Podcasts about Sota

There is consensus among SOTA listeners that we don't care for Presidential pardons. But we usually understand why certain people get pardons. Not so with Trump this week.

In Facebook, it's easy to see where your audience lives. It's harder to explain why the second and third biggest audiences for our show are not even in the US

Why did Trump pardon the Chrissleys? Why are we even still doing pardons? Where are the damn Epstein files already?! What's it really like driving a Cybertruck? Trump and Musk are having a very public breakup (finally); Shout out to the SOTA listeners in West Africa; Fox News floats "punishing" media that didn't cover Biden the right way

SOTA listener Arthur sees a double standard on the media's handling of the Qatari luxury jet story - but turns out he doesn't have all the facts

Where do they keep all the money at in banks, anyway? Financial expert Scoot brings the thunder in chat with bank president; SOTA listeners calling for heads to roll at OPSO after big jailbreak; You should be raw-dogging, not bare beating. You read that right; Once a hippie, always a hippie - Happy Birthday Susan!

Hello and welcome to episode 69 of The DX Mentor – A discussion with Jim, WB2REM. Thank you for joining us. I'm Bill, AJ8B.If this is the first time you are joining us, Welcome! We have a back catalog covering many aspects of DX. Please check us out. If you like what you find, please subscribe to always be notified of a new podcast!    Another way to keep in touch and to see what we are up to is via the DX Mentor Facebook page. I will be posting aboutupcoming podcasts as well as other DX events so please follow us.  Our guest today is Jim, WB2REM. Jim is an experienced, passionate operator and the conversation should be lively and informative.Here is the Mission Statement for this DXPedition: "In the spirit of the 7163/7156 MHZ DXGroup, this DXpedition was formed to provide the Amateur Radio Community with the opportunity of working the Faroe Islands on 6-160 Meters. We plan to be active on SSB, CW and FT8. We also hope to get to know the Amateur community in the Faroe Islands and when possible, explore the natural wonders of the islands, when not operating. Some members also plan to work SOTA and possiblyPOTA from the Faroe Islands." Jim and the team will be QRV from the Faroe Islands, June 1st to the 10th.Jim exhibited excellent patience when we were trying to schedule this podcast as we had to cancel twice. Unfortunately, the date that we finally agreed upon was adate that Joe had a personal conflict and could not be with us. Boy, did I miss him!Resources mentioned include:DXPedition Website - https://faroeis.com/7163 Net - https://7163net.com/Marlin Brandohttps://greylineperformance.com/blogs/news/famous-ham-radio-prepper-marlon-brando-fo5gj-tropical-south-pacific?srsltid=AfmBOop-SjYxYwMEvIhtp7VhxvI_Gzo0YQdI6M7d-JnJC4ZfMgShBZC3New World of Amateur Radio Videohttps://www.youtube.com/watch?v=LJDz2UlcY58Psychology of a QRMer - Page 13https://www.swodxa.org/wp-content/uploads/2018/04/Issue4_03012018A.pdfDX Cop - Page 11https://www.swodxa.org/wp-content/uploads/2018/05/Issue5_050118.pdfSouthwest Ohio DX Assoc. https://www.swodxa.orgDaily DX https://www.dailydx.com/DX Engineering https://www.dxengineering.com/Icom https://www.icomamerica.com/IC-905 https://www.icomamerica.com/lineup/products/IC-905/IC-9700 https://www.icomamerica.com/lineup/products/IC-9700/IC-7610 https://www.icomamerica.com/lineup/products/IC-7610/IC-7300 https://www.icomamerica.com/lineup/products/IC-7300/

Sota el títol 'Joan Domènech, el mestre que transmet cultura', l'acte es farà aquest dijous (19 hores).

This week on the Toy Power Podcast; we shine light on quite an old property; that is The Shadow! From its origins in Pulp Comic Format to the Hollywood Film in 1994 staring Alec Baldwin. That Film was classified big enough to spawn a corresponding Toyline from Kenner. Trent unpacks what was great, and what was left in the dark, around this neat property. Then we switch gears, and have a FULL-ON Spoiler lead discussion around the new Marvel Film that is: Thunderbolts - or New Avengers?!? We run though how each character played their part; the tone of the film & what we all overall thought of it too. Keen to hear from your thoughts on this Film too!Support the show: http://patreon.com/toypowerpodcastSee omnystudio.com/listener for privacy information.

A Sardanes sota el sol passarem una bona estona escoltant sardanes i si algú ho desitja, ballant-les! Juntes redescobrirem la dansa més bella de totes les danses que es fan i es desfan. Selecció de les cançons i presentació a càrrec de Francesca Isern i Pepita Brugada. podcast recorded with enacast.com

A Sardanes sota el sol passarem una bona estona escoltant sardanes i si algú ho desitja, ballant-les! Juntes redescobrirem la dansa més bella de totes les danses que es fan i es desfan. Selecció de les cançons i presentació a càrrec de Francesca Isern i Pepita Brugada. podcast recorded with enacast.com

Despr

Después de una semana intensa marcada por el gran apagón del 28 de abril, volvemos a la carga con el episodio 113, donde retomamos los contenidos que teníamos preparados… ¡y añadimos muchos más! SOTA to SOTA desde Portugal Abrimos con un QSO muy especial entre Juan Mondejar (EA9ADD) y Julio Iroa (EA1FTW), que coincidieron activando desde dos cimas distintas en Portugal. ¡SOTA to SOTA de lujo! Entrevista con Mariano Álvarez (Argentina) Charlamos con Mariano, miembro de la comunidad de mecenas del podcast, que se encuentra en pleno proceso de sacar su licencia de radioaficionado en Argentina. Nos cuenta cómo funciona allí todo el proceso, desde el estudio hasta el indicativo. ¡Muy interesante y con un puntito de envidia sana! Diploma Faros Comunidad Valenciana Te presentamos esta nueva iniciativa organizada por URE Burriana y URE Torrent: 21 faros, un diploma, trofeos para los más activos… y toda la información práctica para participar. Una actividad ideal para este verano. Actividad QRP desde Canarias Escuchamos algunos fragmentos de la última actividad QRP mensual del grupo Conecta Radio, liderado por EA8CAZ, conectando Canarias con la península con apenas 5 vatios. ¡Un logro técnico y humano! Informe AER – Mayo 2025 Cerramos el episodio con el resumen mensual de la Asociación Española de Radioescucha, con las estaciones de onda corta que podremos sintonizar este mes. Ideal para los amantes de la escucha internacional. Además, en la introducción reflexiono sobre el apagón, el QRM —o la ausencia de él— y cómo estoy preparando mi estación para futuras situaciones: baterías, inversores, modos digitales y más. ¡Mucho por explorar en los próximos episodios! Apoya el podcast y únete a nuestra comunidad privada: Si te gusta este podcast y quieres apoyarlo, puedes convertirte en mecenas desde solo 1,99 € al mes en https://cqenfrecuencia.com/apoyar. Al hacerlo, también formarás parte de nuestra comunidad privada de Telegram. NOTAS DEL EPISODIO - Web “Diploma Faros de Valencia” https://hfradio.es - Web de ENACOM (Argentina) https://www.enacom.gob.ar/ Envía tus preguntas, propuestas de temas o lo que quieras: https://cqenfrecuencia.com/contacto/ O en nuestro canal de Telegram: https://t.me/cqenfrecuencia Y no olvidéis de visitar nuestra web: https://cqenfrecuencia.com No olvides el like, subscribirte y/o darle a la campanita para no perderte ningún episodio de nuestro podcast! Nos encontrarás también en Spotify y Youtube.

Yhdysvalloissa Trumpin hallinto on ryhtynyt leikkaamaan yliopistojen rahoitusta. Leikkauksia ja rahoitusjäädytyksiä on perusteltu juutalaisvastaisuuden kitkemisellä. Arvostelijoiden mukaan se on kuitenkin vain tekosyy yliopistojen rankaisemiseen, sillä perimmäinen motiivi olisi yrittää saada yliopisto-opetus hallinnon ideologiaa tukevaksi. Ohjelmassa haastatellaan lukuisia yhdysvaltalaisprofessoreita, miten Trumpin hallinnon leikkaukset heidän yliopistoissaan näkyvät. Lisäksi kaksi Suomessa toimivaa professoria arvioi, kuinka Yhdysvaltain yliopistojen kuristamisella on myös rajat ylittäviä vaikutuksia. Maailmanpolitiikan arkipäivää -ohjelmassa pohditaan, mitä yliopistojen leikkaukset ovat Yhdysvalloille tekemässä. Ohjelman ovat toimittaneet Juri von Bonsdorff ja Paula Vilén. Äänitarkkailijana on Panu Willman.

A Sardanes sota el sol passarem una bona estona escoltant sardanes i si algú ho desitja, ballant-les! Juntes redescobrirem la dansa més bella de totes les danses que es fan i es desfan. Selecció de les cançons i presentació a càrrec de Francesca Isern i Pepita Brugada. podcast recorded with enacast.com

La ciutat de Balaguer mostrarà aquest diumenge la seva solidaritat en la IX Fira dels Somnis contra el càncer infantil. La diada començarà amb la cursa caminada solidària, més gran de les Terres de Lleida, amb una inscripció que espera superar les 3.000 samarretes venudes La Comunitat Energètica de Vallfogona i el Veïnat del Centre Històric de Balaguer signen un acord per compartir energia renovable CCOO i UGT reclamen la reducció de la jornada laboral en una manifestació a Lleida en el marc del Dia del Treballador. Sota el lema ‘Protegir les conquestes i guanyar el futur’ la mobilització ha recorregut l’eix comercial de la ciutat Una plaga de peixos gat col•lapsa la xarxa de reg en una finca de Vallfogona de Balaguer El Tribunal Suprem ha condemnat a 4 anys de presó un monitor per abusar sexualment d’una nena de 13 anys durant unes colònies a Ager el juliol del 2019 Agenda Balaguer La Casa d’Andalusia de Balaguer celebra aquest dissabte la novena edició de la Feria de Abril Aquest dissabte se celebra Casal cívic i comunitari Balaguer-Eixample, el Mes del Comerç Just Arriba la Fira de Titelles de Lleida a Balaguer amb dues companyies internacionals que es presentaran dos espectacles en una mateix funció a el proper diumenge a la sala La Mercantil Agenda comarca Penelles ha donat aquest dijous el tret de sortida de la 10a edició del Gargar amb el bateig d’un nou capgròs com a emblema del festival. La programació preveu tallers artístics, espectacles musicals, activitats culturals i l’elaboració de murals en viu Vallfogona de Balaguer escalfa fogons per a la tercera edició de la Fira Lo Caragol food, aquest proper cap de setmana, amb el xef Sergi de Meià com a gran novetat del concurs gastronòmic L’Hostal Nou inaugura aquest dissabte un mural dedicat als 80, “EL MURAL DELS NENS DELS 80” La plaça de l’Ajuntament d’Artesa de Segre es transformarà aquest dissabte en l’escenari de la 3a edició del Primavera Wine, un esdeveniment ja consolidat que aposta per apropar el vi català i la gastronomia de proximitat a tots els públics, especialment al jovent Esports El primer equip del Club Futbol Balaguer juga aquest dissabte a Terrassa. El juvenil ho fa al municipal contra el Sant Cugat B Última jornada de lliga per al Teixidó Associats, del Club Bàsquet Balaguer, que s’ho juga tot contra l’Sferic Terrassa i quedant pendent del que passi diumenge a Tremp per evitar el descens El Comtat d’Urgell de futbol sala juga diumenge a les 6 de la tarda al 1r d’Octubre de Balaguer contra el Sant Joan Despí. A Primera Catalana el Balaguer Vedruna va guanyar dimarts 8 a 2 a l’Agramunt i el Contat B juga a Castellfollit. El Contat Femení rep al Golmés El dissabte dia 3 de maig tindrà lloc a partir de les 10h del matí a la Piscina coberta la 13a edició del Trofeu de natació Albert Barri, un trofeu nacional català de natació amb diferents categories i distàncies Èxit de participació a la Trail Lo Meló d’Artesa de Segre, prova puntuable per a la Lliga de la Noguera. Abel Carretero i Cristina Gardeñes es van adjudicar la categoria reina de 16km i Óscar Celma i Mireia Capdevila la 10 kmDescarregar àudio (51:57 min / 24 MB)

This week on the Toy Power Podcast; we welcome back Nick Greenslade; to assist us to break-down all things Star Wars related. Kicking things off, with his opinion of who he would have chosen as the candidates for the SW Villains side of things on: The Team.... Then without missing a beat; we take the next challenge of carefully selecting another round of The Team for the Star Wars Heroes campaign - keeping them tightly contained to the Original Kenner releases as our choices. Leader, Muscle, Specialist, Wheelman & an Iconic Vehicle. Then continuing the Star Wars themed banter, we discuss more of the visual announcements coming from SW Celebration & what the future of Star Wars might be... A fun healthy round table chat with fantastic knowledge & true passion from Nick! This Is The Way!Support the show: http://patreon.com/toypowerpodcastSee omnystudio.com/listener for privacy information.

A Sardanes sota el sol passarem una bona estona escoltant sardanes i si algú ho desitja, ballant-les! Juntes redescobrirem la dansa més bella de totes les danses que es fan i es desfan. Selecció de les cançons i presentació a càrrec de Francesca Isern i Pepita Brugada. podcast recorded with enacast.com

Mitä seurauksia sodalla on jälkipolville? Moni meistä on kuullut isovanhempien kertomuksia sodasta ja lukenut tai katsonut Tuntemattoman sotilaan. Sota on osa yhteistä kansallista muistiamme. Mutta voivatko sodan kauhut siirtyä kuultujen kertomusten lisäksi jälkipolville myös perimässä? Nyt asiaa tutkitaan historian- ja epigenetiikan tutkijoiden toimesta. Historioitsijat ovat laatineet sotilaiden kantakorteista kattavan tietokannan, ja nyt se yhdistetään ensimmäistä kertaa maailmassa laajoihin terveystietoaineistoihin. Asiantuntijoina ovat historiantutkija Ville Kivimäki Suomalaisen Kirjallisuuden seurasta, tutkijatohtori Ilari Taskinen kokemuksen historian huippuyksiköstä Tampereen yliopistosta ja akatamiatutkija Emma Raitoharju Tampereen yliopistosta. Toimittajana on Pirjo Koskinen.

How many followers on Scoot's Facebook page are in a race to see who can post the dumbest, meanest, most pointless comment?

Balaguer celebrarà aquest cap de setmana una nova edició de Fira Q, un certamen que, un any més, comptarà amb els principals sectors econòmics de la ciutat i del territori. Enguany, i tenint en compte que Catalunya ostenta aquest 2025 la distinció de Regió Mundial de la Gastronomia, la fira posarà en valor la gran riquesa gastronòmica del territori i, en especial, de Balaguer i comarca En aquest sentit, el IX Concurs de cuina Josep Mª Morell ‘De la nostra terra al plat’, enguany el plat no serà lliure sinó que es demanarà una recepta sobre la cassola de tros, molt representativa de la comarca de la Noguera La Fira l’inaugurarà el conseller d’Empresa, Miquel Sàmper, i diumenge hi participarà també el conseller d’Agricultura, Òscar Ordeig, que assistirà a la Jornada de la Mel El Consell Comarcal de la Noguera participa a la Fira Q de Balaguer amb 3 estands de les àrees de Promoció Econòmica, Turisme i Oficina Jove El DJ Ruben Fuster serà el cap de cartell de la Fira J d’aquest any, que se celebrarà el dissabte al pavelló Molí de l’Esquerrà i que inclourà també el concurs per escollir els dos DJs que actuaran durant la Transsegre La firma Alemany tornarà a ser present a Fira Q de Balaguer amb una proposta centrada en la innovació, la proximitat i l’alimentació amb valor afegit. La marca d’Os de Balaguer hi presentarà l’evolució de la seva gamma de cremes untables i les begudes infusionades Mà de Sant El ple de la Paeria de Balaguer dona llum verda a l’aprovació dels projectes de reforma del local per a la nova oficina d’atenció al ciutadà i el projecte d’obres per a l’adequació de la futura Caserna de la Guàrdia Urbana. Els dos projectes sumen 723 mil euros d’inversió per als qual es demanarà una subvenció del PUOSC Els sindicats de CCOO i UGT fan una crida a la mobilització a Lleida en el marc l’1 de maig per defensar els drets adquirits, exigir un repartiment “més just” dels beneficis empresarials entre els treballadors i reclamar la reducció de la jornada laboral. Sota el lema ‘Protegir les conquestes i guanyar futur’, la manifestació donarà el tret de sortida a la plaça del Treball a les 12h i finalitzarà a la plaça Paeria de Lleida Asaja reitera la preocupació per les conseqüències de la pedregada a Lleida en una reunió amb Ordeig. El sindicat agrari presenta un document amb catorze punts de reivindicacions de tots els sectors productius Els Canals d’Urgell presenten al•legacions a la proposta de la CHE de reduir un 15’5% la dotació de la infraestructura. Els regants rebutgen la proposta perquè consideren que “no reflecteix les necessitats hídriques del territori” Arrenca una nova temporada de turisme actiu a Lleida amb l’objectiu de consolidar les més de 800.000 activitats anuals, d’un sector que l’any passat va generar un impacte econòmic de gairebé 113 milions El singular tren turístic, el Tren dels Llacs, que connecta la plana de Lleida amb el Prepirineu lleidatà a través d’un atractiu recorregut que travessa gorges, muntanyes i embassaments, iniciarà la temporada aquest dissabte i farà un total de 27 viatges fins al 25 d’octubre Agenda Balaguer La música jazz obre el Pati de la Mercantil aquest divendres amb el pianista nord-americà Jeb Patton, un dels músics més brillants i destacats de l’escena internacional L’Associació Cultural Grup D’Art4 organitza un any més el Concurs de Pintura ràpida. Serà aquest dissabte pels carrers i places de Balaguer El Teatre Municipal de Balaguer acollirà aquest dissabte l’11a edició del Free Style Dance Balaguer, una competició de funky i hip-hop que reunirà al voltant de 600 ballarins d’arreu de les comarques de Ponent i Andorra Agenda Comarca Continuen els actes de la Festa Major a Camarasa, amb el sopar i festes populars, els concerts de dissabte nit i la cercavila i ball orquestral del diumenge Menàrguens celebra aquest cap de setmana els actes de Sant Pere Martir, inclosos dins de la Primavera Cultural, i amb la festa de les cassoles com a màxim exponent Os de Balaguer celebrarà aquest diumenge la Trobada de Campaners, amb la tradicional demostració de tocs de campana, el Toc especial i les activitats paral•leles com la fira d’artesania El Castell del Remei celebrarà diumenge l’Aplec de Primavera. El Cant del Virolai, la conversa literària, l’aperitiu amb música en viu, la degustació de vins, i l’espectacle i taller infantils, seran algunes de les propostes ESPORTS El Club Futbol Balaguer rep diumenge al municipal al Juneda, un equip que es juga la permanència. El Juvenil viatja dissabte a Igualada per competir amb un rival assequible El Q2 Consultors del Club Bàsquet Balaguer rep aquest dissabte al 1r d’Octubre al Barça CBS. El Teixidó Associats jugarà diumenge a la pista del Pia Sabadell El Comtat d’Urgell de futbol sala juga diumenge a Salou. A Primera Catalana el Comtat B rep al Fonollosa i el Balaguer Vedruna juga a La Seu. El Comtat femení juga dissabte a ReusDescarregar àudio (56:21 min / 26 MB)

Hey everyone, Alex here

While there are some cool cool news items to talk too, there's also a certain Celebration taking place in Japan right now... As such we bring on a Star Wars expert Nick G who takes us through all latest Black Series and TVC goodness. Closer to home, we recap our local (and the best) Adelaide Comic and Toy Fair with it's April 2025 edition. Huge thanks as always to Brett and Sarah for their amazing work! Support the show: http://patreon.com/toypowerpodcastSee omnystudio.com/listener for privacy information.

KONU BAŞLIKLARI:1. OpenAI, yeni modelleri o3 ve o4-mini'yi duyurdu. Bu modeller, web araması, Python ile veri analizi, görsel okuma ve gerektiğinde görsel içerik oluşturma gibi gelişmiş yeteneklere sahip. Artık yüklenen görselleri sadece açıklamakla kalmıyor, sorulan sorularla birlikte yorumlayabiliyor.

This week on the Toy Power Podcast; we are once again missing Master Frank; but have Special Guest: Chris Canini back in the studio with the usual "Get To Know You Questions". A great insight into what Chris's passions are! Then, without missing a beat,he as brought in a fantastic assortment of Figures, to promote just how awesome the new Jada Street Fighter Toys are!! From M. Bison to Dhalsim (and many more), we annalise just what this Toyline is doing, what it may do in the future & how it compares to older versions of the same figures. Then we move over to latest scores; including more amazing gems from Jada; (courtesy of Chris again); this time in the form of Mega-Man! Another in hand assortment of toys for us all to review on the show. We continue to promote around the room, who has recently scored what, & believe me, there are some exciting items we cover!! For more on Chris Canini, be sure to check out his Instagram pages: @DarkLightCollector @DarkLightTurtleLairSupport the show: http://patreon.com/toypowerpodcastSee omnystudio.com/listener for privacy information.

WHY SOTA? At sota we work every day to give you the best. drink. ever. every. time. Why? Because you deserve it. Whether it's time to celebrate (end of soccer season, big moment at work, hanging with friends), or time... The post Minne”SOTA” – Where The Streets Have No Name – Chad Taylor – 914 appeared first on The Cultural Hall Podcast.

Un grup d'investigadors del departament d'Enginyeria Civil i Ambiental de la Universitat Politècnica de Catalunya han publicat un article a la prestigiosa revista científica Science of the Total Environment amb les primeres conclusions dels estudis que han portat a terme a la platja de l'Aiguadolç. L'equip científic ha utilitzat dues tècniques diferents per avaluar la quantitat tant de l'aigua de la surgència superficial, com de la de les nombroses fons submarines de la mateixa platja, on arriba després d'un recorregut sota el massís càrstic del Garraf. L'aportació de nutrients al litoral d'aquest tipus de surgències és fonamental per a la biodiversitat de la costa mediterrània, i Aiguadolç és un entorn molt destacat per poder-lo estudiar, motiu pel quan esta previstes noves campanyes d'investigació. N'hem pogut parlar amb un dels responsables de l'estudi, Marc Diego-Feliu. L'entrada L’aigua dolça d’Aiguadolç té nombroses fonts sota el mar ha aparegut primer a Radio Maricel.

Somewhere between 1,500 and 2,700 folks showed up to Lafayette Square Saturday to participate in nationwide protests against DOGE, Elon Musk and President Trump - including some SOTA listeners

This week on the Toy Power Podcast; we are missing Frank in the studio; but have Special Guest: Chris Canini join us to help us breakdown a mountain of News & Announcements; mainly from the WonderCon Event! With a little bit of house-keeping aside, its impossible for us to ignore the recent Tariffs that is going to affect our Collecting passions. Mondo are up first with a beautiful array of Soft Vinyl items; 1/6th & 1/12th figures that has us drooling! McFarlane seem to have laid all their cards on the table; in an absolutely enormous slide-show of up-coming releases, in many different formats & sub-categories! Jada continuing to impress, not only with their awesome Street Fighter line; but their Mega-Man offers too! A heap of Marvel Legends that span across Movies, TV shows & Comicbooks too! Then rounding out, we shout out our wish-list of items we will be hunting for, at the upcoming Adelaide Comic & Toy Fair on the following weekend!! For more on Chris Canini, be sure to check out his Instagram pages: @DarkLightCollector @DarkLightTurtleLairSupport the show: http://patreon.com/toypowerpodcastSee omnystudio.com/listener for privacy information.

Poet of the Week, March 31–April 6, 2025. Full text of the poem & interview: brooklynpoets.org/community/poet/monica-sok

This week on the Toy Power Podcast, we take a look at a Galaxy Far, Far Away; and select the most wretched hive of scum & villainy - in order for another installment of The Team! Yes, this round is focused on the Villains from the Original Kenner Star Wars Toyline Universe. Leader, Muscle, Specialist, Wheelman and an Iconic Vehicle; are all needed to be voted on, and then locked in! Then we turn the tide, one quarter way through the year already!..... We take a look at what Movies are slated to be released at the Box Office this year! What has us excited, what are we staying clear of, and how good does the Toxic Crusaders Trailer look!! All this and more; enjoy!!Support the show: http://patreon.com/toypowerpodcastSee omnystudio.com/listener for privacy information.

Yes, there is news to talk too - some of it huge. Like a certain huge dragon. Huge fundraisers. Huge SDCC ecto-glow announcement. Two huge properties join forces (gotta build 'em all). One huge Shredder (bro lifts). But bigger than ALL of those, is the unexpected parcel of absolute joy sent by our favourite Canadian, the one and only Colin Betts. This has to be seen (heard?) to be believed. In spite of some truely awful postage costs, comes so many gifts filled with attention to detail, insight, humor and most importantly, love. Colin - a huge thank you!Support the show: http://patreon.com/toypowerpodcastSee omnystudio.com/listener for privacy information.

La thérapie en France, comment ça marche ? Qui y va ? Combien ça coûte ? Comment bien choisir son spécialiste de santé mentale ? Que peut-on attendre d'un suivi psychologique ? Interactive Transcript and Vocab Helper Get interactive transcripts, live vocabulary and bonus content for all our episodes! 7-Day FREE trial at: easyfrench.fm/membership Show Notes Deux moi, film de Cédric Klapisch (https://www.allocine.fr/film/fichefilm_gen_cfilm=268136.html) Bonus Podcast Emotions (https://louiemedia.com/emotions) Podcast Dose de psy (https://dosedepsy.captivate.fm/) Podcast Se sentir bien (https://www.radio.fr/podcast/sesentirbien) Transcript Intro Hélène: [0:16] Bonjour à tous, bonjour Judith. Judith: [0:19] Bonjour Hélène. Hélène: [0:21] Comment ça va ? Judith: [0:22] Ça va, je sais qu'on fait très souvent un petit récap météo. Hélène: [0:26] Oui, c'est la tradition. Judith: [0:29] Je vais encore en faire un. Ça y est, les beaux jours sont terminés, il fait de nouveau gris et froid à Paris. Hélène: [0:37] Exactement pareil, ici, aux Pays-Bas, on a eu une semaine de début de printemps, et c'est terminé l'hiver et, de nouveau là. C'était de courte durée. Judith: [0:49] Bon, on en a bien profité. Hélène: [0:50] C'est vrai. Alors, aujourd'hui, on va parler d'un sujet qui nous tient à cœur à toutes les deux et qui est un sujet de société aussi vraiment très présent en France. Avant cela, on va écouter un message d'un auditeur et tenter de répondre à sa question. Judith: [1:12] Ok. Sota: [1:12] Bonjour Hélène. Bonjour Judith, comment ça va ? Je m'appelle Sota, je suis japonais, j'habite à Osaka. Aujourd'hui, j'ai une bonne nouvelle pour vous. Je viens de m'inscrire à votre podcast Easy French. Vous savez pourquoi ? Parce que j'adore votre podcast. C'est toujours très intéressant, très amusant, très drôle. Voilà pourquoi. Et aujourd'hui, j'ai une question pour vous concernant la langue étrangère. L'autre fois, vous avez dit que vous êtes douées en langues étrangères. Moi aussi, personnellement, je parle plusieurs langues, comme le japonais, l'anglais et le français. Mais j'ai rencontré des difficultés de parler plusieurs langues étrangères en même temps. Il y a un mois, je suis allé aux États-Unis pour revoir mes amis. Et dès que je suis arrivé, quelqu'un m'a dit quelque chose en anglais et j'ai essayé de répondre en anglais. Mais j'ai toujours fini par répondre en français, tel que merci beaucoup, oui. Donc, comment est-ce que vous pouvez parler plusieurs langues étrangères sans faire le mélange ? C'est tout, à très bientôt. Get interactive transcripts, live vocabulary and bonus content for all our episodes! 7-Day FREE trial at: easyfrench.fm/membership

We are a couple of members down today so yes, it's a Lisa episode. Scot and Frank take the wheel to look at a new Origins reveal, some Latest Scores (where Scot goes BIG) but mainly wax on/off about the finale of Cobra Kai. Did they stick the landing or sweep the leg? How was Anthony Mackie's first solo run as Captain America? Hoe tough is it to integrate two cats into the same space? All these un-expected questions and more await! Support the show: http://patreon.com/toypowerpodcastSee omnystudio.com/listener for privacy information.

Racism, corruption, electoral bias ... in less than three minutes, SOTA iconic caller Rashard covers more topics than you can shake a stick at

While everyone is now repeating that 2025 is the “Year of the Agent”, OpenAI is heads down building towards it. In the first 2 months of the year they released Operator and Deep Research (arguably the most successful agent archetype so far), and today they are bringing a lot of those capabilities to the API:* Responses API* Web Search Tool* Computer Use Tool* File Search Tool* A new open source Agents SDK with integrated Observability ToolsWe cover all this and more in today's lightning pod on YouTube!More details here:Responses APIIn our Michelle Pokrass episode we talked about the Assistants API needing a redesign. Today OpenAI is launching the Responses API, “a more flexible foundation for developers building agentic applications”. It's a superset of the chat completion API, and the suggested starting point for developers working with OpenAI models. One of the big upgrades is the new set of built-in tools for the responses API: Web Search, Computer Use, and Files. Web Search ToolWe previously had Exa AI on the podcast to talk about web search for AI. OpenAI is also now joining the race; the Web Search API is actually a new “model” that exposes two 4o fine-tunes: gpt-4o-search-preview and gpt-4o-mini-search-preview. These are the same models that power ChatGPT Search, and are priced at $30/1000 queries and $25/1000 queries respectively. The killer feature is inline citations: you do not only get a link to a page, but also a deep link to exactly where your query was answered in the result page. Computer Use ToolThe model that powers Operator, called Computer-Using-Agent (CUA), is also now available in the API. The computer-use-preview model is SOTA on most benchmarks, achieving 38.1% success on OSWorld for full computer use tasks, 58.1% on WebArena, and 87% on WebVoyager for web-based interactions.As you will notice in the docs, `computer-use-preview` is both a model and a tool through which you can specify the environment. Usage is priced at $3/1M input tokens and $12/1M output tokens, and it's currently only available to users in tiers 3-5.File Search ToolFile Search was also available in the Assistants API, and it's now coming to Responses too. OpenAI is bringing search + RAG all under one umbrella, and we'll definitely see more people trying to find new ways to build all-in-one apps on OpenAI. Usage is priced at $2.50 per thousand queries and file storage at $0.10/GB/day, with the first GB free.Agent SDK: Swarms++!https://github.com/openai/openai-agents-pythonTo bring it all together, after the viral reception to Swarm, OpenAI is releasing an officially supported agents framework (which was previewed at our AI Engineer Summit) with 4 core pieces:* Agents: Easily configurable LLMs with clear instructions and built-in tools.* Handoffs: Intelligently transfer control between agents.* Guardrails: Configurable safety checks for input and output validation.* Tracing & Observability: Visualize agent execution traces to debug and optimize performance.Multi-agent workflows are here to stay!OpenAI is now explicitly designs for a set of common agentic patterns: Workflows, Handoffs, Agents-as-Tools, LLM-as-a-Judge, Parallelization, and Guardrails. OpenAI previewed this in part 2 of their talk at NYC:Further coverage of the launch from Kevin Weil, WSJ, and OpenAIDevs, AMA here.Show Notes* Assistants API* Swarm (OpenAI)* Fine-Tuning in AI* 2024 OpenAI DevDay Recap with Romain* Michelle Pokrass episode (API lead)Timestamps* 00:00 Intros* 02:31 Responses API * 08:34 Web Search API * 17:14 Files Search API * 18:46 Files API vs RAG * 20:06 Computer Use / Operator API * 22:30 Agents SDKAnd of course you can catch up with the full livestream here:TranscriptAlessio [00:00:03]: Hey, everyone. Welcome back to another Latent Space Lightning episode. This is Alessio, partner and CTO at Decibel, and I'm joined by Swyx, founder of Small AI.swyx [00:00:11]: Hi, and today we have a super special episode because we're talking with our old friend Roman. Hi, welcome.Romain [00:00:19]: Thank you. Thank you for having me.swyx [00:00:20]: And Nikunj, who is most famously, if anyone has ever tried to get any access to anything on the API, Nikunj is the guy. So I know your emails because I look forward to them.Nikunj [00:00:30]: Yeah, nice to meet all of you.swyx [00:00:32]: I think that we're basically convening today to talk about the new API. So perhaps you guys want to just kick off. What is OpenAI launching today?Nikunj [00:00:40]: Yeah, so I can kick it off. We're launching a bunch of new things today. We're going to do three new built-in tools. So we're launching the web search tool. This is basically chat GPD for search, but available in the API. We're launching an improved file search tool. So this is you bringing your data to OpenAI. You upload it. We, you know, take care of parsing it, chunking it. We're embedding it, making it searchable, give you this like ready vector store that you can use. So that's the file search tool. And then we're also launching our computer use tool. So this is the tool behind the operator product in chat GPD. So that's coming to developers today. And to support all of these tools, we're going to have a new API. So, you know, we launched chat completions, like I think March 2023 or so. It's been a while. So we're looking for an update over here to support all the new things that the models can do. And so we're launching this new API. It is, you know, it works with tools. We think it'll be like a great option for all the future agentic products that we build. And so that is also launching today. Actually, the last thing we're launching is the agents SDK. We launched this thing called Swarm last year where, you know, it was an experimental SDK for people to do multi-agent orchestration and stuff like that. It was supposed to be like educational experimental, but like people, people really loved it. They like ate it up. And so we are like, all right, let's, let's upgrade this thing. Let's give it a new name. And so we're calling it the agents SDK. It's going to have built-in tracing in the OpenAI dashboard. So lots of cool stuff going out. So, yeah.Romain [00:02:14]: That's a lot, but we said 2025 was the year of agents. So there you have it, like a lot of new tools to build these agents for developers.swyx [00:02:20]: Okay. I guess, I guess we'll just kind of go one by one and we'll leave the agents SDK towards the end. So responses API, I think the sort of primary concern that people have and something I think I've voiced to you guys when, when, when I was talking with you in the, in the planning process was, is chat completions going away? So I just wanted to let it, let you guys respond to the concerns that people might have.Romain [00:02:41]: Chat completion is definitely like here to stay, you know, it's a bare metal API we've had for quite some time. Lots of tools built around it. So we want to make sure that it's maintained and people can confidently keep on building on it. At the same time, it was kind of optimized for a different world, right? It was optimized for a pre-multi-modality world. We also optimized for kind of single turn. It takes two problems. It takes prompt in, it takes response out. And now with these agentic workflows, we, we noticed that like developers and companies want to build longer horizon tasks, you know, like things that require multiple returns to get the task accomplished. And computer use is one of those, for instance. And so that's why the responses API came to life to kind of support these new agentic workflows. But chat completion is definitely here to stay.swyx [00:03:27]: And assistance API, we've, uh, has a target sunset date of first half of 2020. So this is kind of like, in my mind, there was a kind of very poetic mirroring of the API with the models. This, I kind of view this as like kind of the merging of assistance API and chat completions, right. Into one unified responses. So it's kind of like how GPT and the old series models are also unifying.Romain [00:03:48]: Yeah, that's exactly the right, uh, that's the right framing, right? Like, I think we took the best of what we learned from the assistance API, especially like being able to access tools very, uh, very like conveniently, but at the same time, like simplifying the way you have to integrate, like, you no longer have to think about six different objects to kind of get access to these tools with the responses API. You just get one API request and suddenly you can weave in those tools, right?Nikunj [00:04:12]: Yeah, absolutely. And I think we're going to make it really easy and straightforward for assistance API users to migrate over to responsive. Right. To the API without any loss of functionality or data. So our plan is absolutely to add, you know, assistant like objects and thread light objects to that, that work really well with the responses API. We'll also add like the code interpreter tool, which is not launching today, but it'll come soon. And, uh, we'll add async mode to responses API, because that's another difference with, with, uh, assistance. I will have web hooks and stuff like that, but I think it's going to be like a pretty smooth transition. Uh, once we have all of that in place. And we'll be. Like a full year to migrate and, and help them through any issues they, they, they face. So overall, I feel like assistance users are really going to benefit from this longer term, uh, with this more flexible, primitive.Alessio [00:05:01]: How should people think about when to use each type of API? So I know that in the past, the assistance was maybe more stateful, kind of like long running, many tool use kind of like file based things. And the chat completions is more stateless, you know, kind of like traditional completion API. Is that still the mental model that people should have? Or like, should you buy the.Nikunj [00:05:20]: So the responses API is going to support everything that it's at launch, going to support everything that chat completion supports, and then over time, it's going to support everything that assistance supports. So it's going to be a pretty good fit for anyone starting out with open AI. Uh, they should be able to like go to responses responses, by the way, also has a stateless mode, so you can pass in store false and they'll make the whole API stateless, just like chat completions. You're really trying to like get this unification. A story in so that people don't have to juggle multiple endpoints. That being said, like chat completions, just like the most widely adopted API, it's it's so popular. So we're still going to like support it for years with like new models and features. But if you're a new user, you want to or if you want to like existing, you want to tap into some of these like built in tools or something, you should feel feel totally fine migrating to responses and you'll have more capabilities and performance than the tech completions.swyx [00:06:16]: I think the messaging that I agree that I think resonated the most. When I talked to you was that it is a strict superset, right? Like you should be able to do everything that you could do in chat completions and with assistants. And the thing that I just assumed that because you're you're now, you know, by default is stateful, you're actually storing the chat logs or the chat state. I thought you'd be charging me for it. So, you know, to me, it was very surprising that you figured out how to make it free.Nikunj [00:06:43]: Yeah, it's free. We store your state for 30 days. You can turn it off. But yeah, it's it's free. And the interesting thing on state is that it just like makes particularly for me, it makes like debugging things and building things so much simpler, where I can like create a responses object that's like pretty complicated and part of this more complex application that I've built, I can just go into my dashboard and see exactly what happened that mess up my prompt that is like not called one of these tools that misconfigure one of the tools like the visual observability of everything that you're doing is so, so helpful. So I'm excited, like about people trying that out and getting benefits from it, too.swyx [00:07:19]: Yeah, it's a it's really, I think, a really nice to have. But all I'll say is that my friend Corey Quinn says that anything that can be used as a database will be used as a database. So be prepared for some abuse.Romain [00:07:34]: All right. Yeah, that's a good one. Some of that I've tried with the metadata. That's some people are very, very creative at stuffing data into an object. Yeah.Nikunj [00:07:44]: And we do have metadata with responses. Exactly. Yeah.Alessio [00:07:48]: Let's get through it. All of these. So web search. I think the when I first said web search, I thought you were going to just expose a API that then return kind of like a nice list of thing. But the way it's name is like GPD for all search preview. So I'm guessing you have you're using basically the same model that is in the chat GPD search, which is fine tune for search. I'm guessing it's a different model than the base one. And it's impressive the jump in performance. So just to give an example, in simple QA, GPD for all is 38% accuracy for all search is 90%. But we always talk about. How tools are like models is not everything you need, like tools around it are just as important. So, yeah, maybe give people a quick review on like the work that went into making this special.Nikunj [00:08:29]: Should I take that?Alessio [00:08:29]: Yeah, go for it.Nikunj [00:08:30]: So firstly, we're launching web search in two ways. One in responses API, which is our API for tools. It's going to be available as a web search tool itself. So you'll be able to go tools, turn on web search and you're ready to go. We still wanted to give chat completions people access to real time information. So in that. Chat completions API, which does not support built in tools. We're launching the direct access to the fine tuned model that chat GPD for search uses, and we call it GPD for search preview. And how is this model built? Basically, we have our search research team has been working on this for a while. Their main goal is to, like, get information, like get a bunch of information from all of our data sources that we use to gather information for search and then pick the right things and then cite them. As accurately as possible. And that's what the search team has really focused on. They've done some pretty cool stuff. They use like synthetic data techniques. They've done like all series model distillation to, like, make these four or fine tunes really good. But yeah, the main thing is, like, can it remain factual? Can it answer questions based on what it retrieves and get cited accurately? And that's what this like fine tune model really excels at. And so, yeah, so we're excited that, like, it's going to be directly available in chat completions along with being available as a tool. Yeah.Alessio [00:09:49]: Just to clarify, if I'm using the responses API, this is a tool. But if I'm using chat completions, I have to switch model. I cannot use 01 and call search as a tool. Yeah, that's right. Exactly.Romain [00:09:58]: I think what's really compelling, at least for me and my own uses of it so far, is that when you use, like, web search as a tool, it combines nicely with every other tool and every other feature of the platform. So think about this for a second. For instance, imagine you have, like, a responses API call with the web search tool, but suddenly you turn on function calling. You also turn on, let's say, structure. So you can have, like, the ability to structure any data from the web in real time in the JSON schema that you need for your application. So it's quite powerful when you start combining those features and tools together. It's kind of like an API for the Internet almost, you know, like you get, like, access to the precise schema you need for your app. Yeah.Alessio [00:10:39]: And then just to wrap up on the infrastructure side of it, I read on the post that people, publisher can choose to appear in the web search. So are people by default in it? Like, how can we get Latent Space in the web search API?Nikunj [00:10:53]: Yeah. Yeah. I think we have some documentation around how websites, publishers can control, like, what shows up in a web search tool. And I think you should be able to, like, read that. I think we should be able to get Latent Space in for sure. Yeah.swyx [00:11:10]: You know, I think so. I compare this to a broader trend that I started covering last year of online LLMs. Actually, Perplexity, I think, was the first. It was the first to say, to offer an API that is connected to search, and then Gemini had the sort of search grounding API. And I think you guys, I actually didn't, I missed this in the original reading of the docs, but you even give like citations with like the exact sub paragraph that is matching, which I think is the standard nowadays. I think my question is, how do we take what a knowledge cutoff is for something like this, right? Because like now, basically there's no knowledge cutoff is always live, but then there's a difference between what the model has sort of internalized in its back propagation and what is searching up its rag.Romain [00:11:53]: I think it kind of depends on the use case, right? And what you want to showcase as the source. Like, for instance, you take a company like Hebbia that has used this like web search tool. They can combine like for credit firms or law firms, they can find like, you know, public information from the internet with the live sources and citation that sometimes you do want to have access to, as opposed to like the internal knowledge. But if you're building something different, well, like, you just want to have the information. If you want to have an assistant that relies on the deep knowledge that the model has, you may not need to have these like direct citations. So I think it kind of depends on the use case a little bit, but there are many, uh, many companies like Hebbia that will need that access to these citations to precisely know where the information comes from.swyx [00:12:34]: Yeah, yeah, uh, for sure. And then one thing on the, on like the breadth, you know, I think a lot of the deep research, open deep research implementations have this sort of hyper parameter about, you know, how deep they're searching and how wide they're searching. I don't see that in the docs. But is that something that we can tune? Is that something you recommend thinking about?Nikunj [00:12:53]: Super interesting. It's definitely not a parameter today, but we should explore that. It's very interesting. I imagine like how you would do it with the web search tool and responsive API is you would have some form of like, you know, agent orchestration over here where you have a planning step and then each like web search call that you do like explicitly goes a layer deeper and deeper and deeper. But it's not a parameter that's available out of the box. But it's a cool. It's a cool thing to think about. Yeah.swyx [00:13:19]: The only guidance I'll offer there is a lot of these implementations offer top K, which is like, you know, top 10, top 20, but actually don't really want that. You want like sort of some kind of similarity cutoff, right? Like some matching score cuts cutoff, because if there's only five things, five documents that match fine, if there's 500 that match, maybe that's what I want. Right. Yeah. But also that might, that might make my costs very unpredictable because the costs are something like $30 per a thousand queries, right? So yeah. Yeah.Nikunj [00:13:49]: I guess you could, you could have some form of like a context budget and then you're like, go as deep as you can and pick the best stuff and put it into like X number of tokens. There could be some creative ways of, of managing cost, but yeah, that's a super interesting thing to explore.Alessio [00:14:05]: Do you see people using the files and the search API together where you can kind of search and then store everything in the file so the next time I'm not paying for the search again and like, yeah, how should people balance that?Nikunj [00:14:17]: That's actually a very interesting question. And let me first tell you about how I've seen a really cool way I've seen people use files and search together is they put their user preferences or memories in the vector store and so a query comes in, you use the file search tool to like get someone's like reading preferences or like fashion preferences and stuff like that, and then you search the web for information or products that they can buy related to those preferences and you then render something beautiful to show them, like, here are five things that you might be interested in. So that's how I've seen like file search, web search work together. And by the way, that's like a single responses API call, which is really cool. So you just like configure these things, go boom, and like everything just happens. But yeah, that's how I've seen like files and web work together.Romain [00:15:01]: But I think that what you're pointing out is like interesting, and I'm sure developers will surprise us as they always do in terms of how they combine these tools and how they might use file search as a way to have memory and preferences, like Nikum says. But I think like zooming out, what I find very compelling and powerful here is like when you have these like neural networks. That have like all of the knowledge that they have today, plus real time access to the Internet for like any kind of real time information that you might need for your app and file search, where you can have a lot of company, private documents, private details, you combine those three, and you have like very, very compelling and precise answers for any kind of use case that your company or your product might want to enable.swyx [00:15:41]: It's a difference between sort of internal documents versus the open web, right? Like you're going to need both. Exactly, exactly. I never thought about it doing memory as well. I guess, again, you know, anything that's a database, you can store it and you will use it as a database. That sounds awesome. But I think also you've been, you know, expanding the file search. You have more file types. You have query optimization, custom re-ranking. So it really seems like, you know, it's been fleshed out. Obviously, I haven't been paying a ton of attention to the file search capability, but it sounds like your team has added a lot of features.Nikunj [00:16:14]: Yeah, metadata filtering was like the main thing people were asking us for for a while. And I'm super excited about it. I mean, it's just so critical once your, like, web store size goes over, you know, more than like, you know, 5,000, 10,000 records, you kind of need that. So, yeah, metadata filtering is coming, too.Romain [00:16:31]: And for most companies, it's also not like a competency that you want to rebuild in-house necessarily, you know, like, you know, thinking about embeddings and chunking and, you know, how of that, like, it sounds like very complex for something very, like, obvious to ship for your users. Like companies like Navant, for instance. They were able to build with the file search, like, you know, take all of the FAQ and travel policies, for instance, that you have, you, you put that in file search tool, and then you don't have to think about anything. Now your assistant becomes naturally much more aware of all of these policies from the files.swyx [00:17:03]: The question is, like, there's a very, very vibrant RAG industry already, as you well know. So there's many other vector databases, many other frameworks. Probably if it's an open source stack, I would say like a lot of the AI engineers that I talk to want to own this part of the stack. And it feels like, you know, like, when should we DIY and when should we just use whatever OpenAI offers?Nikunj [00:17:24]: Yeah. I mean, like, if you're doing something completely from scratch, you're going to have more control, right? Like, so super supportive of, you know, people trying to, like, roll up their sleeves, build their, like, super custom chunking strategy and super custom retrieval strategy and all of that. And those are things that, like, will be harder to do with OpenAI tools. OpenAI tool has, like, we have an out-of-the-box solution. We give you the tools. We use some knobs to customize things, but it's more of, like, a managed RAG service. So my recommendation would be, like, start with the OpenAI thing, see if it, like, meets your needs. And over time, we're going to be adding more and more knobs to make it even more customizable. But, you know, if you want, like, the completely custom thing, you want control over every single thing, then you'd probably want to go and hand roll it using other solutions. So we're supportive of both, like, engineers should pick. Yeah.Alessio [00:18:16]: And then we got computer use. Which I think Operator was obviously one of the hot releases of the year. And we're only two months in. Let's talk about that. And that's also, it seems like a separate model that has been fine-tuned for Operator that has browser access.Nikunj [00:18:31]: Yeah, absolutely. I mean, the computer use models are exciting. The cool thing about computer use is that we're just so, so early. It's like the GPT-2 of computer use or maybe GPT-1 of computer use right now. But it is a separate model that has been, you know, the computer. The computer use team has been working on, you send it screenshots and it tells you what action to take. So the outputs of it are almost always tool calls and you're inputting screenshots based on whatever computer you're trying to operate.Romain [00:19:01]: Maybe zooming out for a second, because like, I'm sure your audience is like super, super like AI native, obviously. But like, what is computer use as a tool, right? And what's operator? So the idea for computer use is like, how do we let developers also build agents that can complete tasks for the users, but using a computer? Okay. Or a browser instead. And so how do you get that done? And so that's why we have this custom model, like optimized for computer use that we use like for operator ourselves. But the idea behind like putting it as an API is that imagine like now you want to, you want to automate some tasks for your product or your own customers. Then now you can, you can have like the ability to spin up one of these agents that will look at the screen and act on the screen. So that means able, the ability to click, the ability to scroll. The ability to type and to report back on the action. So that's what we mean by computer use and wrapping it as a tool also in the responses API. So now like that gives a hint also at the multi-turned thing that we were hinting at earlier, the idea that like, yeah, maybe one of these actions can take a couple of minutes to complete because there's maybe like 20 steps to complete that task. But now you can.swyx [00:20:08]: Do you think a computer use can play Pokemon?Romain [00:20:11]: Oh, interesting. I guess we tried it. I guess we should try it. You know?swyx [00:20:17]: Yeah. There's a lot of interest. I think Pokemon really is a good agent benchmark, to be honest. Like it seems like Claude is, Claude is running into a lot of trouble.Romain [00:20:25]: Sounds like we should make that a new eval, it looks like.swyx [00:20:28]: Yeah. Yeah. Oh, and then one more, one more thing before we move on to agents SDK. I know you have a hard stop. There's all these, you know, blah, blah, dash preview, right? Like search preview, computer use preview, right? And you see them all like fine tunes of 4.0. I think the question is, are we, are they all going to be merged into the main branch or are we basically always going to have subsets? Of these models?Nikunj [00:20:49]: Yeah, I think in the early days, research teams at OpenAI like operate with like fine tune models. And then once the thing gets like more stable, we sort of merge it into the main line. So that's definitely the vision, like going out of preview as we get more comfortable with and learn about all the developer use cases and we're doing a good job at them. We'll sort of like make them part of like the core models so that you don't have to like deal with the bifurcation.Romain [00:21:12]: You should think of it this way as exactly what happened last year when we introduced vision capabilities, you know. Yes. Vision capabilities were in like a vision preview model based off of GPT-4 and then vision capabilities now are like obviously built into GPT-4.0. You can think about it the same way for like the other modalities like audio and those kind of like models, like optimized for search and computer use.swyx [00:21:34]: Agents SDK, we have a few minutes left. So let's just assume that everyone has looked at Swarm. Sure. I think that Swarm has really popularized the handoff technique, which I thought was like, you know, really, really interesting for sort of a multi-agent. What is new with the SDK?Nikunj [00:21:50]: Yeah. Do you want to start? Yeah, for sure. So we've basically added support for types. We've made this like a lot. Yeah. Like we've added support for types. We've added support for guard railing, which is a very common pattern. So in the guardrail example, you basically have two things happen in parallel. The guardrail can sort of block the execution. It's a type of like optimistic generation that happens. And I think we've added support for tracing. So I think that's really cool. So you can basically look at the traces that the Agents SDK creates in the OpenAI dashboard. We also like made this pretty flexible. So you can pick any API from any provider that supports the ChatCompletions API format. So it supports responses by default, but you can like easily plug it in to anyone that uses the ChatCompletions API. And similarly, on the tracing side, you can support like multiple tracing providers. By default, it sort of points to the OpenAI dashboard. But, you know, there's like so many tracing providers. There's so many tracing companies out there. And we'll announce some partnerships on that front, too. So just like, you know, adding lots of core features and making it more usable, but still centered around like handoffs is like the main, main concept.Romain [00:22:59]: And by the way, it's interesting, right? Because Swarm just came to life out of like learning from customers directly that like orchestrating agents in production was pretty hard. You know, simple ideas could quickly turn very complex. Like what are those guardrails? What are those handoffs, et cetera? So that came out of like learning from customers. And it was initially shipped. It was not as a like low-key experiment, I'd say. But we were kind of like taken by surprise at how much momentum there was around this concept. And so we decided to learn from that and embrace it. To be like, okay, maybe we should just embrace that as a core primitive of the OpenAI platform. And that's kind of what led to the Agents SDK. And I think now, as Nikuj mentioned, it's like adding all of these new capabilities to it, like leveraging the handoffs that we had, but tracing also. And I think what's very compelling for developers is like instead of having one agent to rule them all and you stuff like a lot of tool calls in there that can be hard to monitor, now you have the tools you need to kind of like separate the logic, right? And you can have a triage agent that based on an intent goes to different kind of agents. And then on the OpenAI dashboard, we're releasing a lot of new user interface logs as well. So you can see all of the tracing UIs. Essentially, you'll be able to troubleshoot like what exactly happened. In that workflow, when the triage agent did a handoff to a secondary agent and the third and see the tool calls, et cetera. So we think that the Agents SDK combined with the tracing UIs will definitely help users and developers build better agentic workflows.Alessio [00:24:28]: And just before we wrap, are you thinking of connecting this with also the RFT API? Because I know you already have, you kind of store my text completions and then I can do fine tuning of that. Is that going to be similar for agents where you're storing kind of like my traces? And then help me improve the agents?Nikunj [00:24:43]: Yeah, absolutely. Like you got to tie the traces to the evals product so that you can generate good evals. Once you have good evals and graders and tasks, you can use that to do reinforcement fine tuning. And, you know, lots of details to be figured out over here. But that's the vision. And I think we're going to go after it like pretty hard and hope we can like make this whole workflow a lot easier for developers.Alessio [00:25:05]: Awesome. Thank you so much for the time. I'm sure you'll be busy on Twitter tomorrow with all the developer feedback. Yeah.Romain [00:25:12]: Thank you so much for having us. And as always, we can't wait to see what developers will build with these tools and how we can like learn as quickly as we can from them to make them even better over time.Nikunj [00:25:21]: Yeah.Romain [00:25:22]: Thank you, guys.Nikunj [00:25:23]: Thank you.Romain [00:25:23]: Thank you both. Awesome. Get full access to Latent.Space at www.latent.space/subscribe

The dumbest, meanest people you know have only one truly safe space to express themselves without fear of consequences for their ignorance, and it happens to be Facebook

Strap yourselves in folks - New York Toy Fair 2025 is here and it brought the big guns! We - and our wallets - are under heavy fire from a carpet bombing of toy goodness and reveals! Enjoy this mid-week drop while we take some time to recover and sell our kidneys to afford all our wants! Don't forget to grab your Super7 items from our affiliate linkSupport the show: http://patreon.com/toypowerpodcastSee omnystudio.com/listener for privacy information.

This week on the Toy Power Podcast, we are joined with Steve Scholz *again*; this round is a much more in depth episode all centred around Steve himself! First up are his initiation questions, as we dive deeper into his person journey in the Pop Culture realm. Find out about a how he was a key contributor on creating an artistic Vinyl Toy Penguin; with a long term plan of other characters in the line; as well as some of the other characters they had planned to release. Don't wish to pay for movie tickets? Steve lets you in on just how successful he was on this endeavor & how his mates & himself where Cosplaying well before it was a mainstream hobby! Then we dive right into just how much Steve is a die hard Mad Max fan; and has been to no less than FIVE dedicated events with a sixth one planned on the horizon! What makes these events so special & what can you expect if you wish to join?! All this and more! Be entertained! Find out more & support Steve Scholz here: https://www.facebook.com/toyroomtattoo https://www.instagram.com/toyroomtattoo https://www.facebook.com/themightywezSupport the show: http://patreon.com/toypowerpodcastSee omnystudio.com/listener for privacy information.

Mark you calendar folks, the second annual TEHRS POTA Campout is happening from Thursday July 31 to Sunday August 3 2025 on the beautiful Danish island of Bornholm. We can promise nerd talk, radios, POTA and SOTA, Danish beer and Danish pastry, and we have even got a really good price on accomodation. Want to know more? Check out https://hamshow.eu/meetup or just watch this show.Please join our discord at https://hamshow.eu/discordTEHRS is: @LB5JJ @labcat73 @LB4FH @AH6UN_OE4JHW @LB0FI #amateurradio #hamradio #amateurfunk Hosted on Acast. See acast.com/privacy for more information.

In a ToyPower first, we record somewhere OTHER than a hosts toy room! We take the show on the road to home of one of Adelaides premier geek aficionados Steve Scholz. While we delve a little into our hosts amazing collection (more on that coming next week!) there is some tasty news to cover. Is this the first Shredder Ben is NOT keen on? Todd and Batman - what could go wrong? JoyToy is KILLING it while Mondo just continue to do Mondo things. Find out more about Steve Scholz to prepare for next week!https://www.facebook.com/toyroomtattoohttps://www.instagram.com/toyroomtattoohttps://www.facebook.com/themightywezSupport the show: http://patreon.com/toypowerpodcastSee omnystudio.com/listener for privacy information.