Podcasts about Eno

Naša življenja zaznamujejo različna čustvena stanja. Eno izmed teh je jeza. Jezi nas lahko zelo veliko stvari: od odnosov do ljudi, s katerimi težko krmarimo skozi vsakdanjik, ampak moramo, do novic, družbene klime in dejstva, da nekaj ne gre po naših načrtih. Jeza ni le razdiralen, negativen odziv na dogajanje, je zapisano v knjigi psihoterapevtskega para Leonide in Alberta Mrgoleta z naslovom Z jezo na lepše. Knjiga bralca vodi do razumevanja, kaj jezo povzroči in kakšni procesi pri tem nastajajo, pa tudi v regulacijo jeze, ki ima vsesplošen pozitiven učinek. Vsebina knjige prinaša številna praktična, uporabna, hkrati pa strokovno podkovana spoznanja in napotke. Leonido in Alberta Mrgoleta je pred mikrofon povabila Darja Groznik.

Daniel Lanois built a studio in his basement in Quebec and began producing local acts when a teenager. Through work with Brian Eno, he went on to record U2, Bob Dylan, Arcade Fire, Emmylou Harris and scores of others with a method that's unique, cinematic and utterly extraordinary, a brand of sonic architecture that creates settings to accommodate the songs, often in exotic and stimulating places. And he's made nine albums of his own, the latest the magical instrumental suite ‘Belladonna Nocturne' – “hear this and you may never go home again”. This rich and fascinating conversation includes … … how the place you record affects the way you think ... producing Dylan and Willie Nelson in an abandoned Mexican cinema … why the first record he bought was Wipe Out by the Surfaris … the process of “printing sound” and his Music Minus One theory … “Songs are doorways to another dimension” … Eno's working method: “he walked round the studio for 45 minutes ringing bells to map out the length of the album” … drawing song sketches to stop everyone having to crowd round a laptop … making the Unforgettable Fire with U2, “expanding Slane Castle ‘til there were little critters crawling out of the walls!” … conjuring the tropical heat of Robbie Robertson's Somewhere Down the Crazy River … and what Hells' Angels like to do to his music. Order Belladonna Nocturne here: https://artsmusic.lnk.to/BelladonnaNocturneHelp us to keep The Longest Conversation In Rock going: https://www.patreon.com/wordinyourear Hosted on Acast. See acast.com/privacy for more information.

Daniel Lanois built a studio in his basement in Quebec and began producing local acts when a teenager. Through work with Brian Eno, he went on to record U2, Bob Dylan, Arcade Fire, Emmylou Harris and scores of others with a method that's unique, cinematic and utterly extraordinary, a brand of sonic architecture that creates settings to accommodate the songs, often in exotic and stimulating places. And he's made nine albums of his own, the latest the magical instrumental suite ‘Belladonna Nocturne' – “hear this and you may never go home again”. This rich and fascinating conversation includes … … how the place you record affects the way you think ... producing Dylan and Willie Nelson in an abandoned Mexican cinema … why the first record he bought was Wipe Out by the Surfaris … the process of “printing sound” and his Music Minus One theory … “Songs are doorways to another dimension” … Eno's working method: “he walked round the studio for 45 minutes ringing bells to map out the length of the album” … drawing song sketches to stop everyone having to crowd round a laptop … making the Unforgettable Fire with U2, “expanding Slane Castle ‘til there were little critters crawling out of the walls!” … conjuring the tropical heat of Robbie Robertson's Somewhere Down the Crazy River … and what Hells' Angels like to do to his music. Order Belladonna Nocturne here: https://artsmusic.lnk.to/BelladonnaNocturneHelp us to keep The Longest Conversation In Rock going: https://www.patreon.com/wordinyourearHelp us to keep The Longest Continuous Conversation In Rock'n'Roll going: https://www.patreon.com/wordinyourear Hosted on Acast. See acast.com/privacy for more information.

Daniel Lanois built a studio in his basement in Quebec and began producing local acts when a teenager. Through work with Brian Eno, he went on to record U2, Bob Dylan, Arcade Fire, Emmylou Harris and scores of others with a method that's unique, cinematic and utterly extraordinary, a brand of sonic architecture that creates settings to accommodate the songs, often in exotic and stimulating places. And he's made nine albums of his own, the latest the magical instrumental suite ‘Belladonna Nocturne' – “hear this and you may never go home again”. This rich and fascinating conversation includes … … how the place you record affects the way you think ... producing Dylan and Willie Nelson in an abandoned Mexican cinema … why the first record he bought was Wipe Out by the Surfaris … the process of “printing sound” and his Music Minus One theory … “Songs are doorways to another dimension” … Eno's working method: “he walked round the studio for 45 minutes ringing bells to map out the length of the album” … drawing song sketches to stop everyone having to crowd round a laptop … making the Unforgettable Fire with U2, “expanding Slane Castle ‘til there were little critters crawling out of the walls!” … conjuring the tropical heat of Robbie Robertson's Somewhere Down the Crazy River … and what Hells' Angels like to do to his music. Order Belladonna Nocturne here: https://artsmusic.lnk.to/BelladonnaNocturneHelp us to keep The Longest Conversation In Rock going: https://www.patreon.com/wordinyourearHelp us to keep The Longest Continuous Conversation In Rock'n'Roll going: https://www.patreon.com/wordinyourear Hosted on Acast. See acast.com/privacy for more information.

Thank you to Eno, Sian and David for sending in your stories! Visit our WEBSITE Subscribe to our PATREON Subscribe to our YOUTUBE CHANNELVisit our MERCH STORE Hosted on Acast. See acast.com/privacy for more information.

Ian did not commit a sports sin last night, abstaining from the NBA. There's plenty to talk about with the Mariners, specifically with JP Crawford making his own decision to move to third base. Eddie Olczyk, National NHL Analyst joins Ian to give us a look at the NHL playoffs as a whole and where the Kraken are heading in their future. Edzo says Seattle needs a star, and they don't have one right now. Mariners and piggyback! JP Crawford is willing to move positions to stay with the Mariners. That speaks a lot about him. Ian talks about what it really means. JP should be celebrated for this. Who should be the backup catcher? Eno Sarris, The Athletic joins Ian to give his thoughts on Colt Emerson's debut, as well as JP Crawford's flexibility to move to third base. JP deserves his flowers for his bat, regardless of what we've seen in the decline defensively. Eno also addresses the potential damage that bringing up players 'too early' can do. Of course, we have to talk about "piggybacking" with pitchers. Finally, we have to talk about Mason Miller and the Athletics. The Daily Power Play! Corbin Smith, Emerald City Spectrum joins us to give us some perspective on the NFL schedule release and what it means for the Seahawks. There's no such thing as a perfect schedule, but this worked out pretty well for Seattle. Two of the final three on the road isn't great, but Ian likes the collegiate feel of it. What can Riley Mills do for this team? We also delve into the running back situation, as well as the defensive backfield. Checking in on the Talkbacks and Texts! Crosstalk with Softy!See omnystudio.com/listener for privacy information.

The Craft   Nick Pollack and Eno Sarris preview Eno's upcoming SP ranks and compare against Nick's. Nick Pollack | Eno SarrisJoin The Discussion | PL+ and PL Pro Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

The Craft   Nick Pollack and Eno Sarris preview Eno's upcoming SP ranks and compare against Nick's. Join Our Discord & Support The Show: PL+ | PL Pro - Get 15% off Yearly with code PODCASTProud member of the Pitcher List Fantasy Baseball Podcast Network Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

Sounders won big last night, and Jackson discusses how big it was for the team. Cal Raleigh heads to the 10-day DL - how are we feeling about him at this time? He needs some time off and a full uniform shower can only do so much. Bryce Miller is BACK! We discuss the work he did to get back, considering how much he had to do to get right between Everett and Tacoma. Softy's sources tell him many of the Seahawks' scheduled games prior to the actual release, and we look at what this season could look like for Seattle. There are leaks out for the NFL schedule right now - when looking ahead, how much should we realistically expect from the Seahawks this year? The World Cup is coming up and one of the hopefuls to make the US National Team, Cristian Roldan joins us to talk about the Sounders win last night and his potential to be a part of the World Cup. Corbin Smith, Emerald City Spectrum joins Anders and Jackson to talk about the NFL schedule release and what it means for the Seahawks. How much does this schedule release actually matter? Corbin nerds out with the guys. He's also really high on the opening quarter of the season for Seattle and 100% sees what he expected with the primetime games they were awarded. Corbin thinks there's good reason to see the Seahawks start 6-0. The NFC West is gonna be the hardest focus for Seattle. The Daily Power Play! Eno Sarris, The Athletic joins Anders and Jackson as we are wrapping up the Mariners game in Houston. He breaks down Bryce Miller's first start back from the IL. What do the numbers say about six-man rotations throughout history? Eno says it benefits a playoff-bound team. The Dodgers are doing it without even announcing it. Also, why is Houston so bad right now? Finally, what are some reasonable expectations for Cal Raleigh this season after he set the bar so high last year? We check the talkbacks and texts and finally, speak to Softy.See omnystudio.com/listener for privacy information.

Prihodnost dela, v kateri vse več nalog prevzema UI, je tako tehnološko kot politično vprašanje Človeštvo vodi neusahljiva želja po napredku in razvoju, pri čemer umetna inteligenca postaja eden najpomembnejših dosežkov moderne dobe. Čeprav se lahko strinjamo, da UI prinaša izjemne priložnosti, pa hkrati z zadržkom spremljamo vsa tveganja in etična vprašanja, ki se odpirajo in dotikajo človeškega dostojanstva, delovanja in znanja. Eno pomembnejših vprašanj je, v kolikšni meri bo umetna inteligenca preobrazila ali celo prevzela dele trga dela. Da smo v tem obdobju tehnološkega razvoja, je to neposreden rezultat človeške radovednosti, ustvarjalnosti in vztrajnosti. Kljub prednostim, ki nam jih prinaša – umetna inteligenca je navsezadnje uporabno orodje – pa ne smemo pozabiti na vprašanje nadzora in tudi zavedanja, da umetna inteligenca ne razmišlja namesto nas. Oddajo je pripravila Tina Lamovšek. Fotografija: Pixabay

And what's really happening inside India's healthcare system that nobody talks about?Dr. Guru N Reddy, Founder of Continental Hospitals, sits down with VK for one of the most honest health conversations we've ever had. Nothing is off limits.Here's what we covered - - Hospitals opening like supermarkets, doctor poaching & medical billing manipulation- Insurance companies, hospitals & patients - who's really winning?- Patented vs generic drugs - Ozempic, Mounjaro & Minoxidil explained- The REAL reasons for weight gain - it's a hormonal problem, not a willpower one- Gut-Brain Axis - how your gut and brain influence each other more than you think- Seasonal fruits, kitchen superfoods & the shocking sugar in cool drinks- Beer & the growing global epidemic of Fatty Liver- Rapid fire - AI for diagnosis, parasites in Indian guts, ENO & moreThis is not your regular health podcast. Raw, real & straight from one of India's top medical minds

Po državi potekajo tradicionalna kresovanja pred jutrišnjim praznikom dela. Eno glavnih sindikalnih praznovanj poteka na na Rožniku v Ljubljani, kjer so zbrane nagovorili vodje sindikalnih central.

It's NFL Draft Day! Ian is live from the Virginia Mason Athletic Center and it's a different feeling this year coming off the Super Bowl. We are all but certain the Seahawks won't take a pick at 32. Greg Cosell, NFL Films takes us through the offensive lineman we'll see over the next three days of the Draft. Who could the Seahawks be coveting and within those, who is in reach? We take a look at a broad view of the Draft as well. Ian learns some new things about Jess, and they talk about the expectations they have in round one today. Ian is quite happy with the new clock on the picks in the first round which will make these things move a lot faster. The Dianna Russini situation appears to keep getting worse. Mike Vrabel won't be present for the 3rd day of the draft? Ian feels bad for her but also doesn't. Eno Sarris, The Athletic joins Ian to talk about the state of the Mariners. Offensively, we've seen on an uptick, but should we be worried about the pitching staff right now? We take a look around the league and what's happening in certain markets. They discuss the markets that could be ripe for expansion if it were to happen in MLB? Eno tells us what he's seen from the lineup so far and...oh no, we have a Softy question coming in. Hugh Millen hops on with Ian for a preview of what he thinks is going to happen in the draft in round one. Hugh tells us what he sees in John Schneider's philosophy when it comes to the draft. Corbin Smith, Emerald City Spectrum joins Ian live at the Virginia Mason Athletic Center as we are just three hours away from the start of the 2026 NFL Draft! Corbin gives us his definition of John Schneider's philosophy when it comes to the draft. He says it's about finding the best player available and THEN plugging the needs as the draft continues. Things have changed over the years as Schneider enters his 17th draft with the Seahawks. Ian and Corbin look at the scenarios for the Seahawks in this first round and how it may affect the next two days, as well as those on the current roster. With the lack of quarterback star-power, this looks like an interesting draft to come. Checking in on the Texts and Talkbacks! Crosstalk with Softy!See omnystudio.com/listener for privacy information.

What happens when a band faces turmoil yet finds the strength to create something beautiful? Join host Buzz Knight on this week's episode of takin' a walk, as he dives deep into a compelling conversation with Carl Newman, the founder and frontman of the critically acclaimed band The New Pornographers. With their latest album, The Former Sight Of, set to release under extraordinary circumstances following the arrest of their drummer, Newman shares the challenges that shaped this unique musical journey. Through candid storytelling, Buzz Knight unravels the complexities of the creative process with Newman, who reflects on how collaboration with legendary drummer Charlie Drayton transformed the album. As they walk through the ups and downs of the music industry, listeners will gain insights into Newman's evolving songwriting approach, striking a balance between complexity and accessibility. This episode is a treasure trove of music history insights, offering a glimpse into the minds of legendary musicians navigating the unpredictable landscape of indie music. Newman’s passion for creativity shines through as he discusses the importance of being true to oneself and the thrill of artistic reinvention as the front man for The New Pornographers. Buzz Knight, known for his engaging music conversations, probes Newman about the stories behind the songs and the emotional healing that music can provide. This episode is not just about an album; it’s a celebration of resilience, creativity, and the music journey that connects us all. As the episode wraps up, Newman shares a delightful twist—his dream of taking a walk with none other than Brian Eno, a nod to his admiration for Eno's innovative approach to music. This charming anecdote adds an extra layer of depth to their discussion, making it a must-listen for fans of rock music history and classic music stories. So, lace up your shoes and get ready to join Buzz Knight on this inspiring episode of takin' a walk. Whether you're a die-hard fan of The New Pornographers or someone who appreciates the stories behind albums, this episode promises to be a captivating exploration of songwriter stories and the transformative power of music. Tune in and discover how music continues to inspire and heal in the most unexpected ways!Support the show: https://takinawalk.com/See omnystudio.com/listener for privacy information.

One of NZ's best-ever band exports is Split Enz.  Formed in the 70's, Split Enz' intelligent pop music made them one of our top bands for over a decade, and still beloved today. We look at how they got started and some highlights of their career and recordings.  We also talk about our annual trip to Bali, where we discovered a local band that played Pink Floyd's  “Wish You Were Here” (yes, really!!)  Radiohead's “Creep”, Johnny Cash's “Ring of Fire” and a stack of other songs straight from our episode playlists. Yep, sure surprised us!  Our “Album You must Hear Before You Die” is Penguin Cafe Orchestra's self-titled album from 1976 – an experience for an open mind!    References:  Bali, Pink Floyd, “Wish You Were Here”, Johnny Cash, “Ring of Fire”, The Bee Gees, “To Love Somebody”, Nick Cave & Shane McGowan, “What a Wonderful World”, Radiohead, “Creep”, “Love is all around us”, The Troggs, “Love Actually”, Bill Nighy, Jonny Greenwood, Michael's Bar in Legian,  “Wedding songs, and other disasters”, New Zealand, Auckland, Split Enz, Coachella 26, David Lee Roth, Teddy Swims, Justin Bieber, Robert Dimery, 1001 Albums you must hear before you die, ”Penguin Cafe Orchestra”, Simon Jeffes, Steve Nye, Eno, Obscure, “Music For a Found Harmonium”, “The Sound of Someone you Love Who's Going Away And It Doesn't Matter”, 101ers, Joe Strummer, Malcolm McLaren, Sid Vicious, "My Way", The Great Rock'n'Roll Swindle, Tim Finn, Phil Judd, APRA Top 100 New Zealand Songs of All Time, Finn Brothers, Crowded House, Neil Finn, Paul Hester, “The Mullanes”,  Countdown, Michael Jackson, MTV, “Mental Notes”, Phil Manzanera, “Second Thoughts”, “In Every Dream Home a Heartache”, “The Swingers”, “Counting the Beat”, ENZSO, “Six Months in a Leaky Boat”, Aotearoa”, Māori, Falklands crisis, The Wiggles, “Wiggly Version”, REM   Playlist – all the music & artists we talked about in this episode Send us a message, so we know what you're thinking!

तमिलनाडु और पश्चिम बंगाल में प्रचार थमा, सुनेत्रा पवार ने की भावुक अपील, अमित शाह और ममता बनर्जी के बीच आरोप-प्रत्यारोप, कांग्रेस ने ममता बनर्जी पर क्या आरोप लगाया, पीएम मोदी के खिलाफ किसने की शिकायत, केरलम में बड़ा हादसा, दिल्ली में 29 अप्रैल को मेयर का चुनाव, नकली ENO बनने वाले पकड़े गए, ईरान और अमेरिका का एक दूसरे पर आरोप, आईपीएल में दिल्ली और हैदराबाद के बीच मुकाबला जारी. सिर्फ 5 मिनट में सुनिए रात 9 बजे तक की बड़ी ख़बरें.

The Craft   Nick Pollack and guest Eno Sarris discuss Eno's most recent set of ranks. Nick Pollack | Eno SarrisJoin The Discussion | PL+ and PL Pro Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

The Craft   Nick Pollack and guest Eno Sarris discuss Eno's most recent set of ranks. Join Our Discord & Support The Show: PL+ | PL Pro - Get 15% off Yearly with code PODCASTProud member of the Pitcher List Fantasy Baseball Podcast Network Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

Ian reflects on the week we've seen when it comes to those who are headlining the news in sports this week. What happened with Angie is flat out wrong. Keyboard warriors should not be praised. Ian has some words for them. Eno Sarris, The Athletic joins us to tell us whether superstitions are actually real in baseball. From one pendulum swing to another, then we saw what happened last night. Ian dives into the Padres series and the mishaps we've seen with the pitching staff of late. Eno also tells us about his latest pitcher rankings, in which three of the Mariners are featured in the top 13. The Daily Power Play! Ian puts a bow on the Kraken season as today will be the last game of the year. Lane Lambert will have some words to say tomorrow. Steve Palozzolo, The 33rd Team tells Ian how fast it feels that the draft comes around each year. He provides a bit of insight on our baseball team, coming from a player perspective himself. Is Mendoza the clear #1 overall pick? Steve tells us who he loves in the draft and gives some insight on the defensive backs we might see in the Seahawks' sights, considering where their picks fall this year. Checking in on the Texts, Talkbacks and YouTube comments! Crosstalk with Softy!See omnystudio.com/listener for privacy information.

Zaradi pomanjkanja družinskih zdravnikov smo bili v preteklosti že večkrat priče dolgim vrstam ljudi, ki so se želeli vpisati k novem zdravniku. Tako je bilo tudi danes v Borovnici. Predsednica Zdravniške zbornice Bojana Beovič meni, da so takšni prizori delno tudi posledica slabe organiziranosti. Eno od težav vidi v obveščanju ljudi, za katero skrbijo zdravstveni domovi ali Zavod za zdravstveno zavarovanje. Drugi poudarki: - Generalni sekretar Nata Mark Rutte: zavezništvo bo zagotovilo pomoč Ukrajini kljub neskladjem pri porazdelitvi bremena med članicami. - Pakistan si prizadeva za obnovitev mirovnih pogajanj med ZDA in Iranom. - Graditev mariborskega Centra Rotovž se počasi bliža koncu.

In the early 1970s, legendary collaborator and self-proclaimed non-musician Brian Eno famously designed a deck of 115 cards containing elliptical imperatives to spark in the user creative connections unobtainable through regular modes of work. He called his creation "Oblique Strategies." For the past six decades, artists the world over in every artistic medium have used Eno's strategy while attempting to overcome a lull in creative output.In 2026, nihilistic, nerdy nimcompoops and self-proclaimed Lightnin' Lickers Jay and Deon found themselves uninspired when contemplating the potential theme of their upcoming forty-seventh episode. Together, they decided... to default back to the alphabet. Because they had a reasonably solid grasp of the alphabet and how it works. They had previously utilized the letters A thru M, so naturally, they went with N.Sonic contributors to the 47th episode of Lightnin' Licks Radio podcast include:NPR, Beaste Boys, Gravediggaz, Brothers Johnson, James Ussery, RZA, Prince Paul. James Todd Smith, Rashaad "Ringo" Smith, Cindy Lee, Pete Jolly Trio, Ace Frehley. Delroy Lindo, Greg Gutfeld, the N***. Nazz, Todd Rundgren, The Temptaitions, Cheap Trick. Aaron Neville. George Davis, Warren Barker, Linda Rondstadt, Cynthia Weil, Tom Snow, The Meters, The Neville Brothers, Arthur Hamilton, David Gates and Bread. Tricky, The Presidents of the United States. The Naked and Famous. Nada Surf, Weezer, America. The Natural Four, Leroy Houston. CNN, Drink Champs podcast, the Neptunes, N.O.R.E., Brittany Spears, N.E.R.D., Clipse. Nice Strong Arm, Dinasaur Jr., Swans. Heatmiser, Elliott Smith, No. 2. LCD Soundsystem, The Rapture, Robert Tepper, Benny Mardones, The Natural History, Gang of Four. The Nonce, Kwest Tha Madd Ladd, Freestyle Fellowship, Aceyalone. Okonski, The Clockers, POSPOTUS DJT, Jim Carey, Megan Kelly, Tim Robinson."YOU CAN'T DO THAT!"Copyright Police hammered us on 6/10 tracks, a new record! Fear not, Lickers -you can still hear the FULL MIXTAPE via Soundcloud or jam 90% of the tunes on thisNEARLY FULL Spotify PlaylistSupport these artists and your local music store.Happy Spring, C'mon, Stewk!

Piše Jože Štucin, bereta Jure Franko in Eva Longyka Marušič. Neža Zajc, rojena leta 1979 kot vnukinja nesmrtnega Daneta Zajca, se je kot pesnica pojavila dokaj pozno. Najprej se je preizkušala s proznim pisanjem in šele po smrti močnega žlahtnika je z žarom in vehemenco zverzirane ustvarjalke stopila v svet poezije. Leta 2014 je izdala pesniški prvenec Ime gore, do najnovejše knjige Bele sence pa je nanizala še tri zbirke. Torej smo pri petem dejanju, ki ima vse značilnosti zrelega opusa. Bele sence še zdaleč niso samo bele, prav pester niz poetik je tu združenih v enovito fresko, ki prepričljivo krmari med intimo in belino sveta, med jazom, ki se bori s podobami, in jazom, ki ga kljuje ujeda naše izgubljene civilizacije. Lepa zbirka, če odmislimo ontološko resignacijo, ki brsti na požganih travah: lepota v trpkosti, lepota v sivini, ki žari močneje kot barvni spekter. Kljub radikalnemu pristopu in preizpraševanju smisla biti, tu-biti, poetičnemu (na)gonu in strastni želji po iskanju prerokbe, se zbirka daje v branje v čisto konvencionalni podobi. Spremno besedo je napisala dr. Vilma Purič, pesmi so sistematično razporejene po sklopih, sedem jih je, in vse teče gladko, kot se za pesniško zbirko nekje na vrhuncu ustvarjanja spodobi. Nekajkrat so cikli uvedeni z verzi iz Zajčeve zapuščine, zato ima bralec na voljo vsaj skromen namig, kako brati, vendar se pesnica zna izogniti pretiranim kazalnikom in citate izbira na ravni, ki dopuščajo več, kot so nemara izvorno v sklopu svoje celote imeli namen sporočiti. Pač, metaforika, tista "šibka" točka Wittgensteinove filozofije, njegovih frenetičnih iskanj mej jezika in začetkov molka, kjer je klonil v mehanizmih, da bi prišel jeziku "do konca". Pri poeziji je filozof pač moral priznati, da metafora suvereno izreka onstranstvo jezika, da sporoča, ozvočuje tišino, molk in jezik neizrekljivega, ter nadvse zgovorno prezentira (ne)smisel poezije, ki je bolj smiseln, kot se zdi slepemu ušesu. S tem se je vedno boril, filozof neizrekljivega. Ko tista hladna resničnost jezika, ki nas obvladuje v komunikaciji pene (vsakodnevnih) dni, v komunikaciji hudičeve samosti, ki hoče govoriti z drugim in biti slišana, pa tudi razumljena, a po zakonitosti narojene samote, kar je človek v bistvu, vedno naleti na oviro interpretacije, vedno pade v prostor diskusije – kaj je kdo hotel povedati, sporočiti. Na zgornji omejitvi metafora preskoči igrico izmenjave besed in prestopi v poezijo, v neposredno poved, ki izreka resničnost. Na tej postavki se zdi, da gradi tudi pesnica Neža Zajc – izreka belino svojih senc in jih tako dela vidne, slišne, čutne, eksistenčno relevantne. Sklopi vsak zase poglabljajo neko pesniško intenco, vzgib, ki kljubuje smrti in piše življenje, in nasprotno, seveda, kot življenje, ki piše smrt. Nemara tudi pod okriljem uvodnih verzov Daneta Zajca, ki zbirki daje začetni zagon. Citat je rokopisna zapuščina slavnega dedka, ima pa vse značilnosti njegove preroško resignirane minljivosti v času praznine in smrti: "... smo živi bolj / in drugje / od naših temnih senc ..." Tu se vse začne, točno na robu smisla, na meji, ko bi pesnik vendarle še kaj rekel, hkrati pa že molči in zre niču v oči. Pesnica takoj povzame ta kongenialni navdih in ga zapelje v polje družbe, skupnosti. Nismo sami, kot je pri Danetu Zajcu včasih mogoče primarno, tu smo vsi, vsi na istem poligonu, v istih škripcih, z enakimi bolečinami in strahovi. Pesem V sencah ima zajčevski liker izraznosti, skoncentriran gnoj in sok, vse v enem, ki se skozi sito poezije cedi z metaforami in črkami do onemoglosti, do meje jezika, ki komaj še zmore nositi strašne pomene. Takole gre: »V sencah se rojevajo bitja, / in prehod v pročelja lét / pomeni daljše izgubljanje / zaznavanje sebe tu. // Kakor bi ne znal shoditi / do morja, do starega pomola, / se ogniti pošasti ogromni / nezaznamovanih ljudi, // zreš le sence menjave prostorov. Pesem razodeva pesničin miselni in čustveni obrat vase, v svoj pojav, ki zgolj receptira svet, ga strahoma sekvencira in opazuje, a ob tem hrepeni po kazalnikih, ki bi svetu, naši pojavnosti sredi niča, razodeli smisel bivanja. Sam si, gol in položen v senco, ali kot je zapisala v pesmi Pred oknom slapovi: "Tako od sijanja lune / izvržen na cesto bos, /in izpraznjen, mil / kakor lačen v grobu, / nag nisi več ranljiv." V poeziji Neže Zajc se spogledujemo z bivanjskimi strahovi, ki so v resnici tramovi naše biti. Soočenje s praznino in "ničem" jo navdihuje do te mere, da samo sebe skuša povzdigniti v smiseln pojav. Pesniška drža je pač suha in nema, v izvoru, šele z realiziranjem "sebstva", se povzdigne nad praznino in začne izrekati. Pri Neži Zajc smo v tej pozicij. Pesnica izreka vse, kar se ji kot pojavnost sili pred oči: "Od onstranstva veje burja / na zaledenelem obzorju / in od tal raste duša ..." Ker gre za sugestibilno pesnico, tako, ki celo presega svoje meje in se dotika drugih, ni nenavadno, da v svoj poetični korpus pritegne tudi Srečka Kosovela. V ciklu Poslednje bilke se mu pokloni s pesmijo Cvetovi, kjer pa ga, pesnika upanja in smrti, v sklepnih verzih tudi zakoplje v njegov Kras: "In na tleh so cvetovi, / pod katerimi prihuljen, / s praznimi rokami upanja, / s stisnjenimi pestmi / kakor dete mižiš, mižiš." Zbirka, ki na gosto beleži stanja duha, smisla, družbene "zgodbe", išče odgovore na strahotna vprašanja, trepeta v svoji minljivosti in se oklepa pokopališč, ki so središčne točke človeštva, ima tudi zelo jasen smisel, biti dober do drugega, biti socialen in živ v skupnosti. Rahlo v disonanci s siceršnjo naracijo te poezije se vsake toliko iz požganin dvigne upanje, ne kot božje razodetje, bolj kot ljubezen, ki je (poleg pesniške metafore) edino, kar presega naše meje. In tudi ne priznava "konca" biti in protežira realnost kot princip čudnega tandema, vzetega iz biolške resničnosti, kjer dominirata življenje in smrti. A v zakulisju, ki je očem nevidno, dopuščata "še nekaj več". Ali kot pesnica Neža Zajc piše v pesmi V ljubezni: "med petjem mrtvih / so beli verzi čarobnosti, / ki spati ne pustijo, / ne oddahniti se končno." To se nekako navezuje tudi na pesem Eno, kjer se eksplicitno zavzame za akcijo, za konkretno vlogo posameznika v svetu, za dejanja, ki tudi edino odrešujejo: ko se odzoveš na krik trpečega, vsi jeziki umolknejo, vsa poezija dobi smisel v akciji: "Ker zavedanje edinosti / razgleda nad morjem / vzame vse jezike. // Ko prosjačiš za bolne, / odsekaš hladne lovke, / verjameš v ščitenje, / prevajaš glasove / v telesne neširine." Zbirka Bele sence izhaja iz prednikov, piše se iz duše, ki je zastavila rod, črkuje se po zakonih belih trav, ki sedaj valovijo v brezvetrju in odsevajo svojo gibkost le skozi besede. Segajo prek smrti in časa, trepetajo pred obličjem neizrečenosti in pozabljenja, obenem pa klijejo ne neki požganini, kjer človek nikoli ne ve, ali bo iz zemlje pokukal nov cvet ali bo luknja v nič še globlja. Neža Zajc je v tej ekvilibristiki med genskim spominom in svojo izvirno potjo polna idej. V knjigi je kar nekaj presežkov, ki plivkajo v vse smeri, iščejo nove izvire, nove vzgibe za pisanje. Jezik, s katerim govori, je tako mitološki, kar jo veže na slavnega prednika, kot tudi živ, sproten, odziven v času in skuša razodevati svoj aktualni trenutek. Taka je brez dvoma tudi pesem-cikel Časov vseh izhod, ki proti koncu knjige preskakuje med preteklostjo, sedanjostjo, prihodnostjo, trenutkom in večnostjo, ter kulminira v pesmi Stopnice, kjer je vse razodeto: "Povzpneš se le do križa / do prekopanega pokopališča, / ki na večernem hribu / privlači telesa resnična."

The Masters are underway and Ian poses the question of whether you were separated from your phone, how stressed would you be? Is it fun or liberating. We dig into what the Kraken are doing in the wake of Ron Francis stepping down. We listen to Tod Leiweke's thoughts on the future of the team. Bobby Casper, Real Golf Radio joins Ian from Augusta to provide us some insight on what he's seeing on the first day of the Masters. Bobby saw his father win in 1970 and has known the course for years. He gives us his thoughts on the field this year. Eno Sarris, The Athletic joins Ian to break down the latest we've seen from the Mariners, especially considering the 'it's early' talk when it comes to the offense. Eno says Julio Rodriguez needs to lock in, but also explains why the perpetual 'big hitters' might be trying to do what's outside of their best skillsets at this time of year. We touch in on Josh Naylor and Cal Raleigh when it comes to the 'cause for concern' meter. The Daily Power Play! We hear from Tod Leiweke on Ron Francis moving away, as well as Jason Botterill conducting the "independent audit" of the team. Steve Palozzolo, The 33rd Team joins Ian to dig into the edge rushers in this year's draft. He tells us who he thinks could be a realistic target for the team, while the Seahawks have limited draft picks. Where are their biggest needs and how can they address them in this year's draft? Checking in on the Texts, Talkbacks and Youtube Comments! Crosstalk with Softy!See omnystudio.com/listener for privacy information.

 This episode, we look at guest appearances.  From Duane Allman playing the famous lead on “Layla”, to Bob Seger doing backing vocals on The Eagles' “Heartache Tonight”. It's all here, from a moment in the studio to creation of an inspirational piece of music It's a chock-a-block episode. “Knockin' on Heaven's Door” looks at Neil Sedaka, Charles Negron II of Three Dog Night, William "Billy Bass" Nelson Jr, of Parliament-Funkadelic, and rappers Lil Poppa 25 and Luci4 22, who were, surprisingly, shot to death. “Rock News” considers nominees for the 2026 Rock and Roll Hall of Fame, and we introduce our latest “Rod Stewart Moment”. If that's not enough, “1001 Albums You Must Hear Before You Die”, looks at Eno's 1978 album “Ambient 1: Music for Airports” and how it fits with his early body of work.  So much to take in!  Enjoy!  References:  Guesting, Collaboration, Session, Eddie Van Halen, “Beat It”, “Eat It”, “Sentimental Hygiene”, Donald Trump - “Home Alone 2”, Voice roles on “The Simpsons”, Crowded House, Sydney Opera House forecourt, Tim Finn, Split Enz, “I See Red”, Lou Reed, Antony Hegarty (Antony and The Johnstons), “Berlin”, Cyndi Lauper, Cher, “Girls just want to have fun”, David Bowie, Hammersmith Odeon, Ziggy Stardust, Jeff Beck, “Jean Genie”, “His Master's Voice”, “Ziggy Stardust: The Motion Picture”, Bono, George Michael – Aretha Franklin, Buddy Guy – Clapton & Phil Collins, Muddy Waters - Mick, Keith & Ronnie, Billy Bragg – Peter Buck & Michael Stipe, Glastonbury, Paul McCartney - Dave Grohl & Bruce Springsteen, Elton John, Sebel Town House, Warren Zevon, Dylan, Don Henley, “Wish You Were Here”, Roy Harper - “Have A Cigar”, The Beatles - Duane Allman/Billy Preston/Eric Clapton, John Lennon - “Whatever gets you through the night”/Elton John, Lennon backing vocals on Bowie's “Fame”, Thin Lizzy, “Live & Dangerous” - Huey Lewis harmonica, Peter Gabriel - “Games Without Frontiers”/“Don't Give Up” - Kate Bush, Neil Young - “Heart of Gold”/“Old Man” - James Taylor & Linda Ronstadt, REM, “Shiny Happy People” - Kate Pierson, “Nightswimming” - John Paul Jones arranged, Rolling Stones, “We Love You” - Lennon & McCartney backing vocals, “All You Need is Love - Jagger and Richards backing vocals, Carly Simon, “You're so Vain” - Jagger backing vocals, Phil Collins, “Another Day in Paradise” - David Crosby backing vocal, “The Great Gig in the Sky” – Pink Floyd/Dark Side of the Moon - Clare Torry, “Let's Dance” – Stevie Ray Vaughan, “While my Guitar Gently Weeps” – Clapton, Sting - “Money for Nothing”, I want my MTV, Dire Straits  Playlist   Robert Fripp & Toyah Wilcox - "Heroes"Send us a message, so we know what you're thinking!

Mistral has been on an absolute tear - with frequent successful model launches it is easy to forget that they raised the largest European AI round in history last year. We were long overdue for a Mistral episode, and we were very fortunate to work with Sophia and Howard to catch up with Pavan (Voxtral lead) and Guillaume (Chief Scientist, Co-founder) on the occasion of this week's Voxtral TTS launch:Mistral can't directly say it, but the benchmarks do imply, that this is basically an open-weights ElevenLabs-level TTS model (Technically, it is a 4B Ministral based multilingual low-latency TTS open weights model that has a 68.4% win rate vs ElevenLabs Flash v2.5). The contributions are not just in the open weights but also in open research: We also spend a decent amount of the pod talking about their architecture that combines auto-regressive generation of semantic speech tokens with flow-matching for acoustic tokens (typically only applied in the Image Generation space, as seen in the Flow Matching NeurIPS workshop from the principal authors that we reference in the pod).You can catch up on the paper here and the full episode is live on youtube!Timestamps00:00 Welcome and Guests00:22 Announcing Voxtral TTS01:41 Architecture and Codec02:53 Understanding vs Generation05:39 Flow Matching for Audio07:27 Real Time Voice Agents13:40 Efficiency and Model Strategy14:53 Voice Agents Vision17:56 Enterprise Deployment and Privacy23:39 Fine Tuning and Personalization25:22 Enterprise Voice Personalization26:09 Long-Form Speech Models26:58 Real-Time Encoder Advances27:45 Scaling Context for TTS28:53 What Makes Small Models30:37 Merging Modalities Tradeoffs33:05 Open Source Mission35:51 Lean and Formal Proofs38:40 Reasoning Transfer and Agents40:25 Next Frontiers in Training42:20 Hiring and AI for Science44:19 Forward Deployed Engineering46:22 Customer Feedback Loop48:29 Wrap Up and ThanksTranscriptswyx: Okay, welcome to Latent Space. We're here in the studio with our gues co-host Vibh u. Welcome. Thanks. Excited for this one as well as Guillaume and Pavan from Mistral. Welcome. Excited to be here.Guillaume: Thank you.swyx: Pavan, you are leading audio research at Mistral and Guillaume, you're Chief Scientist,Announcing Voxtral TTSswyxHost(00:05) Okay. (00:05) Welcome to Lean Space. (00:06) We're here in the studio with trustee co-hosts, Vibhu. (00:09) Welcome.VibhuHost(00:11) Very excited for this one.swyxHost(00:12) As well as Guillaume and Pavan from Mistral. (00:15) Welcome. (00:16) Excited to be here. (00:17) Thank you for having us.(00:18) Pavan, you are leading audio research at Mistral and Guillaume, you're a chief scientist. (00:23) What are we announcing today where we're coordinating this release with you guys?GuillaumeGuest(00:26) Yeah, so we are releasing Voxtral TTS. So it's our first audio model that generates speech. It's not our first audio model. We had a couple of releases before.(00:35) We had one in the summer that was Voxtral, our first audio model, but it was like a transcription model, ASR. Like a few months later, we released some update on top of this, supporting more languages. Also a lot of table stack features for our customers, context biasing, precision, timestamping and transcription. We also have some real-time model that can transcribe not just at the end of the level.(00:56) You don't need to fill your entire audio file, but that can also come in real-time. And here, this is a natural extension in the audio, so basically speech generation. So yeah, so we support nine languages, and this is a pretty small model, 3D model, so very fast, and also state of the art. Performed at the same level as the base model, but it's much more efficient in terms of cost, and also much, in terms of cost, it's also much cheaper, only a fraction of the cost of our competitors.(01:22) And we are also releasing the work that this model is running.swyx What's the decision factor?Guillaume It's a good question.swyxThere will be more. Yeah, Pavan, any sort of research notes to add on?Architecture and CodecPavan: But it's a novel architecture that we develop inhouse.We traded on several internal architectures and ended up with a auto aggressive flow matching architecture. And also have a new in-house neural audio codec. Which, converts this audio into all point by herds latent [00:02:00] tokens, semantic and acoustic tokens. And yeah, that's that's their new part about this model and we're pretty excited that it's, it came out with such good quality and Jim was mentioning. Yeah, it's a three B model. It's based off of the TAL model that we actually released just a few months back and insert trunk and mainly meant for like the TTS stuff, but they need text capabilities are also there. Yeah.swyx: So there's a lot to cover.I always I love any, anything to do with novel encodings and all those things because I think that's obviously I creates a lot of efficiency, but also maybe bugs that sometimes happen. You were previously a Gemini and you worked on post training for language models, and maybe a lot of people will have less experience with audio models just in general compared to pure language.What did you find that you have to revisit from scratch as you joined this trial and started doing this? At leastUnderstanding vs GenerationPavan: when it comes to, for, I think the, there are two buckets, I guess the audio understanding and audio [00:03:00] generation. The audio understanding, like the walkthrough models that Kim was mentioning that we released earlier.The walkthrough chat that we released I think July last year, and the follow up transcription only, models family that we released in January, that would be one bucket, and the generation is another bucket. I think. You can also treat them as a unified set of models, but currently the approaches are a little different between these two.To your question on how audio is fed to the model? In the understanding model, it's very similar to actually Pixar models that we also released,swyx: yes.Pavan: That'sswyx: amazing.Pavan: It was pretty, I, that was the first project I worked on after joined Misra. It was pretty, pretty nice. And Wtu was very similar in spirit.I guess So we feed audio through an audio encoder similar to images through a vision encoder, and it produces continuous embeddings and which are fed as tokens to the main transformer decoded transformer model. Yeah. On the model output is just text. So on the output side, there is nothing that needs to be done in these kinds of mode.I [00:04:00] guess the interesting part of what the generation stuff is, the output now has to produce audio and. The approach that we have is this neural audio codec, which converts audio into these latent tokens. There is a lot of existing attrition and a lot of models which are based off of this kind of approach.And we took a slightly. A different, design decisions around this. But at the end of the day, the neural audio product converts audio into a 12.5 herdz set of latents. And each latent is, has a semantic token and a set of acoustic tokens. And the idea is that you take these discrete tokens and then feed it on the input side.There's several ways to use this at each frame, but we just sum the embedding. So it's like having key different vocabularies. Combine all of them because they all correspond to one audio frame on the input side. The output side is the interesting part on the output side, the, it's not the, I don't know if it's the most popular, but one.Popular technique is to have a depth transformer [00:05:00] because you have K tokens at each time step, like with a text, you just have one token at each time step. So you just do predict the token from the vocabulary with, yeah, with just, you get probabilityswyx: This's a very straightforward text. VeryPavan: straightforward.swyx: Yeah.Pavan: But if you have K tokens, then the name thing would be to predict all of them in paddle. That doesn't work. At least that doesn't work that well because audio has more entropy. And the, one of the techniques people use is this depth transformer where you you almost have a small transformer, or it can be L-S-T-M-R in as well, but people use transformers and you predict the K tokens in auto aggressive fashion in that.So you have two auto reive things going on.Flow Matching for AudioPavan: So the thing we did differently is in, instead of having this auto aggressive K step prediction, we have a flow matching model. Instead of modeling this as a discrete token set we trained the codec to be both discrete and continuous to have this flexibility.So we did try the discrete stuff too, and which it works well, but the continuous stuff works just better. So yeah, we took this flow matching, so the, it's a flow [00:06:00] matching head, which takes the latent from the main transformer and like kind in fusion, it's denoising, but in this flow matching itself, velocity estimate.So you go from this noise t all the way to there. Audio latent, which corresponds to the 80 millisecond audio and then, which is sent through the work order to get back the 80 millisecond audio frame.swyx: Yeah. Is this the first application of flow matching in audio? Because usually I come across this in the image.Pavan: Yeah. Actually, in some sense there are models flow matching models in audio, but I think this specific combination I could be wrong. There could be somewhat. No. I haven't seen. I haven't seen much work in this, so I think it's novel and a lot of it's just a way bigger community, so they, I think they pioneer a lot of these diffusion flow matching work, and it's interesting to adopt some of the ideas there into audio and,swyx: yeah.Pavan: Yeah, I'm, personally that's the think part which is trying out about. One of more meta point is unlike text, even in vision, I think this is true, but in [00:07:00] audio step literature that there is no.Winner model, yet there is no, okay, this is the way you do things. It's it's still by, I think people are still iterating and figuring out like what's the best overall recipe. I guess the idea. Pretty sure there are models which are also completely end-to-end, like NATO audio. NATO audio, but it's still not come to a convergence point where this, the right way to think that.That also makes. A space pretty exciting to explore.Real Time Voice AgentsVibhu: What are some of the ways to look at it?Vibhu: There are ways where you can do diffusion for audio generation, but if you want like real time generation, that's a big thing with the approach I'm assuming that you took. Yeah. And also like how do you go about evaluating different axes of what you care about, yeah,Pavan: good point. I think we so you can do just flow matching diffusion for the whole audio. We didn't even go down that path because one of the main applications is voice agents and we want real time streaming, and that's the use case. That's not the only use case, but that's one of the primary use cases we want to get to.So we [00:08:00] picked the auto aggressive approach for that. And within the auto aggressive space, again, you can do chunk by chunk or you can do so we picked the. I think at least personally prefer the operations, which are the simplest, and so we try to see, can we just add audio as just another head to our regular transformer decode model because that kind of makes it easier for eventual end-to-end modeling of audio text native modeling.Yeah. And it works pretty well. So I guess we went with that and we tried a little bit, but the flow matching head itself, like we had a discreet. Diffusion kind of approach, which also works well, but the flow matching work better.swyx: I was just curious about how you also think about this overall direction of research.Do you basically, when you work with the audio team, do you set some high level parameters and then let them explore whatever, or how does it work between you guys?Guillaume: No I think the way it works is that we are the, we are prioritizing together, I think, what are the most important features because there are many things we can do [00:09:00] in audio.Yeah, I think we try to. These are like how we should do things, for instance. Ultimately what we want to do is to build this through duplex model, but we are not going to start this start there directly, I think is. Some of the project people are doing, butswyx: just to confirm, full effects means it can speak while I'm speaking or,Guillaume: yeah.Okay. Audio. Yeah. Yeah. So intimately we're going to get there, but for us it was, we decided to take it like a step by step. So we start with whatever is the most important. I think support customers, which is the transcription is the most popular use case. Then the speech generation, Soviet time, just a bit before that.And then actually to be like more, but try combining everything all together. But but yeah, we thought it was also important to like separate things and optimize each capability one by one before weswyx: measure of that together. And the super omni model. ButGuillaume: very interesting because as Par said, it's when you work on some other domains of this airline and everything, there are many areas where I think it's not as interesting.For instance. Many places, it's essentially just around data or like creating new environments on a lot of kind [00:10:00] of easy things. But things were, I think the research is maybe not as interesting. Were in audio. There are so many ways to actually build this model. So many ways to go around it. That's the sense I think is really interesting.And what we also tried for speed generation is that we tried multiple approaches. What was interesting that even though they were extremely different, they under the big know the particles but the for matching turned out to be quite more natural. So we are happy with this.swyx: Is there intuition why it maybe like flow matching is just models speech better in some natural fundamental, latent dimension?Pavan: No, I think the main thing is e even at a particular time step, there is a distribution of things.swyx: Yes.Pavan: To be predicted like the way you inflate. So you already know the word that you're speaking and Yeah. The intake space, let's say the word maps register a single token for simplicity.In most cases it does. So there is not a lot of so you just pick the word, but with within audio, even the same word could, even with your own voice, could be inflicted in so many different ways. And I think [00:11:00] any approach which like models this distribution and. And flow matching is one, one of the take.It's not the only one at all, but it's a one which works pretty reasonably well. I think that's better. So you have to pick across several different, the intuition I have is it's, there are some, several different clusters each corresponding to some specific way you would inflict, pronounce that thing.And you can't predict the mean of it because that corresponds to some blurred out speech or something like that. But you have to pick one. And then like sharpswyx: conditional inference.Pavan: Yeah, exactly.swyx: Is that all covered under disfluencies, which is I think the normal term of art. Pauses intonations. By the way, I have to thank Sophia for setting all this up, including like some of these really good notes becausePavan: Yeah.swyx: I'm less familiar with the audios for me.Pavan: No. I think dis dismisses are definitely one such Eno defenses is more likeswyx: which is arms are.Pavan: Yeah, arms. And also repeat like you like,swyx: yeah.Pavan: You do this full of words, your thinking, so you repeat the word.swyx: Okay. Whereas intonation is like a diff, it's up up [00:12:00] speak and all this.Okay.Pavan: Yeah. So I think there is a lot of like entropy. And modeling it as a distribution. And a, any technique which helps with it and the depth transformer is a conditional way of modeling this. And Transformers actually really good at it, even though that's a mini transformers. So I think that worked pretty well too for us too.It's just that the main concentration is when you have a depth transformer. If you have K tokens, you need to do K auto steps, right? Even though it's a small thing, it's K steps, which is very vacant, say heavy, but flow matching. We were able to cut it down significantly. So we are able to do the inference in quad steps or 16 steps and it works pretty well.And there are more normal techniques to bring it down even further to like, in extreme case, one step like we're not doing it yet, but it at least the framework, LEDs itself to more efficient and Yes.swyx: And the image guys have done.Pavan: Yeah.swyx: Incredible work guys. Yeah.Pavan: It now you just. Send a prompt and you get an image.swyx: Yeah. Surprisingly not enough. I think image model labs use those techniques in production. I think it's, I feel like it's a lot of research demos, but [00:13:00] nothing I can use on my phone today.Guillaume: The thing, there's a thing that would be interesting here is that since, indeed I've been so much sure that has been done in the vision community compared to radio dys, stomach, I think there are so many long infra Yeah.And there are so many things we can do to actually improve this further. So it's our first version, but we have so many ways to exist, much better and much more efficient, cost efficient, soswyx: yeah.Guillaume: So really it's not a new field at all, of course, but there are still so many things that can be done.Perfect. It'sswyx: nice. I should also mention for those who are newer to flow matching, I think the creator, this guy's name is Alex, he's done I think in Europe's maybe two Europes as ago. There was, there's a very good workshop. There's one hour on like this matching is I would recommend people look that up.That's the other thing, right?Efficiency and Model Strategyswyx: The efficiency wise, like I, I imagine like the reason is open weights the reason you pick 3.6 B backbone it you are 3.4 B you are, try to fit to some kinda hardware constraints. You kinda fits some kinda basic constraints. What are they?Guillaume: Not necessarily, I think something we care about in our model that they're efficient.So we have a [00:14:00] lot of separate model, for instance. So we have this that is very small, very efficient. We also have a small OCR model that is available. Good, highly efficient as well. And I think on a project maybe there, I think companies are going to take is to have a coverage general model that will do a bit of everything.But that is also going to be expensive. On here. What want say is if you care about this specific use case, if you can actually use this model, it just does that. It's extremely good at it. Survey, very efficient. That's why we can actually add. We do, but also OCR that are like really good at that.And that would be much more cost effective factors and the general model that will contain a lot of capabilities you don't really need. So yeah. So we're doing like general model, but also like more customized model. This,Open Weights and BenchmarksVibhu: how does it compare to other TTS models? It's, we are going follow open wave.We're just dropping it. I think it's pretty good.Pavan: Yeah, I think it's pretty good. Like it, it's definitely one of the best. For sure. It's probably I would say it's the best open source model, butVibhu: decipher themselves.swyx: Yeah.Voice Agents VisionVibhu: Why now? How does it fit into broader ral vision? How do you see voice agents?How do you see voice? I think every year I've heard, okay, you're a [00:15:00] voice. You're a voice. There's a lot of architectural stuff. There's a lot of end time that see it, your solving, but where do you see voice setting?Guillaume: We had so many customers asking for voice. That's also why we wanted to build it.What's interesting in this domain is that. In a sense, if you take something simple like transcription it doesn't seem like something that should be very hard to do for a model. It's essentially, it's pattern recognition. It's classification on this. Models are very good at classifying, right?Or nonetheless, when you talk to them it's not there yet, right? It's not, you don't talk to them the same way you talk to a person. On something, maybe people don't realize it. It's in English it's still much better than in any user language, even compared to French instance. If you talk to this million in French, when you see people talking to this they'll talk very slow.They'll articulate as much as they can. So it's not natural, right? We're not yet to this. And I think, yeah, maybe the next generation will not know this, but yeah, I think people that. But our edge will actually always keep this bias speaking very slowly when they talk to this model. Even if maybe, probably in a couple of years, maybe next year it'll not be necessary anymore.But yeah. But what's interesting is to see that yeah, even for like languages [00:16:00] like yeah, French and Spanish Germans that are not no, no resource on religion. You have a lot of audios there on still it's not as good. And I think a consequence. Because then for this, I suppose just is not as much energy, as much effort that has been put done in some other mod that for some vision or like coding.But but yeah, there's still a lot of progress to be done. I think it's just a question of doing the work and it's clear path I think to get there.Pavan: It's a little fascinating because I worked on Google Assistant I think while back at this point, but it's, I think it's, it like when you take a step back, it's fascinating.It's not that long ago. It was like four years ago or five years ago, and it's now it's completely audio in, audio out and the function calling and the whole thing happens completely end to end. And in a very natural,swyx: yeah,Pavan: natural way and still ways to go. Kim was telling, even despite all the previous, it's not like you're speaking to a person.When you talk to any of these agents, bots, or voice mode kind of situation, it's still like a gap. I think that's the great part and I feel like with even the existing [00:17:00] stack, we should be able to get to this very natural speech conversational abilities soon enough I guess.And we'll also hope. I get thatGuillaume: on this kind of the next step, right? Because when you talk to these agents, like usually people are just writing to them and sometimes they'll this very clear, for instance, you are, you want to write code, but you are, you have a very clear idea of how you want the model to implement what you in mind.But so here you are able to spend a lot of time writing. So it's not really efficient on audio is really like a natural interface that is just not there yet, but I think it's just gonna be the place.Vibhu: How's it like building, serving, inferencing, like we see a lot about, it's very easy to take LMS off the shelf, serve them.Fine tuning, deploying. I know you guys have a whole you have Ford, you have a whole stack of customizing, deploying. Is there a lag in getting that. Like distribution channel. Are you helping? There is. So like prompting, lms, you can have them be concise, verbose, all that.They're built on LM backbones, these models. How do you see all that?Enterprise Deployment and PrivacyGuillaume: Yeah, I think this is a lot of what we're doing with our own customers. Very [00:18:00] often they come to us, so it's for different reasons. I think one reason is sometimes they have this lot of privacy concerns.They have this data that it's very sensitive. They don't want data to leave. The companies, they wanted to stay. Inside the company. So we have them deploy model in-house. So either on a, either on premise or on private cloud. So they're not worried that it's given to a third party on the there some leakage.Sometimes they have this kind of many companies have this different, sensitivity of data they have like sometimes channel chat can send it to the cloud has to stay there. So then it creates some kind of heterogeneous workflows where it's annoying. You cannot send some data to the cloud.This one you can, so here, when we actually deploy the model for them, they don't have this consideration. They are like not worried that, this is going to leak. Everything is much easier. So we help them basically do this on the, so it's one of the very proposition. But but the other is very often, when customers use this off the shelf close model, but very sad is that they are not leveraging, these data that have been collecting for four years or something for decades.So much data. Sometimes it's trillions of tokens of [00:19:00] data in a very specific domain. Their domain, which is data that you'll not find in the public, on the public internet. So data on which, like close model, we actually not have access to one, which that's going to be really good. So if they're using like closed source models are basically not benefiting from all these insights.All these data they have collected three years, they can always give it into the context that in France, but is never as good as if you actually train the modern analysis. So yes, that's basically what we help them to do. We actually provide them some purchase, basically what we announced at GTC this week.So we provide them with this, it's basically like a platform with a lot of tools to actually help them process data. Trained on that. Yeah, it's actually the same thing that we're using in the science team. So it's actually very better tested infrastructure, like a lot of efficient training cut base.For a quality pre-training like a fine tuning, even doing S-F-T-I-L. So we help them do this using the same tools as what our science team is building is using. So since it's tools that we've been using for two years now, it's really better tested. It's really sophisticated.So it's the same thing. We are giving to them, giving the company the same thing [00:20:00] that what are same still using internally actually build their own ai and it makes a really big difference. I think sometimes customers. And many in general don't realize how much better the model becomes when you fine tune it on your own data.And you can have a, your model is here. You start from there. You have a cross source model, which is sort here, but if you actually fine tune it can actually really go much further than this. And then you have a very big advantage. The model is trained on your entire company knowledge, so it knows everything.You don't have to feed like 10 K tokens of contact at every query. So it's it's much easier. It's a bit, I think using a closed source model is really sad because it basically puts. You are not leveraging all this data and you are going to be using the same model as all your old competitors when you're actually using, everything you have been collected for years, which is really valuable.So yeah. So we help basically customers do this. We have a lot of solution I mean deployed for engineers that go in the company that basically look at the problem customers are facing to look at what they're struggling to do what we should do to solve it. So we help them solve them together.So it's I think our approach is a bit different, but here. [00:21:00] Some of their companies and competitors, it's, we don't just release an endpoint on sale, do some stuff on top of that, or we don't just give a checkpoint. We really look very closely with customers. We look at the issues they have, we had them solve them.We really make some tailored solution for the client are facing. Some example are also going to be, sometime we have some customers. They really wanted to have a really good model, really performance on some, like Asian languages on the, if you take some of the shelf models, they can speak it, they can write in this language, but it's not amazing.This language would be like maybe zero 1% of the mixture. So it has been included during training, but very little. So what we did here is upgrade. We trained a new model for them, but so this language was 50% of the mix, so it's much, much stronger. It knows of the dialects, it knows the, so it's yeah.So it's some example of things we can do and it's really arbitrary, custom. I think you had some of their customers, for instance, they wanted some. They wanted some 3D model that can do audio with a very good function cable. So something you wanted to put in the car in particular, they wanted this to be offline because in a car you don't necessarily have access to internet.So [00:22:00] yeah. So here we can actually build the solutions. There is no like model out of the box on this. In the internet you have this very, you have this very general model generalist, like he's strong model. But for things like this, they always want at specific solutions and on some other reasons.Sometimes they come to us is because, like they, they experiment with some closed source model. They get some prototype. They're happy with what they build. They, it works well. They're happy with the performance, and then they want to go to production and then they analyze. But it's extremely expensive.You cannot push this. It's so then they come back to us on this. They can help us build the same thing as this, but using something much cheaper on here. And here we can sometime be something 10 x cheaper by just functioning a model and it'll be better OnPrem on their old server and also much cheaper as well.So yeah,swyx: that's the drop pitch right there. Take all themoney.Vibhu: And outside of that you do, we do put open wave models so people can do this themselves. I feel like not enough people go outta their way.swyx: They're not going to, they're gonna ask them to do it as the expert. IGuillaume: think initially we didn't know, [00:23:00] we wanted completely short at the beginning of the company because, I think our study was not exactly the same as what it is today, but what we underestimated initially is the complexity of deploying this model and connecting them to everything to be sure it has access to the company knowledge on the, and it was, yeah, on, we were seeing customers struggling with this, but it was even, that was three years ago and no, things are much more complicated because now you don't just have, text on SFT on a simple instruction following.You have reasoning like your agents, you have like tools. You have a multimodal audio, so it's much more complicated than before. And even back then it was hard for customers. So they really need, have some support and this is why actually providing like always some four D position as well. The processFine Tuning and Personalizationswyx: I'm curious is there also voice fine tuning that people do?Pavan: So in this forge we also have a say unified framework. And the hope is like the er speech to text that we released earlier this year. And even the ER chart that we released last year. And I think a big people, I think there's a big, rich ecosystem [00:24:00] of people fine tuning whisper, and people want the same thing with w so it's much stronger than Whisper.And yeah, the the platform offers that kind of fine tuning yeah, which could be any kind of fine tuning. Like for instance, even sometimes people want to support new languages to this, which are tail languages, which we hope to cover. Certain natively, but if there is a language where you data and you want to frank you, I think this is a good use case.Or the other use cases, you, it's the same language, like even English but it's in a very domain specific way.swyx: Yeah. Terminology, jargon, medical stuff.Pavan: Exactly. And also there's specific acoustic conditions like there's a lot of noise or the, and. The model will do decently in most conditions, but you can always make it better.And that those are some of the use cases where you can improve it e even further. And that's one good use case for this and for text to speech. We're just releasing it so we'll have support for that soon too. I think it's similar use case.Voice Personalization Pavan: It's little different the kind of things that you want to extend a [00:25:00] text to speech model to, which could be like voice personalization, voice adaptation for enterprises.Many enterprises need very specific kind of tone, very specific kind of like personality for this kind of voice. And all of those are like good use cases for fine tuning.swyx: This one I was gonna ask you, we never talked about cloning voice clothing here. How important is it, right?Like I can clone a famous person's voice. Okay. ButPavan: the main use case would be like for enterprise personalization, like enterprises need like a lot of customization. You don't want the same. Voice for all the enterprises. Each enterprise want a customized, specialized something which is representative both their brand and also their, I guess safety considerations and the use case I think the kind of thing that you would deploy as a empathetic assistant in the context of a healthcare domain would be very different from the kind of thing that would be in a customer support bot and would be different from like more conversational aspects.I think those are the. [00:26:00] Customizations you would expect from enterprise. And that's the main use case, at least from our side.Vibhu: My, my basic example is you don't want to call to customer services and have the same exact voice. It's just, it's gonna be weird.Long-Form Speech ModelsLong-Form Speech ModelsVibhu: But also on the technical side of this, so there's like a few things in TRO that I thought were pretty interesting.He's a big fan of this paper. Oh, he said very good paper. He said this is the best SR paper he's ever read. Yeah. I've hyped up this voice paper enough. We covered it. Somewhere, but a big thing. So Whisper is known for 32nd generation a 32nd processing. You extended this to 40 minutes. There was a lot of good detail in the paper about how this was done.Even little niches of how the padding is. So it's very much needed. You need to have that padding in there, the synthetic data generation around this. I'm wondering if you can share the same about the new speech to text, right? Text to speech. So how do you. How do you generate long form, coherent?How do you generate, how do you do that? And then any gems? Is there gonna be a paper?Pavan: Yeah. Yeah. They would be a technical report. Okay. Yeah. I think I could have a lot of details.Real-Time Encoder AdvancesPavan: But me I think the [00:27:00] summary of it, actually, some of the considerations in this paper were, because we started with the wipa encoder as the starting point, and now we have in-house encoders, like the bigger time model, for instance, which we released in January.Also release a technical report for that real time model as well, which is this dual stream architecture. It's an interesting architecture. You should check it out. And there we have a causal encoder and I don't think there's any strong, multilingual causal encoder out in the community. So we thought it's a good contribution.So that's one nice encoder there. Other people want to adapt. That's a good end code. And we train it from scratch. I think her. Post stack is now mature enough that we are able to train super strong ENC codes. And some of these considerations, like spatting and stuff, is a function of the Whisper ENC code.And now that we train encoders, inhouse the design concentrations are different.Scaling Context for TTSPavan: And for the question on text to speech, I think that's also leans onto the original auto aggressive decoder backbone. I think, it says very, almost identical considerations. I think the long context in it's not even long con, [00:28:00] so the model processes audio at 12.5 herds, so one second maps to like 12.5 tokens.So I think one minute is like 7.8 tokens. You can get like up to 10 minutes in eight K context window and get half an hour and 30 K context window. So that's and 30 2K context is something that's we are very comfortable training on. We can extend it even much longer. 1 48 K. Okay. You can naturally see how it can extend to even our long generations.Yeah. We need the. Like data recipe and the whole algorithm to work coherently enough through such long context. But the techniques are some way very similar to the text, long context modeling. And the key differences, it's just doing flow matching order regressively instead of a text open prediction.swyx: Okay. I think that was most, most of the sort of voice questions that we had. ButWhat Makes a Model SmallVibhu: I have a big question on Mr. Al, Mr. Small. So what is small? How do we define [00:29:00] small? What is this? What is this? I remember the days of Misal seven B on my laptop. The snuff fitting on my laptop. I could run it on the big laptop, butGuillaume: it's just additional.Question of terminology, like here what we did, baseball is north active parameters, but it's true. Really not give it another name, but yeah, we could have called it medium, but only, I,I suppose it's a model that we released mixture of experts. It's a model that combines different model before which we were doing the same, is that we had one model, general model for Israel. Doing instruction following, were like a separate model that was Devrel trial. So qu coding specify specific to code with another model for Reason Maal.So this were separate artifacts built by different team at trial on what we're doing is basically merging all of this. It was, you had pixel trial was the first vision model. We was like a separate model on the way we do things internally is that we have one team focus on one capability, build one model.On the means mature, mature enough, we decide to merge this into the [00:30:00] matrix. But here it was the first time we basically match all of this into one. But there are some other things we did at first time to merge time, for instance, like more capabilities or function coding I think would be, are, it's going to be much, much better in this trial, small platform.But but yeah, so it's our latest model on the working is,Vibhu: and yeah, key things is it's very sparse. Six, be active pretty efficient to serve. 2 56 K context. Yeah,Merging Capabilities vs Specialistsswyx: I think what's interesting is just this general theory of developing individual capabilities in different teams and then merging them.Where is this going gonna end up?Vibhu: Like we've seen the five things put together in this. Yeah. What are the next five teams?swyx: I think actually OpenAI has gone away from the original four Oh. Vision of the Omni model. This was what they were selling. All modalities and all modalities out.But I feel like you might do it.Guillaume: I think there's some mod where it's not competitive use, for instance for audio. For audio here, if you want to do transcription, I think it makes no sense to use a model. If you just want to trans tech it, it'll be very inefficient. If you want to do audio, you probably just want to be the [00:31:00] one VR 3D model performance essentiallyswyx: the same.It's going to be incredibly cheaper. So here, that's why we wantGuillaume: to have a separate but just does this. Yeah, I think the question is just, yeah. If you are to, to your model. By speech and you asking like a very complex questions on how you do this on the, just to cascade things. Do you want to put a d in a model that has like a one key around it?It's like a, not a competitive discussion, I think unaware if you doing into the direction, but that's possible. Of course. But yeah. But I think for us, the next capabilities we want to try to integrate into these models when we are going to be yes, like marketing or no reasoning better, I think more capabilities that people don't talk too much about, but at high bottom, I think for our customers in our, on different industries, for instance, things are around like a legal computer.I design all these things that is this males out of the box are to put at that. Because people, if you don't prioritize this, there is not like too benchmark on that. Butswyx: this done how toGuillaume: make this good and this just start to do the work. Extracting some that processing it [00:32:00] expression. So yeah.But we are offering the imagine to this.swyx: I think for voice. Yeah. The key thing I think over maybe like the last year or so with VO and gr Imagine and all these things is joining voice with video, right? Which people don't understand spatial audio because like most TTS is just oh, I'm speaking to a microphone in perfect studio quality.But when you have video, like the voice moves around.Pavan: That's true. The constitution was a little different in the sense that there it's like a a standalone artifact where you get the whole thing and you consume it. But in a conversational setting, it's a, you need the extreme low latency.swyx: Yeah,Pavan: streaming would be one of the primary concentrations.swyx: You can build a giant company just doing that, right? So you don't need to do the voice, but I was just know on the theme of merging modalities, that is something I, I am like, wow. Like I didn't, everyone up till, let's say mid last year was just doing these like pipelines of okay, we'll stitch a TTS model with a voice thing and a lip sync [00:33:00] thing and what have you.Nope. Just giant model. Yeah.Open Source MissionVibhu: I have a two part question. So one is, it's still open. It seems like open source is still very core to what you guys do and I just have to plug your paper. Jan 2024. This is the one trial of experts like. Very fundamental research on how to do good.Moes paper comes out very good paper for anyone. That's just side tangent. No.swyx: This thing caused, we bring back, eight by 22 was like the nuclear bomb for open source. I think it takes Shouldn be more seven B more. Yeah. Yeah. But this is a bigger opposite than me.Yeah. Yeah I don't remember this. I remember, I don't think it was January, right? It was like new reps it was, it dropped during new reps and everyone in Europes was December of 25th, I think. Yeah. The model was did as well.Vibhu: It's just a little update probably.swyx: Yeah. No, but you have a point to make.Vibhu: No, you gotta check that. But then, I just want to hear more broadly on open source for you guys, and when you had asked earlier [00:34:00] about what's next, what are the other, side tapes working on you. You put out Lean straw. This,swyx: it's not necessarily surprise. I was like, I don't, this doesn't fit my mental model or Misra.Guillaume: Yeah. First for open source in general, I think it's really something which looks to the January of the company. I think we started it per once, is we so we have open sourcing with, since the beginning and even before this. So before this, so me and Tim were at Meta, we released LA and I think what was really nice.To see that before this, for most researchers like universities, it was impossible to work on elements. There was no alien outside. And if you look at many of the techniques that were developed after, for instance, was open source all this post-training approaches like even DPOD, like preference optimization, all of this were done by people that had access to this portal.And it'll have been impossible to do without this. So it's really making sense, move faster. So we really want to contribute to this ecosystem. I think like the deep and also like very lot of impact. All these papers that are I think in the open source community are really helping the science community as a whole to move faster.So [00:35:00] we want contribute to this ecosystem. That's why we're releasing very detailed technical reports. So ma trial and our first reason model, and ation, lot of results, things that work, things that did not work as well. Think helpful on the, yeah, so for the audio model also to share a lot of details, share of them for real time model.And the, yeah, so we really want to continue this, basically belong to this community of people who share science. I think we really don't want to be, leading in a world where the smartest model, the best models are only behind, close doors. Only accessible to a shoe companies that we, as a power to decide we can use them on it.I think it's a scary future. We don't want to live in, we really want this model to be accessible to anyone that want. Intelligence to be used unaccessible by anyone who can use it. So yeah, so that's why we are pushing this mission and source model. Yeah. So not, so yeah, no strategy. So it's open source, not the first model, so not the best on the Yeah.Lean and Formal ProofsGuillaume: LIN trial I think is also one step into this direction. So it's yeah, a bit different than what we are usually releasing. But we have a small team internally [00:36:00] working on them. Formal proofing, formal math. So I think a subject we care about in general and we were working on reasoning. I think we started too early before doing reasoning without LMD is very hard, especially when you work with formal systems because the amount of data you have is negligible.It's addressable community of people writing like formal proofs. But the reason why we like it is because I think there is if you look at what people are doing with reasoning, is there, the problems that you can use. Are usually going to be problems where you can verify the output. So for instance, all this ai ME problem where the solution is a number between 100, like a thousand.So you can verify, compare this with a reference or it's an expression. You can actually compare the output expression generic with the reference. But there are many, most of them have problem and most of the reason problem. There is no like way to easily verify the solution. If the question is show that F is continuous, cannot compare in the reference, right?If it's a probe that this is true or probes is properties, there is no way to. You cannot act, simply verify the correctness of your proof. So it's hard to apply the, there is no referable reward here. So [00:37:00] what you could provide is of course, like a judge and judge that will look at your proof. But it's very hard and it's very, you could do certain, some reward hacking happening there.So it's difficult. You could provide like a reference proof, but then there are also many ways to prove the same thing. So if the model says give negative reward because it's a different poop, maybe it was still digit proof, just different. So it's not going to work well. What's nice with lean and with formal probing is that you don't have to worry about this whatsoever.We just,swyx: they're all function is largely compiles in lean is functionally the same. Exactly.Guillaume: It's like a problem if it compiles it's correct. It's very easy. And you can apply this and then you can,swyx: it's just way too small. So no human will actually go and do it.Guillaume: Yeah, that's exactly.It's the only people can do it. It's like a very small committee of people doing a PhD on that. So it's super small. And it's sad because it's actually very useful on not just mat, but also in software verification. So for instance, software verification today. So tiny market. Very few industries work on this and we need that.It's usually going to be like companies like building airplanes, air robotics,swyx: likeGuillaume: things [00:38:00] where they absolutely want to be sure. Life depend on this, but it's very rare that people formally verify the correctness of their software. But I think one of the reasons for this is simply that it's just hard to do.swyx: Are you think of TLA plus? It's the language that some people do for software verification? No. That people use in a ference, but but yeah, it's the reason I think why people don't use it more and why this industry is not as big as could be is because it's very hard. But now with cutting edges that are there, it's going to be very different.Guillaume: We're going to see much more of this. So I think yes, industry there is going to be much larger in the future that we, these models. So yeah. Here also anticipating this a little bit, we wanted to work on that because it's proving like a math theory and like a, essentially the same tools.swyx: Yeah.Reasoning Transfer and Agentsswyx: One of my theories is that because the proofs takes so long, it's actually just a proxy for long horizon reasoning and coherence and planning. Maybe a lot of people will say okay, it's for people who like math. It's for being okay. It's like a niche math language. Who cares? But actually, and you use this as part of your data mixture for [00:39:00] post-training and reasoning, actually, it might spike everywhere else.Yeah. And I think that's un under explored or no one's like really put out a definitive paper on how this generalizes.Guillaume: Yeah, absolutely. AndPavan: I think evenGuillaume: that's what we're seeing already. For instance, you should do some reasoning on math as then the American should do reason even.Yeah. In the early stage. So we, the, there is some transfer, some sort of emergence that happens. And I think some, it's also interesting, it's not just I think the topic in general, but it's, there is a lot of connection with this on including agents because. Sometimes the model can see like a three that it has to prove it's very complex, but then it can take the initiative to say, I'm going to prove this three lr.I'm going to suggest three Rs, and I'm going to in parallel prove each R. So three of them in parallel with sub agents, but I'm also going to prove them in theory and the three tool so you can do this also. Pretty interesting. You can, even if you fail to put one of the LeMar, you can actually, maybe you succeed to put the normal lema too, so you get some possible reward here.So it's a bit less Spartan issue, just get to zero one for the entire thing. [00:40:00] So it's pretty interesting. I think we can actually,Vibhu: yeah, it's also an interesting case just for specialized models in general, right? Like the cost thing you show is pretty interesting yeah, similar score wise, you are, thirty, seventy, a hundred fifty, three hundred bucks.Smaller.swyx: I think cost is a bit unfair, right? ‘cause this one is at like inference cost. It's always there on top with their margins on top of it. But, we don't know anything else, so we gotta figure it out.Vibhu: Okay.Next Frontiers in TrainingVibhu: I did wanna actually push on that more. Not on cost, but you mentioned about, okay, it's a great way to have verifiable long context reasoning.What are other frontiers that, I'm sure you guys are working on internally, there's a lot of push of people pushing back on pre-training. Scaling, RL pushing, compute towards having more than half of your training budget. All on rl. Where are you guys seeing the frontier of research in that?Guillaume: You mean theVibhu: just in foundation model training in the next, one thing that you guys do actually is you do fundamental research from the ground up, right? So you probably have a really good look at where you can [00:41:00] forecast this out.Guillaume: Yeah. I think for us we're still working a lot on the pre-training side.I think we are very far from situational, the pre-training. I think ML four preprinting will be like big step compared to everything we have done before. So we are pretty excited about this. And I think on the other side, I think now we have more and more to think about this algorithm that will actually support this very long trajectories.I think when it was, for instance, GRPO for it doesn't really work this any bit of policy. Which was okay initially because you are solving math problem that can be solved in like a few thousand tokens. So the model can alize them pretty quickly. So when you do your update, the model is never too far off.It's never too far off. But now when you are moving towards this kind of problems where certain takes hours, like six hours to get a reward, then your model is co pick places. So you have bi new infrastructure that supports this, but also new A, so now everything we're doing internally, we're trying to. Build some infra that we actually anticipate is what we have in six months, one now, which is this extremely no scenarios on the, I think when we started Missal, part of me and [00:42:00] we wanted to, is very nice under element where people are there, they can do research, they like with a lot of resources.So it was nice. I think things changed a lot when I think when J Pity came out. I think after that I think was. This one is same again. But but yeah, but it was nice. And I think we also want to work part of this descrip beforeswyx: coming to the end.Hiring and Team Footprintswyx: We're just, obviously, I think you guys are doing incredible work.You've, they are a very impressive vision for open source and for voice. What are you hiring for? What's the what are you looking for that you are trying to join the company?Guillaume: Yeah, so we are hiring a lot of people in our sense team. We're hiring, in all our offices. So we have a, our H two is in France in Paris.We have a small team in London. We like a team in Pato as well. Co we open some offices in in SAU, in Poland. So one in Zurich. We also like some presence in New York as well on Sooner one in San Francisco. So we all bit either way also like hiring remotely. So we're going the team trying to hire like very strong people.I think we want to stay, so the team is not. Instead of fairly small team. [00:43:00] But I think we want to keep it that way. ‘Cause we we find it quite efficient. So like a small team they agile so yeah.swyx: Okay.AI for Science Partnershipsswyx: Let's focus on science and the forward deployed. We actually are strong believers in science.We started the our new science pod that focuses specifically on the air for science. What areas do you think are the most promis.Guillaume: What we're pretty excited about right now, and something we have already started doing or that we'd probably be able to share more about this in a couple of months, is that we are exploring AI for science.And there are a lot of areas where we think that you could get some extremely promising buzz. If you were to apply AI in these domains. There are a lot of long inputs. You just have to find these domains where actually AI has not been yet applied, and it's usually hard to do because the people working in those domains don't necessarily know the capability of these models.They don't know. How I would just have to pair them with Yeah, exactly. Your researcher slashing, which is actually hard to do. But this matching, we're doing it naturally with our customers. So we have some company we are very closely with. So for instance, ISM Andreesen are one of our partners, so we're doing some research with them on their other, like tons of extremely interesting problems.Columns in physics, in [00:44:00] science matter science that they're essentially the only ones to work on. ‘cause they're doing something No, no one else is doing on the, yeah. So there are many domains where AI can actually revolutionize things. Just you have to think about it on you familiar with what can do or to apply it.So yeah, it's something where more modeling with our partners, with our customers sort AI for s, but.swyx: Yeah. Okay.Forward Deployed Skillsswyx: And then for deployed what it makes a good four deployed engineer, what do they need? Where do people fail?Guillaume: I think it's usually you need people that are very familiar with the tech and not necessarily with a lot of research expertise, but that are actually pretty good at using this model that can actually like that know how to do functioning, that know how to like, start some error pipeline.And it's it's not easy. It's something that mucus. Majority of companies will not be able to do this on their own. So here I think we need people that are, that like to solve problems that are accept solving some complex, very concrete problem. It's applied science basically.And yeah, so I think it's not too different. I think from the case you need in research because it's essentially you are trying to find solutions to problems that in [00:45:00] customers have not yet. So sometimes it's easy. Sometimes you're here to do the work. You have to like create synthetic data.Find some edge case. So it can be, yeah. Depends on the problem. But but yeah, you have to, I think it also a bit of patience on the be creative. I think very similar skill is Asian,Pavan: the diversity of the work they do. It always surprises me. It's it's, it goes all the way from the kind of stuff they encounter in industries.It's just very interesting. I think.swyx: Any fun like success anecdotes.Guillaume: Yeah, it can be actually training this small model on edge that just we do one specific thing can be like training some very large model without some specific languages as well. Making models really good at some tube use, like for instance, computer ID design, these kind of things.Is that pairing with vision as well? Yeah,Pavan: and the fact detection for chips or like in, in factories identifying things like it, the. Diversity could be anything where you can deploy these foundation models. So yeah the work to make it work in that specific setting, basically whatever it takes to make it like add value in that, by the way, workflow.Vibhu: Yeah. [00:46:00] And it goes across the stack, right? Like even just pulling up the website like.swyx: It's so broad on compute. It is so broad.Vibhu: We didn't even touch on if you have a coding CLI tool. One thing you guys were actually like, I think the first tool was agents, ral agents. You had the agent builder, you can serve it via API and all that.And I'm guessing forward deploy people.Guillaume: Yeah.Vibhu: Help build that out and stuff.Customer Feedback LoopGuillaume: It is also why we are, so we're doing many things, but I think that's also part of the value proposition that sometime know customers. They're always very. Extremely careful about their data and they don't want to, they don't like, trusting so many partners, trusting one partner for code, giving the data to another third party for like audios and another one.So they don't like this here. What they really like with our approach that we can help them on anything so they don't have to send the data to so many clouds. So yeah,swyx: I think that there can be many orders of magnitude more. F Ds then research scientists and they don't need your full experience, but they're still super variable to customersGuillaume: in practice.These two teams [00:47:00] are still quite intertwine, very often. Yeah. So first of all, they're using the same tools, the same data pipeline and everything on the, it's it's very helpful for the science team to get the feedback and the solution team ‘cause they can. Look at these customers are trying to do this.This is not working. It can really be show in the next version. Yeah. But this is basically a real world eval. Yeah, it's real world eval and it's not something, for instance, if you're just working in the lab, it's just ships model. But you don't do this work of for customers. You have no idea for whether your model is good at this H case.For instance, you even in year found this, right? So yeah, there is a very gap, big gap between the public benchmarks that are very like academic. OnPavan: the rare cases are just very diverse and in the specific concept of a customer, you can fine tune and make it like first evaluate, create a solid eval, benchmark, and then measure in the context of their, the kind of audio.Like for instance, one use case is literally just, there's the word for kids and they have to just say it out. It's a very specific thing. You're just saying one word and then you have to you, you'll grade the kid whether they did it right or not. It's [00:48:00] like R for, but so there're very diverse use cases and the idea is that they, the.Applied scientist engineer will go and make it better. And then from the learnings we incorporate it into the base model itself. So it's it's just better out of the box.Vibhu: Yeah. It's a good full circle system. Like the foundation model evals are all just proxies of what you really, you're never gonna have one that says it, it doesn't make sense for there to be, a one word transcription like that.It's not something you wanna fit on. Perfect.Wrap Up and Thanksswyx: Everyone should go check out everything that Michelle has to offer and try the TTS model, which will link in the show notes. But thank you so much for coming tha thanks. Such a stretch. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.latent.space/subscribe

The much anticipated, Emmy and Golden Globe Award-winning medical drama The Pitt finally hits HBO max screens in the UK this week. Samira talks to lead actor Noah Wyle who plays Dr ‘Robby' Robinavitch, about being back in a high octane emergency department drama decades after making his name as Dr Carter in ER.The Elizabethan composer John Dowland died 400 years ago this month. Next weekend there will be a celebratory Weekend of his music performed at London's Wigmore Hall. We speak with two musicians who will be celebrating Dowland's music: Counter tenor Iestyn Davies and lutenist Elizabeth Kenny.Does opera need to be telling new stories? The ENO's former artistic director John Berry, and playwright Mark Ravenhill join us to discuss. Presenter: Samira Ahmed

Eno joins the show to discuss the improved Stuff metrics for Cardinals rotation arms Richard Fitts, Matthew Liberatore, and Dustin May. What is the ceiling for the Cardinals rotation this season? Plus, what does Eno make of the Cardinals transition from bullpen arm to starter with Kyle Leahy.See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Paul Eno is a paranormal researcher, lecturer, and author best known for his work Dancing Past the Graveyard, which examines ghost phenomena through a blend of field investigation, historical analysis, and theoretical interpretation. Eno explores hauntings, apparitions, and poltergeist activity while questioning traditional assumptions about the afterlife and the nature of paranormal experiences. His work emphasizes that such phenomena may not always fit conventional “ghost” explanations, encouraging a broader, more nuanced understanding of consciousness, environment, and unexplained events.Become a supporter of this podcast: https://www.spreaker.com/podcast/the-x-zone-radio-tv-show--1078348/support.Please note that all XZBN radio and/or television shows are Copyright © REL-MAR McConnell Meda Company, Niagara, Ontario, Canada – www.rel-mar.com. For more Episodes of this show and all shows produced, broadcasted and syndicated from REL-MAR McConell Media Company and The 'X' Zone Broadcast Network and the 'X' Zone TV Channell, visit www.xzbn.net. For programming, distribution, and syndication inquiries, email programming@xzbn.net.We are proud to announce the we have launched TWATNews.com, launched in August 2025.TWATNews.com is an independent online news platform dedicated to uncovering the truth about Donald Trump and his ongoing influence in politics, business, and society. Unlike mainstream outlets that often sanitize, soften, or ignore stories that challenge Trump and his allies, TWATNews digs deeper to deliver hard-hitting articles, investigative features, and sharp commentary that mainstream media won't touch.These are stories and articles that you will not read anywhere else.Our mission is simple: to expose corruption, lies, and authoritarian tendencies while giving voice to the perspectives and evidence that are often marginalized or buried by corporate-controlled media

Baxie speaks with Dutch author and visual artist Bette Adriaanse (Bette A.). For the second time in less than a year Bette has teamed up with the legendary Brian Eno to produce two separate projects. The first of which to collaborate on the book “What Art Does: An Unfinished Theory”. Their second collaboration is a full multi-media presentation called “Slow Stories”. This is a collection of two short stories that Bette has been developing over the last twenty years. The stories have been set to a stunning musical score composed by Brian Eno—combined with visuals created by both Bette and Eno specifically for this project. “Slow Stories” is set to be released on March 3rd. And Bette talks about all of it as well as about her friendship with Brian—one of music's most legendary producers (Talking Heads, David Bowie, U2, Peter Gabriel, and more!) Listen on Apple Podcasts, YouTube, Spotify, and on the Rock102 app! Brought to you by Metro Chrysler Dodge Jeep Ram of Chicopee!

This piece for the Century of Sound project began with a single field recording drawn from the archive of the Pitt Rivers Museum, Oxford. Rather than this recurring functioning as an objective document of place or event, I approached the recording as a temporal fracture, a sound that had already been severed from the moment that produced it. I was inspired by the thought that a recording is made not to preserve presence, but to register our disappearance and that an archive does not store the past intact, it stores its decaying remains. Thus all recorded sound is hauntological, and exists as an audible ghost or spectral presence of something or someone, the reanimation of the past as a memory becoming a new memory and so on, each time changing its perception. The record I used carried voices and environmental details (mostly of work activities) that no longer exist, yet through the recording can never fully vanish, as sound has folded time back on itself.The entire composition is derived from this single archival recording, utilising a range of techniques and methods serving to evoke the idea of decay and ephemerality. My influences were from Basinski's Disintegration Loops, early Fripp and Eno tape looping (Frippertronics), and ambience and texture processing such as that used by Burial, all of which led to an approach to the recording where erosion and degradation was treated as source material. The conversational voices and percussive hammering elements, were fragmented and reassembled to drift in and out of intelligibility. suggestive of memory replayed imperfectly, half-heard and misremembered. Here noise reduction processes from Izotope RX were used against their intended purpose, rather than cleaning the recording, they are used to reveal what remains when inverted, for example the removed reverb, or the removed spectral artefacts, recording scars, and otherworldly sonic residues. Also analogue processes were central to the compositional methodology, where the recordings and echoes were run through delay pedals and recorded on to cassette, the composition was then rerecorded using worldising (playing sounds in to a space and rerecording them) as a method. Through the repeated rerecording, tape saturation, wow and flutter, and worldising techniques, distance and materiality became embedded into the composition.As such, the composition does not progress linearly, but I hope that voices and sounds return altered, degraded, unresolved, yet seeming forming a newer narrative where the listener is evoked into considering their own sound world and memory. I am trying to evoke a past which is neither accessible nor gone, but caught in a loop, yet re-embedded in the present. In this sense, the work reflects a hauntological impasse, where the archive continues to speak, even as it itself continues to disintegrate.Laarim elder recounts the history of his people reimagined by Neil Spencer Bruce.———Part of the project A Century of Sounds, reimagining 100 sounds covering 100 years from the collections of the Pitt Rivers Museum at the University of Oxford. Explore the full project at citiesandmemory.com/century-sounds

Nehvaležna bitja so četrti celovečerec na Češkem živečega slovenskega režiserja Olma Omêrzuja. Kot že v Družinskem filmu, je tudi tokrat v središču družina – ločena starša, hčerka s prehransko motnjo in sin, ki se počuti zapostavljenega. Eno od ključnih vlog igra Timon Šturbej, glavno vlogo očeta pa irski igralec Barry Ward, ki je bil pri filmu tudi izvršni producent. Ob premieri filma je pogovor z režiserjem posnela Tesa Drev Juh. V njem Omerzu med drugim govori o občutku brezizhodnosti, ki ga je želel vnesti v film, o tem, kako težko je danes nagovoriti gledalce, pa o posebnem razmerju med otroki in odraslimi v okviru družine, ki otežuje resnično poznavanje drug drugega.

  When Daniel wrote that he had a new mix based around silence I knew it would be good. Then I saw the tracklist and I knew it would be great. He includes cuts from some of my favorite artists - Halftribe, Innesti, Sonmi451, Loscil, and A Produce. The A Produce track is one of my favorite ambienbt tracks of all time. Here's what Daniel says about his new mix: Claude Debussy once wrote: “The music is not in the notes, but in the silence between them”, suggesting that music's emotional impact, beauty, and expression come from the pauses and spacing between sounds.  The first thing I think of is Eno's classic Music for Airports - man did I fall in love with that album.  Roach's Dream Circle comes to mind - low and slow - the music just seems to breathe.  Of course you have the steady state drone stuff from Grassow and friends, which I like - but there is no real structure - that's the point I guess.  I tried to pick work for this mix that had at least a bit of melody, but plenty of silence to define the notes.  There is a sweet spot that when achieved sends me at least into a deep peaceful space.  I'm thinking we all need to spend some time in that space these days to recharge and nurture our sanity.  Hoping this mix might help with that my friends.  Thanks, Daniel, for another excellent mix. Cheers!  T R A C K L I S T : 00:00   Halftribe & Spinnet - A Minimal Resolution (Patterns of Sync 2020) 09:09   Snufmumriko - Mot Nattens Hjärta (Sekunder, Eoner 2019) 12:12   ASC - Find Yourself (Tales Of Introspection 2025) 22:48   Innesti - Nothwithstanding (Filament and Place 2021) 28:00   Sonmi451 - Oxygen Is Flowing (Oxygen Is Flowing single 2025) 33:12   Loscil - Stella (Clara 2021) 42:23   A Produce - A Smooth Surface(Edit) (White Sands 1995) 47:40   Hipnotic Earth - Repose (The Waters of Home 2017) 57:00   Lab's Cloud - Rising (The Structure of Emotions 2021) 63:58   end

Hey! Ho! Let's Go! Welcome to our bi-monthly ENCORE PRESENTATION of classic REVOLUTIONS PER MOVIE episodes from the vault! The incredible Craig Finn on the amazing Ramones' cult film Rock 'N' Roll High School...what more can I say, Principal Togar...this episode rules...enjoy!(Episode 51 originally aired on August 24th, 2024).Original Show Notes:This week, we talk to CRAIG FINN of THE HOLD STEADY & 'That's How I Remember It' podcast about the legendary cult classic ROCK 'N' ROLL HIGH SCHOOL! We discuss how discovering THE RAMONES is a young person's game, reading THRASHER magazine in the school library, not knowing what bands sounded like, KTEL record complitaions and ROCK 80 LP, the Summer of 1980 AM Rock Radio, Craig seeing STYX's KILROY WAS HERE tour, vomiting at a DEVO show, $1.92 new wave shows, fantasing about where bands are getting coffee in your hometown when they come through on tour, the VHS release of the film, ROAD TO RUIN LP, Craig getting guitar lessons from punk legend Chris Osgood of The Suicide Commandoes, the singleminded yet 4 headed songwriting beast that was THE RAMONES & the cultish nature of the band, Joe Dante's script, how producer ROGER CORMAN wanted to cut out the middle of The Ramones songs, DISCO HIGH, teaching the Ramones to walk in the film, staying overnight to get concert tickets, getting punished by your parents by them forcing you to go see a LAURIE ANDERSON concert, our big Ramones regrets, the trouble with filmming the Ramones' live footage and how it almost started a riot, learning about Chicken Vindaloo through the band's song lyrics, getting the courage to go to a punk rock show, Violent Femmes, our first punk/new wave show we went too, clove cigarettes, The Replacements, ticket prices vs. record prices, under attended hardcore matinee shows, Clint Howard, PJ Soles & Vince Van Patton, does the movie hold up as a cult film, High School permanent records, how the soundtrack turned us on to the MC5 and ENO and the search for those records, Mudhoney & Tad, how the film smartly adds more and more Ramones to the film as it goes on, the Americana side of the Ramones, what Ramones lyric would Craig wished he had written and what lyric of his is the most Ramones, what would a Roger Corman produced Hold Steady movie consist of and what role Clint Howard would play in it and so much more!!!So, let's tear up our permanent records on this episode of Revolutions Per Movie!!!CRAIG FINN:https://craigfinn.net/https://theholdsteady.net/REVOLUTIONS PER MOVIE:Host Chris Slusarenko (Eyelids, Guided By Voices, owner of Clinton Street Video rental store) is joined by actors, musicians, comedians, writers & directors who each week pick out their favorite music documentary, musical, music-themed fiction film or music videos to discuss. Fun, weird, and insightful, Revolutions Per Movie is your deep dive into our life-long obsessions where music and film collide.The show is also a completely independent affair, so the best way to support it is through our Patreon at patreon.com/revolutionspermovie. By joining, you can get weekly bonus episodes, physical goods such as Flexidiscs, and other exclusive goods.Revolutions Per Movie releases new episodes every Thursday on any podcast app, and additional, exclusive bonus episodes every Sunday on our Patreon. If you like the show, please consider subscribing, rating, and reviewing it on your favorite podcast app. Thanks!TIP JAR:ko-fi.com/revolutionspermovieSOCIALS:@revolutionspermovieBlueSky: @revpermovieTHEME by Eyelids 'My Caved In Mind'www.musicofeyelids.bandcamp.com ARTWORK by Jeff T. Owenshttps://linktr.ee/mymetalhand Hosted on Acast. See acast.com/privacy for more information.

Bowie's early years have been scrutinised repeatedly but people tend to speed through the last act, from the early ‘90s to his death in 2016. Alexander Larman's ‘Lazarus: The Second Coming Of David Bowie' looks at his resurrection and the mystery of his final days in Manhattan in attractively honest detail, a book that's as fondly critical of his artistic decisions as it's celebratory. Under discussion here … … ‘David Bowie was a fictional invention and much of his life an act' … how wrong so many album reviews turned out to be … “he liked to be liked and he put a lot of effort into being liked” … Eno, Tony Visconti, Nile Rodgers, Pet Shop Boys and his endless search for collaborators … the Lucian Freud incident at the Dorchester … Scott Walker's taped message: “I see God in the window” ... “he trusted in the idea he was a genius” … the sharp contrast been his public image and private life … how his Lord's Prayer at the Freddie Mercury tribute was a deliberate attempt to steal the show … the piercing question Tin Machine were asked on ‘Wogan' … and the struggle to find anything sincere in his interviews. Order ‘Lazarus' here: https://www.amazon.co.uk/Lazarus-Second-Coming-David-Bowie/dp/1917923449Help us to keep the conversation going: https://www.patreon.com/wordinyourear Hosted on Acast. See acast.com/privacy for more information.

Bowie's early years have been scrutinised repeatedly but people tend to speed through the last act, from the early ‘90s to his death in 2016. Alexander Larman's ‘Lazarus: The Second Coming Of David Bowie' looks at his resurrection and the mystery of his final days in Manhattan in attractively honest detail, a book that's as fondly critical of his artistic decisions as it's celebratory. Under discussion here … … ‘David Bowie was a fictional invention and much of his life an act' … how wrong so many album reviews turned out to be … “he liked to be liked and he put a lot of effort into being liked” … Eno, Tony Visconti, Nile Rodgers, Pet Shop Boys and his endless search for collaborators … the Lucian Freud incident at the Dorchester … Scott Walker's taped message: “I see God in the window” ... “he trusted in the idea he was a genius” … the sharp contrast been his public image and private life … how his Lord's Prayer at the Freddie Mercury tribute was a deliberate attempt to steal the show … the piercing question Tin Machine were asked on ‘Wogan' … and the struggle to find anything sincere in his interviews. Order ‘Lazarus' here: https://www.amazon.co.uk/Lazarus-Second-Coming-David-Bowie/dp/1917923449Help us to keep the conversation going: https://www.patreon.com/wordinyourear Hosted on Acast. See acast.com/privacy for more information.

Bowie's early years have been scrutinised repeatedly but people tend to speed through the last act, from the early ‘90s to his death in 2016. Alexander Larman's ‘Lazarus: The Second Coming Of David Bowie' looks at his resurrection and the mystery of his final days in Manhattan in attractively honest detail, a book that's as fondly critical of his artistic decisions as it's celebratory. Under discussion here … … ‘David Bowie was a fictional invention and much of his life an act' … how wrong so many album reviews turned out to be … “he liked to be liked and he put a lot of effort into being liked” … Eno, Tony Visconti, Nile Rodgers, Pet Shop Boys and his endless search for collaborators … the Lucian Freud incident at the Dorchester … Scott Walker's taped message: “I see God in the window” ... “he trusted in the idea he was a genius” … the sharp contrast been his public image and private life … how his Lord's Prayer at the Freddie Mercury tribute was a deliberate attempt to steal the show … the piercing question Tin Machine were asked on ‘Wogan' … and the struggle to find anything sincere in his interviews. Order ‘Lazarus' here: https://www.amazon.co.uk/Lazarus-Second-Coming-David-Bowie/dp/1917923449Help us to keep the conversation going: https://www.patreon.com/wordinyourear Hosted on Acast. See acast.com/privacy for more information.

durée : 00:05:03 - Dans la playlist de France Inter - Un inédit de David Byrne en Playlist de France Inter, peu après la sortie récente de son album « Who Is The Sky ? » Vous aimez ce podcast ? Pour écouter tous les autres épisodes sans limite, rendez-vous sur Radio France.

Don and Dude continue the “I Love the 80s” tour with a stop in 1982, a year when rock still ruled the charts even as the culture splintered into cable TV excess, recession anxiety, and neon‑lit moral ambiguity. One host brings a haunted, lo‑fi folk song cycle from Bruce Springsteen that strips away arena gloss to stare down American failure, while the other counters with Brian Eno's fog‑shrouded ambient landscapes, where memory, geography, and unease blur into one continuous sound world. Together, the records trace how 1982 stretched rock from bombastic stadium anthems to cassette‑recorded confessions and experimental soundscapes that felt more like places than songs.The AlbumsBrian Eno – Ambient 4: On Land (1982) A dark, place‑obsessed ambient record, Ambient 4: On Land finds Eno retreating from pop structures into immersive soundscapes built from drones, treated instruments, and environmental textures. Working largely alone with tape composting and field‑recording‑like sounds, he reconstructs half‑remembered English coastal and marshland environments so the listener feels inside foggy, unstable “memory spaces” rather than listening to background music. The album pushes ambient away from soothing wallpaper toward quietly unsettling figurative music that would shape film scores, dark ambient, and textural rock for decades.Bruce Springsteen – Nebraska (1982) Recorded at home on a four‑track cassette, Nebraska strips Springsteen down to voice, guitar, and harmonica for ten stark story‑songs about killers, drifters, laid‑off workers, and families coming apart on the American margins. Intended as demos for the E Street Band, the tapes were released essentially as‑is because their raw immediacy captured a moral and emotional weight the studio could not, turning lo‑fi hiss and dead room sound into part of the storytelling. Long viewed as one of his bravest works, the album reframes the early‑80s landscape as recession‑era noir, where debts “no honest man can pay” blur the line between crime, survival, and faith.Diggin' AlbumsAlter Bridge – Alter Bridge (2026) Hard‑rock veterans Alter Bridge deliver towering riffs and soaring melodies that refine the heavy, emotionally charged sound they have been sharpening for two decades.Toto – Toto IV (1982) Studio‑honed pop rock at its most polished, Toto IV marries big hooks and meticulous production on songs that helped define early‑80s radio sleekness.Butch Dains – “Amelia” (2025) Retro‑minded singer Butch Dains leans into gentle, 50s‑inspired pop that matches his “always clean never nasty or mean” ethosPeter Gabriel – “Been Undone” (o, Dark‑Side Mix) (2026) The lead track from Gabriel's forthcoming album o turns a mid‑90s idea into a quietly luminous meditation on all the ways a life can come apart, carried by subtle grooves and harmonium‑like warmth.Follow & SupportFollow the show on Instagram, Facebook, Threads, and Bluesky @albumnerds, and support by subscribing, rating, reviewing, and sharing."There is some Eighties music that is just timeless, and some that is so dated it's embarrassing.” - Grace Jones

durée : 00:57:42 - Very Good Trip - par : Michka Assayas - Nous avons rendez-vous sur France Inter avec l'avatar le plus fascinant de toute la carrière de David Bowie, de sa période dite berlinoise de l'année 1977. Vous aimez ce podcast ? Pour écouter tous les autres épisodes sans limite, rendez-vous sur Radio France.

Matt Nathanson returns!Matt returns and we talk about U2 AGAIN!?! Heck Yeah! And, yes, we've already done an episode about "The Unforgettable Fire" but when Matt Nathanson says he wants to do an episode about the album, you let him.Plenty of other discussion including the Tampa Pig Jig and Megan Moroney, Live Aid, GNR, R.E.M.'s "Green," The Black Crowes, listening to the same song over and over, Def Leppard, MLK, the influence of Eno and Lanois, and much more.  Check out Matt Nathanson at:  https://mattnathanson.com/Check out other episodes at RecordsRevisitedPodcast.com, Apple Podcasts, Castbox, iHeartMedia, Google Podcasts and Spotify. Additional content is found at: Facebook.com/recordsrevisitedpodcast or twitter @podcastrecords or IG at instagram.com/recordsrevisitedpodcast/ or join our Patreon at patreon.com/RecordsRevisitedPodcast

Film is generally a fixed medium: the scenes are shot, the edits are made, and the final version is the one and only movie you'll see. Filmmaker Gary Hustwit flips this convention on its head, introducing his project "Eno" — a documentary about the musician and composer Brian Eno that reinvents itself every time you watch it ... and never ends the same way twice. Hosted on Acast. See acast.com/privacy for more information.

Ben & Woods start the 8am hour by thanking our extremely loyal audience, and how the Tier 1 Mafia has already sold out our 2026 trip to Chicago that we've been promoting! Then we play today's game of "Take On Woods" before the guys get stood up by The Athletic's Eno Sarris, and we finally track Eno down and find out he was just "tired" and waking up in Orlando... Listen here!

The Craft Nick Pollack and recurring guest Eno Sarris break down Eno's mock draft in the 2026 PL Pods Mock Draft Review Series. Nick Pollack | Eno SarrisProducer | Adam HoweJoin The Discussion | PL+ and PL Pro Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

The CraftNick Pollack and recurring guest Eno Sarris break down Eno's mock draft in the 2026 PL Pods Mock Draft Review Series.  Join Our Discord & Support The Show: PL+ | PL Pro - Get 15% off Yearly with code PODCASTProud member of the Pitcher List Fantasy Baseball Podcast Network Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

In the early 1970s, legendary collaborator and self-proclaimed non-musician Brian Eno famously designed a deck of 115 cards containing elliptical imperatives to spark in the user creative connections unobtainable through regular modes of work. He called his creation "Oblique Strategies." For the past six decades, artists the world over in every artistic medium have used Eno's strategy while attempting to overcome a lull in creative output.In 2025, moody-melodramatic-mediocre yet somehow still award-winning* hobby podcasters and self-proclaimed Lightnin' Lickers Jay and Deon found themselves uninspired when contemplating the potential theme of their upcoming forty-fifth episode. Together, they decided... to default back to the alphabet. Because they have a reasonably solid grasp of the alphabet and how it works. They had previously utilized the letters A thru L, so naturally, they went with M.Sonic contributors to the forty-fifth episode of Lightnin' Licks Radio podcast include:  Brothers Johnson, M. M. Knapps, James Todd Smith, Tone Loc. Prince Paul, Camp Lo, Dynasty, Mary Jane Girls. Dire Straits, Uncle Tupelo, various Sesame Street characters, Crash Test Dummies. Emma Ruth Rundle, Marraiges, Drab Majesty, Ted Lucus. The bible, Mudhoney, Pearl Jam, Sir Mix-a-Lot. The Rolling Stones, Mantronix, Afrika Bambaataa, Beck, De La Soul. Big Daddy Kane, Crooklyn Dodgers, Q-Tip, Masta Ace. M.F. Doom, Metal Fingers. Ducks Deluxe, Tyla Gang, The Motors, Brinsley Schwartz, Leif Garrett, Homer Simpson. The Impressions, MC 900-ft Jesus, Curtis Mayfield, Martha and the Muffins, Romeo Void, M & M. DanielLineau, Maps & Atlases, Bandeau, La Rosa Noir, Dave Matthes Band. The Music Machine, Alice Cooper, The Association, Rick Springfield, Joe Walsh, Fleetwood Mac, Stevie Nicks & Lindsay Buckingham. Joe “Beans” Espisito, Harold Faltermeyer and Steve Stevens, The Main Ingredient, The Temptations, Seals & Croft, Stevie Wonder, Leon Ware. Alicia Keys, 21 Savage, J. Cole, and the Clockers.Please defend the rights of (y)our neighbors. Drink Blue Chair Bay responsibly. Stay warm and keep it in your pants.The Letter “M” mixtape: HEAR IT ON SOUNDCLOUD[side one] 1 mudhoney - night of the hunted 2 marth & the muffins - paint by number heart 3 the main ingredient - let me prove my love to you 4 the music machine - talk talk 5 masta ace  -nineteen ninety seventy something [side two] 1 the motors - forget about you 2 curtis mayfield - billy jack 3 marriages - skin 4 maps and atlases - vampires 5 mantronix - who is it [end]

The raw ingredients of this week's news gently diced, simmered and served as a nutritious broth. And flavoured with the following … … why Lily Allen's divorce album doubled the value of her house … how can you play real living people as fundamentally bad after Steve Coogan's ‘Lost King' court case? … the cowbell on Honky Tonk Women, the guiro on Gimme Shelter, the tambourine on classic Motown: Richard Pite gives a percussion demo … Kraftwerk, 10cc, Coolio, George McCrae – more records that sound unique … music used in movies to say ‘we're flying East!' … You Have Selected Regicide, Kill Wealthy Dowager: Morrissey song or line from the Simpsons? … Woodbines, potted herrings, Paris buns: things we expect to find in Van Morrison's soon-to-open childhood home ... why it's worth hearing Mishima by Philip Glass and John the Revelator by Son House … the time Jack Ashford was flown across America just to add a tambourine … people who found they had a famous father … and Mick ‘Two Pairs of Maracas' Jagger and what Eno predicted about I Feel Love.Help us to keep The Longest Conversation In Rock going: https://www.patreon.com/wordinyourear Hosted on Acast. See acast.com/privacy for more information.

Bruce Springsteen has released a four-disc set around his 1982 acoustic album Nebraska, including electric versions of many of the songs. "You could multi-track right in the bathroom." Help support The Next Track by making regular donations via Patreon (https://www.patreon.com/thenexttrack). We're ad-free and self-sustaining so your support is what keeps us going. Thanks! ‌Show notes Nebraska '82: Expanded Edition (https://amzn.to/48I3cKO) Bruce Springsteen: Nebraska '82: Expanded Edition review – fabled album falls short of expectations (https://www.theguardian.com/music/2025/oct/13/bruce-springsteen-nebraska-82-expanded-edition-review-fabled-album-falls-short-of-expectations) Ian Penman: Infinite Wibble: Brian v. Eno (https://www.lrb.co.uk/the-paper/v47/n17/ian-penman/infinite-wibble) Betty Cantor-Jackson - Wikipedia (https://en.wikipedia.org/wiki/Betty_Cantor-Jackson) Springsteen on Broadway (https://www.netflix.com/gb/title/80232329) Our next tracks: Brian Eno and Beatie Wolfe: Liminal (https://amzn.to/479tjYC) The Ratchets: Glory Bound (https://amzn.to/3L2Ploq) If you like the show, please subscribe in Apple Podcasts (https://itunes.apple.com/podcast/the-next-track/id1116242606) or your favorite podcast app, and please rate the podcast.

Paul Riedl and Morris Kolontyrsky of Blood Incantation discuss the incredible 1st year of the album "Absolute Elsewhere", how it's transformed their lives and art, the creation of the record, the band's deep interest in vinyl collecting and lots more. Enter to win a signed vinyl copy of "Absolute Elsewhere" by becoming a sponsor at Patreon.com/VinylGuide Topics Include: Absolute Elsewhere transformed their lives: bigger venues, mainstream press, entirely new audiences. Album allows new stage production; band already writing faster than ever before. Now headlining shows in US; Europe tours were always headliners, just smaller. Forbes called it one of most important death metal records in history. Record serves as gateway, exposing listeners to extreme metal and progressive influences. Vinyl LP format is their artistic endpoint; last two albums are side-long tracks. Twenty-minute sides provide perfect breathing room for their narrative-driven compositions and riffs. Maxed out Pro Tools voices at Hansa Studios during Absolute Elsewhere recording sessions. First three records recorded live on analog tape; complete takes, minimal punch-ins. Absolute Elsewhere used hybrid approach: drums on tape, then built digitally with Arthur. Recording live on tape creates collective synergy and tension they want captured. Band uses Oblique Strategies cards; asks "what would Trey, Chuck, or Eno do?" Paul designs all layouts; collects test pressings and creates prototype covers himself. Searching for roughly 200 more records; has specific rare pressings in mind. Weakling's Dead as Dreams LP extremely rare; basement flood destroyed most copies. Double album versus double LP distinction: complementary discs versus interrupted single work. Songs start with riffs that suggest where to go; excitable band keeps moving. Timewave Zero was critical palate cleanser enabling more holistic collaborative approach forward. Tangerine Dream collaboration manifested unexpectedly; Thorsten used vintage Edgar Froese Mellotron samples. Future dreams include Brian Eno, Steve Roach; already have secret collaborations lined up. High resolution version of this podcast is available at: www.Patreon.com/VinylGuide Apple: https://tinyurl.com/tvg-ios Spotify: https://tinyurl.com/tvg-spot Amazon Music: https://tinyurl.com/tvg-amazon Support the show at Patreon.com/VinylGuide

Brian Eno's music opens up worlds I love to step into during trying times. And this conversation with Eno did the same thing.Eno is a trailblazing musician and producer who's worked on seminal records by U2, David Bowie, the Talking Heads and Coldplay, among others. But Eno isn't just a great collaborator with other artists; he's also a great collaborator with machines. He's been experimenting with music technology for decades. Long before we started worrying about ChatGPT replacing human creativity, Eno was tinkering with generative systems to pioneer ambient music – a genre that has deeply influenced how we listen to music today. Eno's use (and playful misuse) of technology has expanded the possibilities of what music and sound can be.Many of you emailed in asking for a break from the news. Here it is.This episode contains strong language.Mentioned:What Art Does by Brian Eno and Bette AdriaanseEast West Street by Philippe SandsSilence by John CageBook Recommendations:Printing and the Mind of Man edited by John Carter and Percy H. MuirA Pattern Language by Christopher AlexanderNaples '44 by Norman LewisMusic Recommendations:The Rural Blues“The Velvet Underground” by the Velvet UndergroundThe ConsolersThoughts? Guest suggestions? Email us at ezrakleinshow@nytimes.com.You can find transcripts (posted midday) and more episodes of “The Ezra Klein Show” at nytimes.com/ezra-klein-podcast, and you can find Ezra on Twitter @ezraklein. Book recommendations from all our guests are listed at https://www.nytimes.com/article/ezra-klein-show-book-recs.This episode of “The Ezra Klein Show” was produced by Annie Galvin. Fact-checking by Mary Marge Locker, Kate Sinclair and Michelle Harris. Our senior engineer is Jeff Geld, with additional mixing by Aman Sahota. Our executive producer is Claire Gordon. The show's production team also includes Marie Cascione, Rollin Hu, Kristin Lin, Jack McCordick, Marina King and Jan Kobal. Original music by Aman Sahota and Pat McCusker. Audience strategy by Kristina Samulewski and Shannon Busta. Transcript editing by Sarah Murphy. The director of New York Times Opinion Audio is Annie-Rose Strasser. And special thanks to Geeta Dayal, Jack Hamilton, Victor Szabo and Sophie Abramowitz. Subscribe today at nytimes.com/podcasts or on Apple Podcasts and Spotify. You can also subscribe via your favorite podcast app here https://www.nytimes.com/activate-access/audio?source=podcatcher. For more podcasts and narrated articles, download The New York Times app at nytimes.com/app.

Order The Memory Palace book now, dear listener. On Bookshop.org, on Amazon.com, on Barnes & Noble, or directly from Random House. Or order the audiobook at places like Libro.fm.The Memory Palace is a proud member of Radiotopia from PRX. Radiotopia is a collective of independently owned and operated podcasts that's a part of PRX, a not-for-profit public media company. If you'd like to directly support this show, you can make a donation at Radiotopia.fm/donate. Music On-ness by Tom Rogerson and Eno. Etude by Joep Beving Ebb Tide by Houston & Dorsey Learn about your ad choices: dovetail.prx.org/ad-choices