react type reasoning loop. I think my belief is that we should be using like workflows. If we do this, then we always have a request and a complete workflow. We can fine tune a model that has a better workflow. Whereas it's hard to think about like, how do you fine tune a better react loop? Yeah. You always train it to have less looping, in which case like you wanted to get the right answer the first time, in which case it was a workflow to begin with, right?Swyx [00:23:31]: Can you define workflow? Because I used to work at a workflow company, but I'm not sure this is a good term for everybody.Jason [00:23:36]: I'm thinking workflow in terms of like the prefect Zapier workflow. Like I want to build a DAG, I want you to tell me what the nodes and edges are. And then maybe the edges are also put in with AI. But the idea is that like, I want to be able to present you the entire plan and then ask you to fix things as I execute it, rather than going like, hey, I couldn't parse the JSON, so I'm going to try again. I couldn't parse the JSON, I'm going to try again. And then next thing you know, you spent like $2 on opening AI credits, right? Yeah. Whereas with the plan, you can just say, oh, the edge between node like X and Y does not run. Let me just iteratively try to fix that, fix the one that sticks, go on to the next component. And obviously you can get into a world where if you have enough examples of the nodes X and Y, maybe you can use like a vector database to find a good few shot examples. You can do a lot if you sort of break down the problem into that workflow and executing that workflow, rather than looping and hoping the reasoning is good enough to generate the correct output. Yeah.Swyx [00:24:35]: You know, I've been hammering on Devon a lot. I got access a couple of weeks ago. And obviously for simple tasks, it does well. For the complicated, like more than 10, 20 hour tasks, I can see- That's a crazy comparison.Jason [00:24:47]: We used to talk about like three, four loops. Only once it gets to like hour tasks, it's hard.Swyx [00:24:54]: Yeah. Less than an hour, there's nothing.Jason [00:24:57]: That's crazy.Swyx [00:24:58]: I mean, okay. Maybe my goalposts have shifted. I don't know. That's incredible.Jason [00:25:02]: Yeah. No, no. I'm like sub one minute executions. Like the fact that you're talking about 10 hours is incredible.Swyx [00:25:08]: I think it's a spectrum. I think I'm going to say this every single time I bring up Devon. Let's not reward them for taking longer to do things. Do you know what I mean? I think that's a metric that is easily abusable.Jason [00:25:18]: Sure. Yeah. You know what I mean? But I think if you can monotonically increase the success probability over an hour, that's winning to me. Right? Like obviously if you run an hour and you've made no progress. Like I think when we were in like auto GBT land, there was that one example where it's like, I wanted it to like buy me a bicycle overnight. I spent $7 on credit and I never found the bicycle. Yeah.Swyx [00:25:41]: Yeah. Right. I wonder if you'll be able to purchase a bicycle. Because it actually can do things in real world. It just needs to suspend to you for off and stuff. The point I was trying to make was that I can see it turning plans. I think one of the agents loopholes or one of the things that is a real barrier for agents is LLMs really like to get stuck into a lane. And you know what you're talking about, what I've seen Devon do is it gets stuck in a lane and it will just kind of change plans based on the performance of the plan itself. And it's kind of cool.Jason [00:26:05]: I feel like we've gone too much in the looping route and I think a lot of more plans and like DAGs and data structures are probably going to come back to help fill in some holes. Yeah.Alessio [00:26:14]: What do you think of the interface to that? Do you see it's like an existing state machine kind of thing that connects to the LLMs, the traditional DAG players? Do you think we need something new for like AI DAGs?Jason [00:26:25]: Yeah. I mean, I think that the hard part is going to be describing visually the fact that this DAG can also change over time and it should still be allowed to be fuzzy. I think in like mathematics, we have like plate diagrams and like Markov chain diagrams and like recurrent states and all that. Some of that might come into this workflow world. But to be honest, I'm not too sure. I think right now, the first steps are just how do we take this DAG idea and break it down to modular components that we can like prompt better, have few shot examples for and ultimately like fine tune against. But in terms of even the UI, it's hard to say what it will likely win. I think, you know, people like Prefect and Zapier have a pretty good shot at doing a good job.Swyx [00:27:03]: Yeah. You seem to use Prefect a lot. I actually worked at a Prefect competitor at Temporal and I'm also very familiar with Dagster. What else would you call out as like particularly interesting in the AI engineering stack?Jason [00:27:13]: Man, I almost use nothing. I just use Cursor and like PyTests. Okay. I think that's basically it. You know, a lot of the observability companies have... The more observability companies I've tried, the more I just use Postgres.Swyx [00:27:29]: Really? Okay. Postgres for observability?Jason [00:27:32]: But the issue really is the fact that these observability companies isn't actually doing observability for the system. It's just doing the LLM thing. Like I still end up using like Datadog or like, you know, Sentry to do like latency. And so I just have those systems handle it. And then the like prompt in, prompt out, latency, token costs. I just put that in like a Postgres table now.Swyx [00:27:51]: So you don't need like 20 funded startups building LLM ops? Yeah.Jason [00:27:55]: But I'm also like an old, tired guy. You know what I mean? Like I think because of my background, it's like, yeah, like the Python stuff, I'll write myself. But you know, I will also just use Vercel happily. Yeah. Yeah. So I'm not really into that world of tooling, whereas I think, you know, I spent three good years building observability tools for recommendation systems. And I was like, oh, compared to that, Instructor is just one call. I just have to put time star, time and then count the prompt token, right? Because I'm not doing a very complex looping behavior. I'm doing mostly workflows and extraction. Yeah.Swyx [00:28:26]: I mean, while we're on this topic, we'll just kind of get this out of the way. You famously have decided to not be a venture backed company. You want to do the consulting route. The obvious route for someone as successful as Instructor is like, oh, here's hosted Instructor with all tooling. Yeah. You just said you had a whole bunch of experience building observability tooling. You have the perfect background to do this and you're not.Jason [00:28:43]: Yeah. Isn't that sick? I think that's sick.Swyx [00:28:44]: I mean, I know why, because you want to go free dive.Jason [00:28:47]: Yeah. Yeah. Because I think there's two things. Right. Well, one, if I tell myself I want to build requests, requests is not a venture backed startup. Right. I mean, one could argue whether or not Postman is, but I think for the most part, it's like having worked so much, I'm more interested in looking at how systems are being applied and just having access to the most interesting data. And I think I can do that more through a consulting business where I can come in and go, oh, you want to build perfect memory. You want to build an agent. You want to build like automations over construction or like insurance and supply chain, or like you want to handle writing private equity, mergers and acquisitions reports based off of user interviews. Those things are super fun. Whereas like maintaining the library, I think is mostly just kind of like a utility that I try to keep up, especially because if it's not venture backed, I have no reason to sort of go down the route of like trying to get a thousand integrations. In my mind, I just go like, okay, 98% of the people use open AI. I'll support that. And if someone contributes another platform, that's great. I'll merge it in. Yeah.Swyx [00:29:45]: I mean, you only added Anthropic support this year. Yeah.Jason [00:29:47]: Yeah. You couldn't even get an API key until like this year, right? That's true. Okay. If I add it like last year, I was trying to like double the code base to service, you know, half a percent of all downloads.Swyx [00:29:58]: Do you think the market share will shift a lot now that Anthropic has like a very, very competitive offering?Jason [00:30:02]: I think it's still hard to get API access. I don't know if it's fully GA now, if it's GA, if you can get a commercial access really easily.Alessio [00:30:12]: I got commercial after like two weeks to reach out to their sales team.Jason [00:30:14]: Okay.Alessio [00:30:15]: Yeah.Swyx [00:30:16]: Two weeks. It's not too bad. There's a call list here. And then anytime you run into rate limits, just like ping one of the Anthropic staff members.Jason [00:30:21]: Yeah. Then maybe we need to like cut that part out. So I don't need to like, you know, spread false news.Swyx [00:30:25]: No, it's cool. It's cool.Jason [00:30:26]: But it's a common question. Yeah. Surely just from the price perspective, it's going to make a lot of sense. Like if you are a business, you should totally consider like Sonnet, right? Like the cost savings is just going to justify it if you actually are doing things at volume. And yeah, I think the SDK is like pretty good. Back to the instructor thing. I just don't think it's a billion dollar company. And I think if I raise money, the first question is going to be like, how are you going to get a billion dollar company? And I would just go like, man, like if I make a million dollars as a consultant, I'm super happy. I'm like more than ecstatic. I can have like a small staff of like three people. It's fun. And I think a lot of my happiest founder friends are those who like raised a tiny seed round, became profitable. They're making like 70, 60, 70, like MRR, 70,000 MRR and they're like, we don't even need to raise the seed round. Let's just keep it like between me and my co-founder, we'll go traveling and it'll be a great time. I think it's a lot of fun.Alessio [00:31:15]: Yeah. like say LLMs / AI and they build some open source stuff and it's like I should just raise money and do this and I tell people a lot it's like look you can make a lot more money doing something else than doing a startup like most people that do a company could make a lot more money just working somewhere else than the company itself do you have any advice for folks that are maybe in a similar situation they're trying to decide oh should I stay in my like high paid FAANG job and just tweet this on the side and do this on github should I go be a consultant like being a consultant seems like a lot of work so you got to talk to all these people you know there's a lot to unpackJason [00:31:54]: I think the open source thing is just like well I'm just doing it purely for fun and I'm doing it because I think I'm right but part of being right is the fact that it's not a venture backed startup like I think I'm right because this is all you need right so I think a part of the philosophy is the fact that all you need is a very sharp blade to sort of do your work and you don't actually need to build like a big enterprise so that's one thing I think the other thing too that I've kind of been thinking around just because I have a lot of friends at google that want to leave right now it's like man like what we lack is not money or skill like what we lack is courage you should like you just have to do this a hard thing and you have to do it scared anyways right in terms of like whether or not you do want to do a founder I think that's just a matter of optionality but I definitely recognize that the like expected value of being a founder is still quite low it is right I know as many founder breakups and as I know friends who raised a seed round this year right like that is like the reality and like you know even in from that perspective it's been tough where it's like oh man like a lot of incubators want you to have co-founders now you spend half the time like fundraising and then trying to like meet co-founders and find co-founders rather than building the thing this is a lot of time spent out doing uh things I'm not really good at. I do think there's a rising trend in solo founding yeah.Swyx [00:33:06]: You know I am a solo I think that something like 30 percent of like I forget what the exact status something like 30 percent of starters that make it to like series B or something actually are solo founder I feel like this must have co-founder idea mostly comes from YC and most everyone else copies it and then plenty of companies break up over co-founderJason [00:33:27]: Yeah and I bet it would be like I wonder how much of it is the people who don't have that much like and I hope this is not a diss to anybody but it's like you sort of you go through the incubator route because you don't have like the social equity you would need is just sort of like send an email to Sequoia and be like hey I'm going on this ride you want a ticket on the rocket ship right like that's very hard to sell my message if I was to raise money is like you've seen my twitter my life is sick I've decided to make it much worse by being a founder because this is something I have to do so do you want to come along otherwise I want to fund it myself like if I can't say that like I don't need the money because I can like handle payroll and like hire an intern and get an assistant like that's all fine but I really don't want to go back to meta I want to like get two years to like try to find a problem we're solving that feels like a bad timeAlessio [00:34:12]: Yeah Jason is like I wear a YSL jacket on stage at AI Engineer Summit I don't need your accelerator moneyJason [00:34:18]: And boots, you don't forget the boots. But I think that is a part of it right I think it is just like optionality and also just like I'm a lot older now I think 22 year old Jason would have been probably too scared and now I'm like too wise but I think it's a matter of like oh if you raise money you have to have a plan of spending it and I'm just not that creative with spending that much money yeah I mean to be clear you just celebrated your 30th birthday happy birthday yeah it's awesome so next week a lot older is relative to some some of the folks I think seeing on the career tipsAlessio [00:34:48]: I think Swix had a great post about are you too old to get into AI I saw one of your tweets in January 23 you applied to like Figma, Notion, Cohere, Anthropic and all of them rejected you because you didn't have enough LLM experience I think at that time it would be easy for a lot of people to say oh I kind of missed the boat you know I'm too late not gonna make it you know any advice for people that feel like thatJason [00:35:14]: Like the biggest learning here is actually from a lot of folks in jiu-jitsu they're like oh man like is it too late to start jiu-jitsu like I'll join jiu-jitsu once I get in more shape right it's like there's a lot of like excuses and then you say oh like why should I start now I'll be like 45 by the time I'm any good and say well you'll be 45 anyways like time is passing like if you don't start now you start tomorrow you're just like one more day behind if you're worried about being behind like today is like the soonest you can start right and so you got to recognize that like maybe you just don't want it and that's fine too like if you wanted you would have started I think a lot of these people again probably think of things on a too short time horizon but again you know you're gonna be old anyways you may as well just start now you knowSwyx [00:35:55]: One more thing on I guess the um career advice slash sort of vlogging you always go viral for this post that you wrote on advice to young people and the lies you tell yourself oh yeah yeah you said you were writing it for your sister.Jason [00:36:05]: She was like bummed out about going to college and like stressing about jobs and I was like oh and I really want to hear okay and I just kind of like text-to-sweep the whole thing it's crazy it's got like 50,000 views like I'm mind I mean your average tweet has more but that thing is like a 30-minute read nowSwyx [00:36:26]: So there's lots of stuff here which I agree with I you know I'm also of occasionally indulge in the sort of life reflection phase there's the how to be lucky there's the how to have high agency I feel like the agency thing is always a trend in sf or just in tech circles how do you define having high agencyJason [00:36:42]: I'm almost like past the high agency phase now now my biggest concern is like okay the agency is just like the norm of the vector what also matters is the direction right it's like how pure is the shot yeah I mean I think agency is just a matter of like having courage and doing the thing that's scary right you know if people want to go rock climbing it's like do you decide you want to go rock climbing then you show up to the gym you rent some shoes and you just fall 40 times or do you go like oh like I'm actually more intelligent let me go research the kind of shoes that I want okay like there's flatter shoes and more inclined shoes like which one should I get okay let me go order the shoes on Amazon I'll come back in three days like oh it's a little bit too tight maybe it's too aggressive I'm only a beginner let me go change no I think the higher agent person just like goes and like falls down 20 times right yeah I think the higher agency person is more focused on like process metrics versus outcome metrics right like from pottery like one thing I learned was if you want to be good at pottery you shouldn't count like the number of cups or bowls you make you should just weigh the amount of clay you use right like the successful person says oh I went through 100 pounds of clay right the less agency was like oh I've made six cups and then after I made six cups like there's not really what are you what do you do next no just pounds of clay pounds of clay same with the work here right so you just got to write the tweets like make the commits contribute open source like write the documentation there's no real outcome it's just a process and if you love that process you just get really good at the thing you're doingSwyx [00:38:04]: yeah so just to push back on this because obviously I mostly agree how would you design performance review systems because you were effectively saying we can count lines of code for developers rightJason [00:38:15]: I don't think that would be the actual like I think if you make that an outcome like I can just expand a for loop right I think okay so for performance review this is interesting because I've mostly thought of it from the perspective of science and not engineering I've been running a lot of engineering stand-ups primarily because there's not really that many machine learning folks the process outcome is like experiments and ideas right like if you think about outcome is what you might want to think about an outcome is oh I want to improve the revenue or whatnot but that's really hard but if you're someone who is going out like okay like this week I want to come up with like three or four experiments I might move the needle okay nothing worked to them they might think oh nothing worked like I suck but to me it's like wow you've closed off all these other possible avenues for like research like you're gonna get to the place that you're gonna figure out that direction really soon there's no way you try 30 different things and none of them work usually like 10 of them work five of them work really well two of them work really really well and one thing was like the nail in the head so agency lets you sort of capture the volume of experiments and like experience lets you figure out like oh that other half it's not worth doing right I think experience is going like half these prompting papers don't make any sense just use chain of thought and just you know use a for loop that's basically right it's like usually performance for me is around like how many experiments are you running how oftentimes are you trying.Alessio [00:39:32]: When do you give up on an experiment because a StitchFix you kind of give up on language models I guess in a way as a tool to use and then maybe the tools got better you were right at the time and then the tool improved I think there are similar paths in my engineering career where I try one approach and at the time it doesn't work and then the thing changes but then I kind of soured on that approach and I don't go back to it soonJason [00:39:51]: I see yeah how do you think about that loop so usually when I'm coaching folks and as they say like oh these things don't work I'm not going to pursue them in the future like one of the big things like hey the negative result is a result and this is something worth documenting like this is an academia like if it's negative you don't just like not publish right but then like what do you actually write down like what you should write down is like here are the conditions this is the inputs and the outputs we tried the experiment on and then one thing that's really valuable is basically writing down under what conditions would I revisit these experiments these things don't work because of what we had at the time if someone is reading this two years from now under what conditions will we try again that's really hard but again that's like another skill you kind of learn right it's like you do go back and you do experiments you figure out why it works now I think a lot of it here is just like scaling worked yeah rap lyrics you know that was because I did not have high enough quality data if we phase shift and say okay you don't even need training data oh great then it might just work a different domainAlessio [00:40:48]: Do you have anything in your list that is like it doesn't work now but I want to try it again later? Something that people should maybe keep in mind you know people always like agi when you know when are you going to know the agi is here maybe it's less than that but any stuff that you tried recently that didn't work thatJason [00:41:01]: You think will get there I mean I think the personal assistance and the writing I've shown to myself it's just not good enough yet so I hired a writer and I hired a personal assistant so now I'm gonna basically like work with these people until I figure out like what I can actually like automate and what are like the reproducible steps but like I think the experiment for me is like I'm gonna go pay a person like thousand dollars a month that helped me improve my life and then let me get them to help me figure like what are the components and how do I actually modularize something to get it to work because it's not just like a lot gmail calendar and like notion it's a little bit more complicated than that but we just don't know what that is yet those are two sort of systems that I wish gb4 or opus was actually good enough to just write me an essay but most of the essays are still pretty badSwyx [00:41:44]: yeah I would say you know on the personal assistance side Lindy is probably the one I've seen the most flow was at a speaker at the summit I don't know if you've checked it out or any other sort of agents assistant startupJason [00:41:54]: Not recently I haven't tried lindy they were not ga last time I was considering it yeah yeah a lot of it now it's like oh like really what I want you to do is take a look at all of my meetings and like write like a really good weekly summary email for my clients to remind them that I'm like you know thinking of them and like working for them right or it's like I want you to notice that like my monday is like way too packed and like block out more time and also like email the people to do the reschedule and then try to opt in to move them around and then I want you to say oh jason should have like a 15 minute prep break after form back to back those are things that now I know I can prompt them in but can it do it well like before I didn't even know that's what I wanted to prompt for us defragging a calendar and adding break so I can like eat lunch yeah that's the AGI test yeah exactly compassion right I think one thing that yeah we didn't touch on it before butAlessio [00:42:44]: I think was interesting you had this tweet a while ago about prompts should be code and then there were a lot of companies trying to build prompt engineering tooling kind of trying to turn the prompt into a more structured thing what's your thought today now you want to turn the thinking into DAGs like do prompts should still be code any updated ideasJason [00:43:04]: It's the same thing right I think you know with Instructor it is very much like the output model is defined as a code object that code object is sent to the LLM and in return you get a data structure so the outputs of these models I think should also be code objects and the inputs somewhat should be code objects but I think the one thing that instructor tries to do is separate instruction data and the types of the output and beyond that I really just think that most of it should be still like managed pretty closely to the developer like so much of is changing that if you give control of these systems away too early you end up ultimately wanting them back like many companies I know that I reach out or ones were like oh we're going off of the frameworks because now that we know what the business outcomes we're trying to optimize for these frameworks don't work yeah because we do rag but we want to do rag to like sell you supplements or to have you like schedule the fitness appointment the prompts are kind of too baked into the systems to really pull them back out and like start doing upselling or something it's really funny but a lot of it ends up being like once you understand the business outcomes you care way more about the promptSwyx [00:44:07]: Actually this is fun in our prep for this call we were trying to say like what can you as an independent person say that maybe me and Alessio cannot say or me you know someone at a company say what do you think is the market share of the frameworks the LangChain, the LlamaIndex, the everything...Jason [00:44:20]: Oh massive because not everyone wants to care about the code yeah right I think that's a different question to like what is the business model and are they going to be like massively profitable businesses right making hundreds of millions of dollars that feels like so straightforward right because not everyone is a prompt engineer like there's so much productivity to be captured in like back office optim automations right it's not because they care about the prompts that they care about managing these things yeah but those would be sort of low code experiences you yeah I think the bigger challenge is like okay hundred million dollars probably pretty easy it's just time and effort and they have the manpower and the money to sort of solve those problems again if you go the vc route then it's like you're talking about billions and that's really the goal that stuff for me it's like pretty unclear but again that is to say that like I sort of am building things for developers who want to use infrastructure to build their own tooling in terms of the amount of developers there are in the world versus downstream consumers of these things or even just think of how many companies will use like the adobes and the ibms right because they want something that's fully managed and they want something that they know will work and if the incremental 10% requires you to hire another team of 20 people you might not want to do it and I think that kind of organization is really good for uh those are bigger companiesSwyx [00:45:32]: I just want to capture your thoughts on one more thing which is you said you wanted most of the prompts to stay close to the developer and Hamel Husain wrote this post which I really love called f you show me the prompt yeah I think he cites you in one of those part of the blog post and I think ds pi is kind of like the complete antithesis of that which is I think it's interesting because I also hold the strong view that AI is a better prompt engineer than you are and I don't know how to square that wondering if you have thoughtsJason [00:45:58]: I think something like DSPy can work because there are like very short-term metrics to measure success right it is like did you find the pii or like did you write the multi-hop question the correct way but in these workflows that I've been managing a lot of it are we minimizing churn and maximizing retention yeah that's a very long loop it's not really like a uptuna like training loop right like those things are much more harder to capture so we don't actually have those metrics for that right and obviously we can figure out like okay is the summary good but like how do you measure the quality of the summary it's like that feedback loop it ends up being a lot longer and then again when something changes it's really hard to make sure that it works across these like newer models or again like changes to work for the current process like when we migrate from like anthropic to open ai like there's just a ton of change that are like infrastructure related not necessarily around the prompt itself yeah cool any other ai engineering startups that you think should not exist before we wrap up i mean oh my gosh i mean a lot of it again it's just like every time of investors like how does this make a billion dollars like it doesn't i'm gonna go back to just like tweeting and holding my breath underwater yeah like i don't really pay attention too much to most of this like most of the stuff i'm doing is around like the consumer of like llm calls yep i think people just want to move really fast and they will end up pick these vendors but i don't really know if anything has really like blown me out the water like i only trust myself but that's also a function of just being an old man like i think you know many companies are definitely very happy with using most of these tools anyways but i definitely think i occupy a very small space in the engineering ecosystem.Swyx [00:47:41]: Yeah i would say one of the challenges here you know you call about the dealing in the consumer of llm's space i think that's what ai engineering differs from ml engineering and i think a constant disconnect or cognitive dissonance in this field in the ai engineers that have sprung up is that they are not as good as the ml engineers they are not as qualified i think that you know you are someone who has credibility in the mle space and you are also a very authoritative figure in the ai space and i think so and you know i think you've built the de facto leading library i think yours i think instructors should be part of the standard lib even though i try to not use it like i basically also end up rebuilding instructor right like that's a lot of the back and forth that we had over the past two days i think that's the fundamental thing that we're trying to figure out like there's very small supply of MLEs not everyone's going to have that experience that you had but the global demand for AI is going to far outstrip the existing MLEs.Jason [00:48:36]: So what do we do do we force everyone to go through the standard MLE curriculum or do we make a new one? I'

Sometimes we loop (repeat lessons) until we finally surrender to what is and stop playing the victim. Nobody has to do it alone, we all need a village, children and adults -so let me be a part of that village and let me help you. It would be an honor to support you. Reach out on empoweredmajestyteam.com and be on the lookout for self-paced courses on Shadow Work and Finding Harmony in Your Life. Thank you for your listenership. Send your listener letters to truelessonspodcast@gmail.com Love this podcast? Share! Rate & Review. Help others discover this show.

In this eye-opening episode, we dive deep with Chris Lautenslager, the visionary behind The Prosperity Loop, an innovative model poised to revolutionize organizational success. Chris walks us through how his inclusive, self-sustaining formula not only fosters a common purpose and cooperation but also aligns profitability with prosperity, creating a ripple effect of positive change across communities and industries. Listen in as we explore the potential of The Prosperity Loop to redefine business practices for entrepreneurs, CEOs, and employees, aiming for a more balanced life, business, and community. Discover why this is just the beginning of a series of movements from the GET LOOPED organization, destined to transform the very fabric of societal success.

Think about the conversations you have every day. There are the ones you have with your friends over coffee to catch up on life, the ones you have with a family member while walking the dog, and countless others throughout your week. While it may not seem like it, every conversation (yes, even the mundane ones!) is a negotiation, and once we have the skills to know which type of conversation we're in, we can use every single conversation to better connect with those around us.  That's what Charles Duhigg argues in his new book “Supercommunicators: How to Unlock the Secret Language of Connection.” He shares the difference between the three different types of conversation, and why knowing which one we're engaged in can make all the difference.  In Mailbag, a listener asks about the red flags to look out for when choosing a high-interest savings account, and we hear from a retiree who's wondering if they're paying too much for private insurance. In our news of the week, we talk about what the Federal Reserve meeting last week means for your money. Additionally, we explore Unilever's decision to sell Ben & Jerry's, and how some families are handling the rising costs of storing frozen embryos. Takeaways: Every conversation is a negotiation, and understanding the different types of conversations can help improve communication. Asking questions and using techniques like looping for understanding can enhance connection and understanding in conversations. Acknowledging and embracing differences, including gender, can lead to more effective communication. Investing in relationships and conversations is crucial for long-term happiness and success. Chapters 00:00 News You Can Use 05:04 Different Types of Conversations 08:16 Neural Entrainment and Connection 12:34 Asking Questions and Looping for Understanding 30:02 Vulnerability and Gender in Communication 35:58 The Importance of Relationships and Conversations 36:48 Mailbag Join us! Snag all the latest episodes, savvy budgeting tips, investing advice and even giveaways via the HerMoney Newsletter at Hermoney.com/subscribe! The HerMoney with Jean Chatzky podcast is sponsored by Edelman Financial Engines. The podcast team and its host are neither employees nor clients of EFE, however, the show does receive fixed compensation and is a paid endorser and therefore has an incentive to endorse EFE and its planners. To learn more about the sponsorship, please visit PlanEFE.com/HerMoney. Please contact advertising@airwavemedia.com if you would like to advertise on our podcast, and to learn more about Airwave, head to www.airwavemedia.com. Learn more about your ad choices. Visit megaphone.fm/adchoices

#162: Bestselling author Daniel Pink shares science-based tactics to become a better persuader, whether its to sell a product, motivate yourself, or write an email pitch. This episode also addresses the misconception of coercion as persuasion, the significance of information asymmetry, strategies for handling rejection, the surprising truth about extroverts in sales, and so much more. Daniel Pink is the author of several provocative, NYT bestselling books about business, work, creativity, and behavior. His books have won multiple awards, been translated into 44 languages, and sold millions of copies around the world. Link to Full Show Notes: https://allthehacks.com/daniel-pink-persuasion Partner Deals LMNT: Free sample pack of my favorite electrolyte drink mix NetSuite: Free KPI checklist to upgrade your business performance Vuori: 20% off the most comfortable performance apparel I've ever worn Indochino: 10% off my favorite bespoke suits and shirts (with code ALLTHEHACKS) Pique Tea: 15% off delicious teas + a free quiver with 12 tea samples MasterClass: Learn from the world's best with 15% off For all the deals, discounts and promo codes from our partners, go to: allthehacks.com/deals Resources Mentioned Daniel Pink: Website | LinkedIn | Twitter | Newsletter | Podcast Book: To Sell is Human The Washington Post Column: Why Not Masterclass: Daniel Pink Teaches Sales and Persuasion Amanda Ripley: High Conflict Robert B Cialdini: Influence, New and Expanded: The Psychology of Persuasion All the Hacks: Episode #40: The Power of Regret, Motivation and Good Timing with Daniel Pink Leave a review: Apple Podcasts | Spotify Full Show Notes (02:17) Persuasion vs. Coercion (03:49) The Definition of Persuasion (09:02) The Skills Needed to Become Better Persuaders (13:00) What Matters Most in Persuasion: Curating Information (14:46) Tactics to Refine Your Persuasion Skills (18:37) Persuasive Tool: Listen More and Talk Less (24:43) Dealing With Rejection (27:06) Techniques to Handle Rejection: 3P's & 10-10-10 (30:27) Tactics for Better Clarity (32:10) The Most Important Question in Sales and Persuasion (35:04) The Shift From Problem Solving to Problem Framing (36:43) Looping as a Technique to Mitigate Disagreements (41:40) How to Persuade Your Kids Using Motivational Interviewing (44:59) The Importance of Social Proof in Persuasive Encounters (47:48) Daniel's Favorite Decision-Making Heuristics (48:25) Persuasion Tactics for Self-Motivation (50:11) Online Pitching Tactics (51:24) How to Use Utility & Curiosity for Email Pitches (53:05) Daniel's New Column on The Washington Post Connect with All the Hacks All the Hacks: Newsletter | Website | Membership | Email Chris Hutchins: Twitter | Instagram | Website | LinkedIn Editor's Note: The content on this page is accurate as of the posting date; however, some of our partner offers may have expired. Opinions expressed here are the author's alone, not those of any bank, credit card issuer, hotel, airline, or other entity. This content has not been reviewed, approved or otherwise endorsed by any of the entities included within the post. Learn more about your ad choices. Visit megaphone.fm/adchoices

When EconTalk's Russ Roberts sat down with Charles Duhigg to talk about his new book on the art of conversation, Supercommunicators, Roberts tried to apply some of its lessons to his conversation with the author. The result is this special conversation between two people eager to connect and communicate. Enjoy.

This episode is brought to you by Lumebox and AquaTru. We understand that the quality of our relationships and connections within our community leads to a more fulfilling life and promotes happiness. However, communicating authentically and genuinely aren't necessarily traits we're born with or that come naturally. Charles Duhigg is here to show us how we can change the way we communicate, add more meaning to our relationships, and extend our lifespan. Today, on the Dhru Purohit Show, Dhru sits down with author and writer Charles Duhigg to discuss how to become a supercommunicator. Charles shares the top traits that super communicators practice in conversations and how these practices can lead to deeper and more meaningful relationships. He also delves into the science behind how these traits can promote longevity and overall happiness. If you're seeking guidance on becoming a better communicator, even with people you fundamentally disagree with, this episode is for you!Charles Duhigg is the author of The Power of Habit, about the science of habit formation in our lives, companies, and societies, and Smarter Faster Better, about the science of productivity.He currently writes at The New Yorker Magazine, and until a few years ago, was a reporter at the New York Times. There, he wrote “The iEconomy,” which focused on Apple and won a Pulitzer prize for explanatory reporting in 2013. In this episode, Dhru and Charles dive into (audio version / Apple Subscriber version):The top mistakes people make that prevent genuine connection (00:24 / 00:24)Ask yourself, why am I choosing to speak? (3:25 / 3:25) Looping for understanding (6:27 /6:27)Neuro Alignment during conversations (10:09 / 7:58)Listening to learn about the other person (15:57 / 13:53)Acquiring the right tools (23:20 / 21:11)Keywords and demeanor and what they signal (25:37 / 23:30)Words or responses that show a communication disconnect (34:23 / 30:35)Why you should want to be a supercommunicator (39:55 / 35:57) Every conversation is a quiet negotiation (53:45/ 50:02)How to connect with people who have different viewpoints (1:12:00/ 1:08:20)Four rules of a meaningful conversation (1:12:50 / 1:09:10)How super communication manifests to external success (1:24:10 / 1:22:12)Also mentioned in this episode:Charles' new book: Supercommunicators: How to Unlock the Secret Language of ConnectionCharles' substack Hello listeners! I could use your feedback about the podcast. If you click here and answer this question, it would mean the world to me.Lumbeox is offering my community $260 off their FDA-approved portable Red Light device! That's over 50% off! Go to thelumebox.com/dhru and get your Red Light device. AquaTru is a countertop reverse osmosis purifier with a four-stage filtration system that removes 15x more contaminants than the bestselling water filters out there. Go to dhrupurohit.com/filter/ and get $100 off when you try AquaTru for yourself. Hosted on Acast. See acast.com/privacy for more information.

Scott and Wes are joined by security expert, Alex Sexton of Stripe to cover all things: client security, XSS, attack vectors, and CSP (content security policy). Show Notes 00:00 Welcome to Syntax! 00:31 Brought to you by Sentry.io. 00:57 Who is Alex Sexton? 04:44 Stripe dashboard is a work of art. 05:08 Tell us about the design system. React Aria 08:59 Who develops the iOS app? 09:50 Stripe's CSP (content security policy). 12:50 What even is a content security policy? Content Security Policy explanation 13:57 Douglas Crockford of Yahoo on security. Douglas on GitHub 15:13 Security philosophy. 16:59 What about inline styles and inline JavaScript? 19:41 How do we safely set inline styles from JS? 20:20 Setting up with meta tags. 22:52 What are common situations that require security exceptions? 26:24 Potential damage with inline style tags. 32:45 Looping vulnerabilities. 36:32 What about JavaScript injection? 37:09 Myspace Samy Worm. Myspace Samy Worm Wiki Sentry.io Security Policy Reporting 42:02 Does a CSP stop code from running in the console? 43:28 What are some general security best practices? 46:35 Strategies for rolling out a CSP. 51:49 Final tip, Strict Dynamic. Strict Dynamic 56:36 Where does the CSP live within Stripe? Original Black Friday story 59:35 One last story. 01:01:20 Sick Picks + Shameless Plugs Sick Picks + Shameless Plugs Alex: Wes Bos' Instagram Hit us up on Socials! Syntax: X Instagram Tiktok LinkedIn Threads Wes: X Instagram Tiktok LinkedIn Threads Scott:X Instagram Tiktok LinkedIn Threads Randy: X Instagram YouTube Threads

In this episode of "The Good Life", @taylorawelch shares with us a snippet from an event called the " Relentless Summit" where he was a guest speaker. In this clip, he talks about the intricacies of belief systems and their profound impact on our thoughts and actions. Exploring how beliefs influence our reactions to situations like traffic jams and stressful meetings, Taylor navigates the complexities of the mind's response mechanisms. With insights into the concept of "looping" and the architecture of belief, we will gain a deeper understanding of how to reprogram their minds for success and positivity.IF you enjoyed the show please leave us a review to help push this message to more listeners around the world!Please visit Taylorawelch.com to access all of Taylor's socials and content Text Taylor: 615-326-5037Daily Mind Medicine is back!Chapters: (00:38) Looping patterns(02:38) Understanding beliefs and their influence(03:49) Looping and pre-programming of reactions(05:48) Belief architecture and its impact on outcomes

Looping thoughts about people you barely know, or don't know at all.  Prologue: We get a tip that an entire town is consumed by a huge, elementary-school-style crush on a local veterinarian. Guest host Lilly Sullivan goes to Utah to investigate the mystery of the hot vet. (8 minutes)Act One: We do the thing the people in town would rather die than do – spill the crush to the legendary Dr. Artz himself. Lilly Sullivan reports. (8 minutes)Act Two: Producer Alix Spiegel talks to one of her closest friends, Sarah Blust, about the time Sarah met a stranger who, unbeknownst to her, had already spent years thinking about her. (29 minutes)Act Three: There are certain jobs where thinking about someone else's life is just built into it. Aviva DeKornfeld has a theory that petsitting is a job like that. She talks to a couple of pet sitters to find out. (14 minutes)Transcripts are available at thisamericanlife.org