Podcasts about zoekt

Je winst verdubbelen en tóch teleurgestelde aandeelhouders hebben. Het lukt Amazon! De inkomsten stijgen bij de techreus aan alle kanten, maar volgens beleggers is het allemaal niet genoeg. Tel daar de mega-investeringen bij op: Amazon investeert dit jaar ruim 105 miljard dollar. En dat terwijl ze niet eens aan de vraag van klanten kunnen voldoen. Zijn beleggers verwende snotneuzen? Of zijn hun zorgen over de mega-investeringen terecht? Dat vertellen we je in deze aflevering. En dan vertellen we je ook over Roy Jakobs, de topman van Philips. Die dacht eindelijk rustig te kunnen slapen en nooit meer iets over de apneu-affaire te horen. Maar nu krijgt het hele debacle toch een staartje. Hij heeft namelijk een massaclaim van aandeelhouders aan zijn broek. Het gaat ook over de ECB. Hopelijk heeft Christine Lagarde een flink potje geld apart staan voor afscheidsfeestjes. Anders wordt het een duur jaar voor haar, want een enorm aantal bestuurders moet vertrekken. Dat is een reden voor zorgen bij sommige economen. Want met onheilspellende plannen van Trump en een blijvende inflatie die boven de markt hangen, kan het nog een onstuimig jaar worden. Al helemaal als er een hoop nieuwelingen over het economische beleid gaan. En we blikken uiteraard terug op de week. Die waarin Spotify voor het eerst een jaarwinst noteerde. En die waarin autobouwers de sfeer verpestten met waarschuwingen.See omnystudio.com/listener for privacy information.

Je winst verdubbelen en tóch teleurgestelde aandeelhouders hebben. Het lukt Amazon! De inkomsten stijgen bij de techreus aan alle kanten, maar volgens beleggers is het allemaal niet genoeg. Tel daar de mega-investeringen bij op: Amazon investeert dit jaar ruim 105 miljard dollar. En dat terwijl ze niet eens aan de vraag van klanten kunnen voldoen. Zijn beleggers verwende snotneuzen? Of zijn hun zorgen over de mega-investeringen terecht? Dat vertellen we je in deze aflevering. En dan vertellen we je ook over Roy Jakobs, de topman van Philips. Die dacht eindelijk rustig te kunnen slapen en nooit meer iets over de apneu-affaire te horen. Maar nu krijgt het hele debacle toch een staartje. Hij heeft namelijk een massaclaim van aandeelhouders aan zijn broek. Het gaat ook over de ECB. Hopelijk heeft Christine Lagarde een flink potje geld apart staan voor afscheidsfeestjes. Anders wordt het een duur jaar voor haar, want een enorm aantal bestuurders moet vertrekken. Dat is een reden voor zorgen bij sommige economen. Want met onheilspellende plannen van Trump en een blijvende inflatie die boven de markt hangen, kan het nog een onstuimig jaar worden. Al helemaal als er een hoop nieuwelingen over het economische beleid gaan. En we blikken uiteraard terug op de week. Die waarin Spotify voor het eerst een jaarwinst noteerde. En die waarin autobouwers de sfeer verpestten met waarschuwingen.See omnystudio.com/listener for privacy information.

Pierrette heeft zich teruggetrokken in een tent. Haar pijprokende sjamanistische grootmoeder vindt het de hoogste tijd voor een 'rite de passage'. Drie dagen vasten op de Kezelberg en dan zal in haar dromen een totemdier verschijnen, haar gids voor het leven - zoals vroeger elke jonge indiaan zijn totemdier zag. Die grootmoeder heeft dan ook iets met pak weg vredespijpen, Cherokee, Hiawatha, en vandaar - zelfs redelijk letterlijk - met Guido Gezelle. Zal Pierrette uiteindelijk een trek van het familie-calumet mogen nemen?  Pierrette COffrée is woordkunstenaar maar ook een Moriense sjamane. Geroot in West-Vlaamse klei spoelde zij aan in Antwerpen, waar ze performt, schrijft en acteert. Als magisch-realist is ze verbonden aan het Hubert-Lampo-Genootschap. Ze doceert Woordkunst aan de podiumacademie van Lier.In 2024 verscheen Tabak Taboek bij vzw de Scriptomanen, een werk dat neerkomt op een poëtisch pogen om het ‘roken' te redden uit de handen van Big Tabacco enerzijds en een totaal verbod anderzijds. Moeten de ‘gerechtigde' rokers voortaan Arawaks spreken? Mag Pierrette dromen van een wereld zonder verslaving? Zoekt zij de hulp van Gezelles Hiawatha? Wil zij een kiezelsteentje of veeleer een plukje tabak bijdragen om het trauma van het Zuid-Amerikaanse kolonialisme te helen? ‘Dit is te zware toebak', zegt ze schouderophalend. ‘Ik wil alleen maar dat de lezer gewoon geniet!' Genieten kunt u bijgevolg volop doen door dit heerlijk surrealistische, magisch-realistische maar vooral onversneden Pierrettistische boek aan te schaffen in de betere boekhandel, of rechtstreeks bij de uitgever:https://www.scriptomanen.org/2024/10/tabak-taboek-pierrette-coffree.html Abonneer je nu op Mysterieus België zodat je zeker geen aflevering hoeft te missen. Misschien vind je ook de tijd om onze podcast een mooi boeketje sterren toe te kennen op je favoriete platform, of een review te schrijven? Wil je ons bovendien een onmisbaar financieel steuntje in de rug geven? Word dan lid van onze SUPPORTERS CLUB! Voor een kleine maandelijkse bijdrage krijg je toegang tot allerlei lekkers. Volg de link:https://www.spreaker.com/podcast/mysterieus-belgie--5917929/support

We hebben het de hele maand geroepen, nu is er geen woord meer aan gelogen: de gekte op de transfermarkt is écht losgebarsten. Wat is er aan de hand met Jordan Henderson? Wie moet de geblesseerde Ricardo Pepi vervangen bij PSV en speelt Feyenoord over twee weken tégen Santiago Gimenez?Speciaal vanwege het gekkenhuis gaat #DoneDeal deze vrijdag live. In een uitzending van ruim een uur komt alles aan bod, van de Nederlandse Eredivisie tot de Europese topcompetities en ver daarbuiten. Check hem hierboven!Zie het privacybeleid op https://art19.com/privacy en de privacyverklaring van Californië op https://art19.com/privacy#do-not-sell-my-info.

Voor de laatste keer dit seizoen schuiven Stéphanie (Shitshow) en Dook aan in de studio. In Seefeld is het klaar met het stiekeme gedoe. Mama Monique probeert onder het genot van zoete witte wijn nog één keer de mommy-issues van Mike te projecteren op Antine. Blijkbaar zoeken alle mannen een vrouw zoals hun moeder. In Zweden neemt Willem het voortouw in de liefde door Jan een stiekeme smakkerd te geven, maar Timo twijfelt aan de intenties van de sieradenimporteur. Maarten is zijn zwembroek weer eens kwijt, dus stapt hij in adamskostuum met Annette een ijsbad in. Jorik probeert Marieke naar huis te sturen (kortsluiting) en Adrienne lijkt op de valreep te zwichten voor Disney-prins Frits.Hello Fresh: (Her)activeer je lidmaatschap en krijg tot wel € 90 korting op je eerste 4 boxen met de code HELLOREALITYDeze winter bespreken we dagelijks Winter vol Liefde. En elke week zijn we er ook met een weeksamenvatting met een speciale gast, exclusief op Podimo. Niet getreurd, je kunt 30 dagen helemaal gratis luisteren via podimo.nl/realitycheck.Heb jij een hot take, spannende achtergrondinformatie of wil je heel graag je mening met ons delen? Stuur ons dan een (voice)berichtje op instagram (@realitycheck_depodcast). Op onze Instagram & TikTok houden we 24/7 alles voor je in de gaten houden uit Reality-TV land.Productie: Eva Essers, Gijs Grimm, Bo CourantZie het privacybeleid op https://art19.com/privacy en de privacyverklaring van Californië op https://art19.com/privacy#do-not-sell-my-info.

Washington en World Economic Forum | Trump belt met Xi | Xi belt met PoetinSee omnystudio.com/listener for privacy information.

Op zoek naar technisch, of sales talent? CC.Talent biedt remote professionals vanuit de Filipijnen.

Elke zondag checken Vincent en Daniël in bij B&B De Podcast om de perikelen in Winter Vol Liefde te bespreken. Vandaag: wie gaan deze winter op zoek naar de liefde? En hoe gaat het nu met Guido?

Spreker: Prof. Dr. H. van den BeltTekst: Mattheüs 6:33Thema: Zoekt eerst het Koninkrijk en de gerechtigheid van GodLocatie: Her. Gemeente Oud-AlblasDatum: 7 januari 2024Bron: https://kerkdienstgemist.nl/stations/1189/events/recording/170461620001189?media=audio ★ Support this podcast ★

“Het is heel belangrijk dat Europa een gedeelde visie heeft als het om steun aan Oekraïne gaat,” zei president Volodymyr Zelensky gisteravond tijdens een bezoek aan de Navo. Ook vandaag ontmoet Zelensky leiders op een Europese top in Brussel. Met het naderende presidentschap van Donald Trump in de VS is Europese eensgezindheid richting Oekraïne, Rusland én de VS urgenter dan ooit.  Daarover EU-correspondent bij NRC Rik Rutten.  (12:02) Zonder vrouwen sneuvelt de Afghaanse zorg  De Taliban sluiten de deuren van zorgscholen voor vrouwen, en daarmee zien velen hun laatste hoop op zelfstandigheid vervliegen. De zorg was de laatste publieke plek in Afghanistan waar vrouwen nog welkom waren. Toch slagen sommigen erin om binnen alle beperkingen nog een kleine ruimte te vinden om vrouwen aan het werk te houden in de zorg. We bespreken dit met de Afghaans-Nederlandse arts Niloufar Rahim en Mahbooba Menapal, voorzitter van Rescue Mother & Child Afghanistan. Presentatie: Tim de Wit

Wat zit er in De 7 vandaag?Het aantal buitenlanders dat Belg wordt, is op weg naar een piek. Het is van 2001 geleden dat we deze niveau's haalden. Hoe komt dat? En hoe divers is die groep nieuwe BelgenWelk energiebedrijf mag tien jaar lang nucleaire stroom gaan verkopen in ons land? De regering lanceert een enorme aanbesteding. Die hebben we bij De Tijd kunnen inkijken.En naar goeie gewoonte checken we op het einde van de week de stand van onze beursrally. Wie neemt daar de leiding? En welke beurstendensen heeft die gevolgd om daar te geraken? Host: Bert RymenProductie: Roan Van EyckSee omnystudio.com/listener for privacy information.

Nina Derwael spreekt voor het eerst sinds de Olympische Spelen van afgelopen zomer. In een gesprek met onze Inge Van Meensel heeft ze het over de afgelopen Spelen, haar ambities in de nieuwe olympische cyclus én over de Gymfed. Ze steekt haar teleurstelling in de federatie over het uitblijven van een nieuwe hoofdcoach niet weg. Ilse Arys, algemeen manager van Gymfed, begrijpt de bezorgdheden, maar verzekert dat er naar oplossingen wordt gezocht.

Het regime van Assad kwam gisterochtend ten einde nadat Syrische rebellen hoofdstad Damascus waren binnengetrokken. Volgens het Russische ministerie van buitenlandse zaken stapte Assad op na mislukte onderhandelingen met een aantal partijen in het conflict. Rebellenleider Abu Mohammad al-Jolani claimde daarop de overwinning. De gevluchte Syrische president Assad zit inmiddels in Rusland, zo melden Russische staatsmedia. De voormalige president van Syrië en zijn gezin bevinden zich in de hoofdstad Moskou. Rusland was een bondgenoot van het gevallen regime. ‘Rusland heeft hen op basis van humanitaire overwegingen asiel verleend', zei een Kremlin-bron tegenover Russische persbureaus.  De aankomende Amerikaanse president Donald Trump heeft geen plannen om Jerome Powell, voorzitter van de Federal Reserve, te vervangen zodra hij in januari aan zijn ambt begint. Dat heeft Trump zondag gezegd in een interview met NBC News. De politie doet nog volop onderzoek naar de toedracht van de explosies aan de Tarwekamp in Den Haag van zaterdagochtendvroeg. Het Openbaar Ministerie ziet in dat onderzoek aanwijzingen voor een misdrijf, zegt justitieminister David van Weel tijdens een bezoek aan de plek van de explosie.See omnystudio.com/listener for privacy information.

Brian Priske zei het na afloop tijdens de persconferentie en de mannen van Podcast Feyenoord zijn het met de trainer van Feyenoord eens. Het gebrek aan intensiteit was het grote probleem van Feyenoord in de moeizame wedstrijd tegen RKC Waalwijk, die met 3-2 werd gewonnen. "Feyenoord gaf niet thuis en de intensiteit was ondermaats", concludeert Dennis van Eersel.

Veel Nederlands succes op de buitenlandse velden in deze VI ZSM, want zowel Memphis Depay, Tijjani Reijnders als Frenkie de Jong waren trefzeker. Het wordt besproken door Lentin Goodijk en Matthijs Vegter. Bovendien kende Ruud van Nistelrooij een succesvol debuut als trainer van Leicester City én speelt Ajax vanavond de topper tegen FC Utrecht.Zie het privacybeleid op https://art19.com/privacy en de privacyverklaring van Californië op https://art19.com/privacy#do-not-sell-my-info.

Welk dier is het best voor de natuur? Waar is het klimaat het best en waar het slechtst? Wie is de grootste held van het klimaat? En wat is eigenlijk het allergrootste klimaatprobleem? In de laatste aflevering van dit seizoen rinkelt de EHBU-telefoon aan de lopende band. Gelukkig is Willie Wartaal er om samen met Carice en Sieger antwoorden te zoeken op belangrijke vragen van kinderen. De podcast EHBU wordt gemaakt in samenwerking met Milieudefensie. Help ons Nederland duurzaam en eerlijk te maken. In je eentje los je de klimaatcrisis niet op. Maar jij, ik en nog een heleboel jij's wel. Hoe meer jij's, hoe sterker de wij. Een wij die niet te negeren is! Vervuilers zijn sterk, met z'n allen zijn wij sterker. Ruim 200.000 mensen doen al mee! Jij ook? [milieudefensie.nl] Muziek: Goldband - De Wereld Voice over: Jacob Derwig Fotografie: Aischa Zijpveld

De Haarlemse stadsambassadeur in Osnabrück, Levy Gores, wacht nog steeds op een opvolger. De ambassadeur, die Haarlem officieel vertegenwoordigt in de Duitse zusterstad, hoopte zijn functie in september al te kunnen overdragen, maar dat is niet gelukt: “Helaas heeft zich nog niemand gemeld”, vertelt Gores in Haarlem Vandaag.

Toon Roefs en Jan van Laake zijn te gast in deze podcast. Beiden zijn lid van de bridgeclub Mill en zij zoeken liefhebbers om een cursus bridge (start medio februari 2025) te gaan volgen. Enthousiast vertellen zij over bridge, waar veel meer bij komt kijken dan bij een gemiddeld ander potje kaarten.

André Kievits en Theo Cools zijn te gast in deze podcast. Zij praten over het succesvolle Walking Football, dat bij EGS'20 gespeeld wordt. Ze kunnen versterking gebruiken, maar dat wil niet zeggen dat ze geen leden hebben. Ze hebben de leeftijdsgrens verlaagd om nóg toekomstbestendiger te worden.

Het Vierdaagse Orkest staat onder leiding van dirigent Bart van Zutven, die samen met vocal coach Stephanie van Werkhoven en dansdocent Janne van Lanen van Dance Departement Malden een reeks fantastische concerten weet neer te zetten. In deze podcast is Stephanie van Werkhoven telefoongast. Zij vertelt over de mogelijkheid voor zangers/zangeressen om aan te sluiten bij het koor en roept liefhebbers op om zich te melden voor een auditie.

Waardeer je onze video's? Steun dan Café Weltschmerz, het podium voor het vrije woord: https://www.cafeweltschmerz.nl/doneren/In de 32e aflevering van De Andere Tafel ontvangt Sander Compagner de filmmakers Marijn Poels en Adrian Kuipers. Poels en Kuipers zijn de producenten van de documentaire Primordial code, The Burning Essence die eerder dit weekend in première is gegaan. Bekijk de documentaire via https://www.youtube.com/watch?v=yR8ovcfshfsVoor meer informatie over de concerten van Kuipers: https://shop.adriankuipers.com/nl---Deze video is geproduceerd door Café Weltschmerz. Café Weltschmerz gelooft in de kracht van het gesprek en zendt interviews uit over actuele maatschappelijke thema's. Wij bieden een hoogwaardig alternatief voor de mainstream media. Café Weltschmerz is onafhankelijk en niet verbonden aan politieke, religieuze of commerciële partijen.Wil je meer video's bekijken en op de hoogte blijven via onze nieuwsbrief? Ga dan naar: https://www.cafeweltschmerz.nl/videos/Wil je op de hoogte worden gebracht van onze nieuwe video's? Klik hierboven dan op Abonneren!

In Haps speelt op dinsdag- en donderdagmorgen een clubje mensen badminton in de sporthal. We spraken Sjef Janssen telefonisch en dat gesprek is in deze podcast te horen.

Welkom allemaal bij een nieuwe podcast met de missie om de online automotive beter te maken. Vandaag gaan we dat doen Rutger Hoekstra, Manager Business to Business and Innovations bij ViaBOVAG.nl. Welkom Rutger, leuk dat je er bent, wil je onze luisteraars vertellen wie je bent en wat je doet?    "Ik ben 44 jaar en het zijn spannende en leuke tijden voor mij: het BOVAG-congres, en ik ga trouwen in december en onze zoon van 1 jaar, gaat de ringen brengen. Bij ViaBOVAG heeft twee pijlers: B2C, voor de consument en B2B voor de autobedrijven. Commercie, marketing, data en innovatie, value added service aan de B2B kant. Aan de B2C hebben we het over online marketing daar is een collega voor verantwoordelijk. Ik verkoop ViaBOVAG op een informele manier aan de leden. Ik kom vanuit Bovemij en ik was in eerste instantie product owner van innovaties op ViaBOVAG.nl. Toen ViaBOVAG los kwam te staan van Bovemij heb ik de overstap gemaakt naar ViaBOVAG.”   “Het is ons uitstekend bevallen om ook auto's zonder BOVAG-garantie of onder de BOVAG-grens toe te laten op ViaBOVAG.nl. Het afgelopen jaar hebben we een enorme groei doorgemaakt qua aansluiten van nieuwe leden op het platform. Er zijn veel BOVAG-leden die auto's hebben die zich niet lenen voor die 12 maanden BOVAG-garantie, ook die maken we nu blij en we hadden veel klanten die hun aanbod niet op ons platform kwijt konden en nu dus wel. ViaBOVAG staat nog steeds voor betrouwbaar, dat kan ook zonder 12 maanden BOVAG-garantie, bijvoorbeeld als je te maken hebt met een betrouwbaar BOVAG-bedrijf. We zien meer advertenties op het platform, mijn missie is om alle BOVAG-leden aan te sluiten en dat we de niet-BOVAG-leden lid gaan maken en ook gaan aansluiten op het platform.  Qua leads zien we een nog sterkere groei dan het aantal advertenties op het platform. We zien leads sneller stijgen dan het aanbod.”   “Vandaag is een heugelijk moment; we zijn genomineerd voor een DDMA-award, op het gebied voor innovatie, maar niet in de autobranche, dat is landelijk. Rituals, Friesland Campina en Intergamma zijn dat ook. Wat we doen valt op. Ons doel is om die award te gaan winnen. Er is nog meer aan de hand vandaag. Vorig jaar zijn we begonnen met leadbegeleiding en die service is vandaag live gegaan. Het heet LeadInzicht, we pakken de inzichten mee over hoe de lead zich gedraagt, waar kijkt hij, hoelang etc.  Als portal willen we niet inbreken in het proces van te mobiliteitsbedrijf. We hebben gekeken vanuit de consument. We houden de consument met extra aandacht op de auto en we attenderen het bedrijf op de lead. We wijzen niet met het vingertje. Als de lead geen belangstelling meer heeft in de auto en het bedrijf, laten we gelijksoortig aanbod zien, maar alleen als de lead is afgehaakt op het bedrijf. We halen ‘m niet weg bij het ene bedrijf om ‘m elders aan te bieden.”   “LeadInzicht geeft inzicht in de consument, en je ziet een leadpotentiescore, dat aangeeft hoe groot de kans is dat de klant gaat converteren. Die score is bepaald door time on site, aantal bekeken pagina's, inruil van zijn auto. Als er een lead wordt aangeleverd bij het bedrijf, zit er een magic link bij. Dan kom je zonder in te loggen meteen in de omgeving met informatie over de lead. Het zoekgedrag is een van de inzichten. Zoekt de lead op trekhaak, een bepaald prijsbereik, in een specifieke regio? Dat zijn allemaal belangrijke inzichten waar de verkoper op kan inspelen. Ik ben geen autoverkoper, maar misschien moet je wel zeggen dat je allerlei informatie hebt ontvangen van ViaBOVAG.nl en ik zie dat jij interesse hebt in een auto met een trekhaak. Het is een mes dat aan twee kanten snijdt. De consument voelt zich begrepen, de verkoper hoeft niet meer het gesprek van scratch af aan te beginnen. Voor de switchlead hebben we een mooie oplossing. Als er patronen ontstaan, kijken we naar de voorraad en geven wij aan welke auto nog meer past bij het zoekgedrag van de klant. Als een klant niet vast is qua merk, kun je veel breder zoeken in de voorraad, dat is iets wat de verkoper niet automatisch doet. Wij geven dat dan aan.”   We zijn overgestapt op pay-per-lead-model, je houdt de klant dus op de website. ViaBOVAG is er om de leden te ondersteunen, die filosofie staat heel hoog, misschien nog wel hoger dan in het verleden. Ik snap dat de leden traffic naar hun eigen omgeving willen brengen, maar wij bieden de consument misschien wel de perfecte omgeving om tot een lead te komen. Viabovag gaat in Q4 van dit jaar LeadOptimize lanceren, opgebouwd uit het lead-to-sale-principe. Wij gaan bedrijven inzichten geven hoe zij nog beter die lead kunnen laten converteren. Het doel is om de waarde van de lead die van ViaBOVAG komt, verder te laten toenemen. Met LeadInzicht en straks met LeadOptimize gaan we dat doen.”   

Documentairemaker, schrijver, columnist en culinair recensent Hassnae Bouazza heeft een passie voor verhalen die de ene mens dichter bij de andere brengen. En die verhalen kunnen vaak heel goed worden verteld via eten. ‘Je kunt een land of gemeenschap niet begrijpen door alleen naar de politiek te kijken: daaronder liggen de échte levens van mensen.' In deze aflevering van ‘Achter de Frontlinie' breekt Hassnae een lans voor meer aandacht en respect voor tradities en culturele identiteit, vertelt ze wat haar moeder voor haar heeft betekend en legt ze uit waarom couscous liefde is. Abonneer je op ‘Achter de Frontlinie' en mis nooit nieuwe afleveringen. Wil je meer weten? Abonneer je dan ook vooral op de Frontlinie-nieuwsbrief en ontvang elke twee weken extra verhalen van Bram Vermeulen, achtergronden bij het nieuws en lees-, kijk- en luistertips in je inbox. Of kijk naar 'Frontlinie' op NPO Start. Alles van Frontlinie vind je op vpro.nl/frontlinie.

Het is moeilijk om een platonische relatie te hebben met een vrouw. In De Zelfspodcast zoekt een vriendin proberen Sander en Jaap hun langverwachte droom in te lossen: hun vriendschap en podcast uitbreiden met een gelijkgestemde vrouw.Sander en Jaap begonnen De Zelfspodcast in 2019. Maar toen de wereld hen - in 2022 - het hardst nodig had, verdwenen ze achter een betaalmuur. Een update voor de gierige luisteraars die hierdoor zijn afgehaakt: ze zijn daar twee jaar lang doorgegaan met mansplainen. Maar nu ze terugkomen op de open kanalen, is het tijd voor een renaissance. Want er is één ding dat al die tijd ontbrak: een vrouwelijk geluid. Dit alles zodat het volk binnenkort van de daken schreeuwt: twee vrienden en één vriendin, waar ken ik ze toch van?

De partij Groen moet op zoek naar een nieuwe voorzitter. Want het huidige duo trekt er de stekker uit na de tegenvallende verkiezingsresultaten, zowel in juni als in oktober. Voor de opvolging zoekt de partij “een soort groene Rousseau”, iemand die het verhaal wél enthousiasmerend verteld krijgt, en daarvoor wordt vooral gekeken naar één persoon: Petra De Sutter. See omnystudio.com/listener for privacy information.

Ds. G. van Meijeren ( Rotterdam ) over Genesis 38 en Matheus 1 vers 1 t/m vers 3 en vers 16; thema : Tamar zoekt haar recht.

In deze podcast spreken we met Michel Moolenaar directeur van een mbo-opleiding en Han Snijders directeur van een vmbo. Centraal staat de doorgaande lijn in het beroepsonderwijs. Voor het mbo is dat vanuit de aard van de opleiding net iets anders dan voor het vmbo, maar er is een duidelijke overeenkomst naast de beroepscontext is er veel aandacht voor pedagogische en didactische benadering van de leerling en student.

ABN Amro zoekt een nieuwe ceo. Maar kan de staatsbank wel de gewenste topbankier strikken zonder een topsalaris te betalen? In de markt overheerst scepsis en de commissarissen zijn bezorgd. Het overheidskorset knelt steeds meer, vertelt bankenredacteur Mathijs Rotteveel. Zelfs nu Den Haag haar belang in de bank afbouwt. Lees: Achterblijver ABN Amro zoekt topbanker  Nederlandstalige webshops verkopen afslankinjecties als Ozempic aan klanten die zij nauwelijks kennen. Niks mis mee, vinden de webwinkels en apothekers zelf. Maar de toezichthouder denkt daar anders over. Zij waarschuwen dat de online verkoop risico's met zich meebrengt en startte een grootschalig onderzoek. Verslaggever Lisa van der Velden legt uit waarom de wildgroei zo gevaarlijk is. Lees: Snel een doosje Ozempic: afslankhype leidt tot wildgroei in onlinehandel  Redactie: Jildou Beiboer en Anna de Haas Presentatie: Anna de HaasSee omnystudio.com/listener for privacy information.

Het is vandaag 23 september! Tina deelt nieuwe geruchten over het laatste seizoen van De Slimste Mens met Philip Freriks en Maarten van Rossem. Binnenkort keert Oogappels terug en gisteravond was een belangrijk moment voor Yvon Jaspers. Is de Boer zoekt vrouw-hype voorbij?  

Om de 700ste verjaardag van Enschede te vieren, verzamelt historicus Marco Krijnsen allerlei objecten die te maken hebben met de geschiedenis van de stad. In het jubileumjaar wil hij een selectie van honderd voorwerpen tentoonstellen en bundelen in een boek. En daarvoor heeft hij de hulp van Enschedeërs nodig. “Kijk nog eens op zolder.”

Vraagt en u zal gegeven worden; zoekt en ge zult vinden; klopt en er zal worden opengedaan. Want al wie vraagt, verkrijgt; wie zoekt, vindt en voor wie klopt, doet men open. Of is er wel iemand onder u die zijn zoon een steen zal geven als hij om brood vraagt? Of een slang wanneer […]

In de Daily KINK hoor je elke avond om 20:20 het belangrijkste muzieknieuws en de nieuwste releases in KINK IN TOUCH. Ook als podcast. Met vandaag nieuws over: 📌Oasis📌The Smiths

Eindelijk beweging bij Ajax: Silvano Vos vertrekt en maakt ruimte voor Wout Weghorst, die nu écht op weg is naar Amsterdam. Maar wat moet Francesco Farioli met vier spitsen!? Bij Feyenoord zijn het chaotische dagen door de afgeketste transfer van Justin Bijlow en de soap rond Santiago Gimenez. Tegelijkertijd zijn de Rotterdammers ook nog druk bezig met potentiële versterkingen. Johan Bakayoko zou ondertussen ‘nee' hebben gezegd tegen een monstersalaris terwijl Olivier Boscagli wél wil vertrekken en PSV nog altijd geen nieuwe verdediger heeft aangetrokken. Tot slot komt de nog altijd clubloze Memphis aan bod, evenals spraakmakende potentiële versterkingen voor de traditionele top-drie...Zie het privacybeleid op https://art19.com/privacy en de privacyverklaring van Californië op https://art19.com/privacy#do-not-sell-my-info.

Het is maandag 19 augustus! Tina bespreekt het oer-Hollandse programma Boer zoekt Vrouw. Het programma is al meer dan twintig jaar op televisie en is nog steeds succesvol. Waar zit de magie in? En waarom is presentatrice Yvonne Jaspers zo vaak in opspraak geweest? Dat hoor je in deze nieuwe aflevering van Tina's TV Update.

Donald Trump is duidelijk een beetje de weg kwijt, nu hij moet omschakelen van schelden op Joe Biden naar schelden op Kamala Harris. Zijn strategie was het verslaan van Joe Biden, en dat deed hij met een soort vast repertoire: Biden was een mislukking, de slechtste president ooit, incompetent, wat hij aanraakte mislukte, hij kon niet praten, hij had een laag IQ. Maar wat moest hij nou zo gauw van Kamela Harris verzinnen? Nou, gewoon dezelfde teksten, maar dan in plaats van de naam Biden de naam Harris. Jan bereikte een mijlpaal, letterlijk en figuurlijk: hij haalde de finish van de roemruchte highway Route 66, en legde zijn oor op die lange route goed te luisteren. Heb je vragen, opmerkingen, kritiek of complimenten, dan kan dat met een tweet naar @janpostmaUSA of @BNRdewereld, of met een mailtje naar dewereld@bnr.nl. Je kunt ook je vraag inspreken of intikken op de Amerika Podcast WhatsApp: 06 28 13 50 20.See omnystudio.com/listener for privacy information.

In de dagelijkse podcast van FC Afkicken bespreken Bart Obbink en Nicky Bartens onder meer de tweede wedstrijd in de voorronde van de Champions League tussen Twente en RB Salzburg, Ajax dat Aaron Ramsdale wil huren van Arsenal en Ten Hag die Matthijs de Ligt en Noussair Mazraoui naar Manchester haalt!(0:00) Intro(1:04) Twente neemt het op tegen Salzburg!(7:34) Ramsdale naar Ajax?(12:55) Mazraoui en De Ligt naar United!(20:14) Community ShieldZie het privacybeleid op https://art19.com/privacy en de privacyverklaring van Californië op https://art19.com/privacy#do-not-sell-my-info.

Deze week praat Qmusic-dj Menno Barreveld je bij in een nieuwe Top 40. En heb je die gemist, dan doet 'ie het nu dunnetjes over in de podcastfeed. Met deze week: een nieuwe nummer #1! Ook zocht Billie Eilish het hoger op. Niet in de Top 40, maar waar dan wel, dat vertelt Menno je in de podcast. Net als de vier nieuwe binnenkomers waarvan eentje wel heel bijzonder is. Je hoort het allemaal, in dit nieuwe Top 40 Weekoverzicht! En de volledige Nederlandse Top 40? Die hoor je iedere vrijdagmiddag tussen 14:00 uur en 18:00 uur op Qmusic.See omnystudio.com/listener for privacy information.

Kamala Harris was een paar dagen geleden nog de ‘running ‘mate' van, maar inmiddels zoekt ze er zelf een. Wie zijn de kanshebbers en waarom?

Wat zit er in De 7 vandaag? In de Vlaamse onderhandelingsnota worden de ziekenfondsen afgeslankt. De N-VA- onderhandelaars willen dat het zorgbudget en de kinderbijslag niet meer door het middenveld, maar door de overheid worden uitbetaald.Gisteravond was het time to shine voor Joe Biden op de persconferentie na afloop van de NAVO-top in Washington. Hij wil kandidaat-president blijven maar heeft ook nu weer niet alle twijfels weg kunnen nemen.En Cowboy, het hippe elektrische fietsenmerk uit Brussel, klimt langzaam uit het dal. Maar voordat ze effectief winst kunnen maken, hebben ze wel nog eens een miljoeneninvestering nodig. Host: Bert RymenProductie: Lara Droessaert, Roan Van EyckSee omnystudio.com/listener for privacy information.

TomTom, je weet wel, dat bedrijf dat groot is geworden met navigatiekastjes, heeft grootse plannen om de omzet op te krikken. Het aandeel verloor in de eerste zes maanden van dit jaar zo'n 17%, onder meer door tegenvallende omzetcijfers over het eerste kwartaal als gevolg van de ingezakte vraag vanuit de auto-industrie. TomTom Orbis Maps, een nieuw systeem dat openbare gegevens combineert met de kaarten die het bedrijf zelf in huis heeft, moet dit tij keren. De eerste klant hiervoor is binnen: het Estse taxi- en bezorgplatform Bolt, een concurrent van Uber. Maar in hoeverre leidt deze deal de koers van TomTom de weg omhoog? Beurssnerd en Beursnerd XL Iedere werkdag iets na elf uur werpt de Beursnerd in gesprek met presentator Thomas van Zijl een blik op de AEX, waarbij hij of zij de diepgang niet schuwt. Daarnaast is er donderdag om tien voor twaalf een langere beursanalyse. Die neemt Beursnerd XL Jochem Visser voor zijn rekening.See omnystudio.com/listener for privacy information.

Als je iemand vraagt hoe de wereld er over 50 jaar uitziet, hoor je altijd hetzelfde antwoord: vliegende auto's. Als het aan Robert Dingemanse ligt, is die toekomst dichterbij dan je denkt. Met zijn Pal-V zijn snelwegen straks verleden tijd. In Buiten de Beurs kijken we naar bedrijven die belachelijk succesvol zijn, en dat zónder beursnotering. Waarom kiezen die bedrijven ervoor de beurs links te laten liggen? Hoe komen zij dan aan hun geld? En hoe doe jij mee als je zo'n aandeel niet op de beurs kan kopen?See omnystudio.com/listener for privacy information.

De Autoriteit Financiële Markten is voor de komende jaren de nieuwe cryptotoezichthouder. Met de Europese cryptowet MICAR komen er meer regels voor projecten, exchanges en ander soortige bedrijven. Daarbij kiest de AFM nadrukkelijk voor een andere houding dan toezichthouder DNB. De autoriteit wil in gesprek blijven met de sector en heeft naar eigen zeggen veel cryptokennis in huis. Te gast is Jasper Bets, senior supervision officer bij de AFM. Met hem spreken we over het hoe en waarom van de nieuwe cryptowet micar. Het cryptoloket van de AFM gaat 22 april open voor het verwerken van de eerste aanvragen. Dat is naar eigen zeggen een 'zwaarder' traject dan het proces waar bedrijven voor DNB doorheen moesten. Als bedrijven halverwege 2025 geen micar-vergunning hebben, mogen zij niet meer opereren op de Europese markt. Dat roept natuurlijk ook vragen op over de handhaving, want in het verleden opereerde meerdere internationale cryptobedrijven illegaal op de Nederlandse markt, tot groot ongenoegen van de Nederlandse sector. De vraag is ook hoe populair Nederland zal worden als 'uitvalsbasis' voor internationale cryptobedrijven. Want één micar-vergunning biedt de mogelijkheid om te opereren in alle Europese landen. Kiezen bedrijven voor de soepelste toezichthouder (zoals techbedrijven zich het liefst in Ierland vestigen) of gaat het toezicht van de AFM als een soort 'keurmerk' beschouwd worden. Het zal ongetwijfeld onderdeel van gesprek zijn in de bestuurskamers van Binance, Kraken en Coinbase. En vanaf wanneer kunnen Nederlandse cryptobedrijven Europa in trekken? Het uitgeven van deze vergunningen heeft raakvlakken met de goedkeuring van de Amerikaanse Bitcoin ETF's. Toezichthouder SEC liet toen tien fondsen tegelijk van start gaan, om een eerlijk speelveld te garanderen. En wat gaat er concreet veranderen voor cryptogebruikers? Kunnen Europese bedrijven straks alle coins blijven aanbieden? Hoe zit het met de populaire dollar-stablecoins? En zijn er gevolgen voor 'finfluencers', die in crypto toch goed vertegenwoordigd zijn. Mag je nog zomaar crypto-adviezen delen op X (Twitter) of in podcasts? Dat is niet meer zo vanzelfsprekend. En zelfs voor Bitcoin moet er onder Micar een nieuw whitepaper worden aangeleverd, want die van Satoshi voldoet niet aan de voorwaarden.  Gasten Jasper Bets Bert Slagter Links De AFM-pagina rond MICAR Voorzitter Laura van Geest over crypto Host Herbert Blankesteijn Redactie Daniël MolSee omnystudio.com/listener for privacy information.

In de nieuwe aflevering van VI ZSM gaan Tim Tempelaars en Jarno Verweij uitgebreid in op de mogelijke komst van Jordan Henderson naar Ajax. Verder ook de financiële situatie van de clubs in de Eredivisie en de nederlaag van Chelsea tegen Middlesbrough.Zie het privacybeleid op https://art19.com/privacy en de privacyverklaring van Californië op https://art19.com/privacy#do-not-sell-my-info.

We are running an end of year survey for our listeners. Let us know any feedback you have for us, what episodes resonated with you the most, and guest requests for 2024! RAG has emerged as one of the key pieces of the AI Engineer stack. Jerry from LlamaIndex called it a “hack”, Bryan from Hex compared it to “a recommendation system from LLMs”, and even LangChain started with it. RAG is crucial in any AI coding workflow. We talked about context quality for code in our Phind episode. Today's guests, Beyang Liu and Steve Yegge from SourceGraph, have been focused on code indexing and retrieval for over 15 years. We locked them in our new studio to record a 1.5 hours masterclass on the history of code search, retrieval interfaces for code, and how they get SOTA 30% completion acceptance rate in their Cody product by being better at the “bin packing problem” of LLM context generation. Google Grok → SourceGraph → CodyWhile at Google in 2008, Steve built Grok, which lives on today as Google Kythe. It allowed engineers to do code parsing and searching across different codebases and programming languages. (You might remember this blog post from Steve's time at Google) Beyang was an intern at Google at the same time, and Grok became the inspiration to start SourceGraph in 2013. The two didn't know eachother personally until Beyang brought Steve out of retirement 9 years later to join him as VP Engineering. Fast forward 10 years, SourceGraph has become to best code search tool out there and raised $223M along the way. Nine months ago, they open sourced SourceGraph Cody, their AI coding assistant. All their code indexing and search infrastructure allows them to get SOTA results by having better RAG than competitors:* Code completions as you type that achieve an industry-best Completion Acceptance Rate (CAR) as high as 30% using a context-enhanced open-source LLM (StarCoder)* Context-aware chat that provides the option of using GPT-4 Turbo, Claude 2, GPT-3.5 Turbo, Mistral 7x8B, or Claude Instant, with more model integrations planned* Doc and unit test generation, along with AI quick fixes for common coding errors* AI-enhanced natural language code search, powered by a hybrid dense/sparse vector search engine There are a few pieces of infrastructure that helped Cody achieve these results:Dense-sparse vector retrieval system For many people, RAG = vector similarity search, but there's a lot more that you can do to get the best possible results. From their release:"Sparse vector search" is a fancy name for keyword search that potentially incorporates LLMs for things like ranking and term expansion (e.g., "k8s" expands to "Kubernetes container orchestration", possibly weighted as in SPLADE): * Dense vector retrieval makes use of embeddings, the internal representation that LLMs use to represent text. Dense vector retrieval provides recall over a broader set of results that may have no exact keyword matches but are still semantically similar. * Sparse vector retrieval is very fast, human-understandable, and yields high recall of results that closely match the user query. * We've found the approaches to be complementary.There's a very good blog post by Pinecone on SPLADE for sparse vector search if you're interested in diving in. If you're building RAG applications in areas that have a lot of industry-specific nomenclature, acronyms, etc, this is a good approach to getting better results.SCIPIn 2016, Microsoft announced the Language Server Protocol (LSP) and the Language Server Index Format (LSIF). This protocol makes it easy for IDEs to get all the context they need from a codebase to get things like file search, references, “go to definition”, etc. SourceGraph developed SCIP, “a better code indexing format than LSIF”:* Simpler and More Efficient Format: SCIP utilizes Protobuf instead of JSON, which is used by LSIF. Protobuf is more space-efficient, simpler, and more suitable for systems programming. * Better Performance and Smaller Index Sizes: SCIP indexers, such as scip-clang, show enhanced performance and reduced index file sizes compared to LSIF indexers (10%-20% smaller)* Easier to Develop and Debug: SCIP's design, centered around human-readable string IDs for symbols, makes it faster and more straightforward to develop new language indexers. Having more efficient indexing is key to more performant RAG on code. Show Notes* Sourcegraph* Cody* Copilot vs Cody* Steve's Stanford seminar on Grok* Steve's blog* Grab* Fireworks* Peter Norvig* Noam Chomsky* Code search* Kelly Norton* Zoekt* v0.devSee also our past episodes on Cursor, Phind, Codeium and Codium as well as the GitHub Copilot keynote at AI Engineer Summit.Timestamps* [00:00:00] Intros & Backgrounds* [00:05:20] How Steve's work on Grok inspired SourceGraph for Beyang* [00:08:10] What's Cody?* [00:11:22] Comparison of coding assistants and the capabilities of Cody* [00:16:00] The importance of context (RAG) in AI coding tools* [00:21:33] The debate between Chomsky and Norvig approaches in AI* [00:30:06] Normsky: the Norvig + Chomsky models collision* [00:36:00] The death of the DSL?* [00:40:00] LSP, Skip, Kythe, BFG, and all that fun stuff* [00:53:00] The SourceGraph internal stack* [00:58:46] Building on open source models* [01:02:00] SourceGraph for engineering managers?* [01:12:00] Lightning RoundTranscriptAlessio: Hey everyone, welcome to the Latent Space podcast. This is Alessio, partner and CTO-in-Residence at Decibel Partners, and I'm joined by my co-host Swyx, founder of Smol AI. [00:00:16]Swyx: Hey, and today we're christening our new podcast studio in the Newton, and we have Beyang and Steve from Sourcegraph. Welcome. [00:00:25]Beyang: Hey, thanks for having us. [00:00:26]Swyx: So this has been a long time coming. I'm very excited to have you. We also are just celebrating the one year anniversary of ChatGPT yesterday, but also we'll be talking about the GA of Cody later on today. We'll just do a quick intros of both of you. Obviously, people can research you and check the show notes for more. Beyang, you worked in computer vision at Stanford and then you worked at Palantir. I did, yeah. You also interned at Google. [00:00:48]Beyang: I did back in the day where I get to use Steve's system, DevTool. [00:00:53]Swyx: Right. What was it called? [00:00:55]Beyang: It was called Grok. Well, the end user thing was Google Code Search. That's what everyone called it, or just like CS. But the brains of it were really the kind of like Trigram index and then Grok, which provided the reference graph. [00:01:07]Steve: Today it's called Kythe, the open source Google one. It's sort of like Grok v3. [00:01:11]Swyx: On your podcast, which you've had me on, you've interviewed a bunch of other code search developers, including the current developer of Kythe, right? [00:01:19]Beyang: No, we didn't have any Kythe people on, although we would love to if they're up for it. We had Kelly Norton, who built a similar system at Etsy, it's an open source project called Hound. We also had Han-Wen Nienhuys, who created Zoekt, which is, I think, heavily inspired by the Trigram index that powered Google's original code search and that we also now use at Sourcegraph. Yeah. [00:01:45]Swyx: So you teamed up with Quinn over 10 years ago to start Sourcegraph and you were indexing all code on the internet. And now you're in a perfect spot to create a code intelligence startup. Yeah, yeah. [00:01:56]Beyang: I guess the backstory was, I used Google Code Search while I was an intern. And then after I left that internship and worked elsewhere, it was the single dev tool that I missed the most. I felt like my job was just a lot more tedious and much more of a hassle without it. And so when Quinn and I started working together at Palantir, he had also used various code search engines in open source over the years. And it was just a pain point that we both felt, both working on code at Palantir and also working within Palantir's clients, which were a lot of Fortune 500 companies, large financial institutions, folks like that. And if anything, the pains they felt in dealing with large complex code bases made our pain points feel small by comparison. So that was really the impetus for starting Sourcegraph. [00:02:42]Swyx: Yeah, excellent. Steve, you famously worked at Amazon. And you've told many, many stories. I want every single listener of Latent Space to check out Steve's YouTube because he effectively had a podcast that you didn't tell anyone about or something. You just hit record and just went on a few rants. I'm always here for your Stevie rants. And then you moved to Google, where you also had some interesting thoughts on just the overall Google culture versus Amazon. You joined Grab as head of eng for a couple of years. I'm from Singapore, so I have actually personally used a lot of Grab's features. And it was very interesting to see you talk so highly of Grab's engineering and sort of overall prospects. [00:03:21]Steve: Because as a customer, it sucked? [00:03:22]Swyx: Yeah, no, it's just like, being from a smaller country, you never see anyone from our home country being on a global stage or talked about as a startup that people admire or look up to, like on the league that you, with all your legendary experience, would consider equivalent. Yeah. [00:03:41]Steve: Yeah, no, absolutely. They actually, they didn't even know that they were as good as they were, in a sense. They started hiring a bunch of people from Silicon Valley to come in and sort of like fix it. And we came in and we were like, Oh, we could have been a little better operational excellence and stuff. But by and large, they're really sharp. The only thing about Grab is that they get criticized a lot for being too westernized. Oh, by who? By Singaporeans who don't want to work there. [00:04:06]Swyx: Okay. I guess I'm biased because I'm here, but I don't see that as a problem. If anything, they've had their success because they were more westernized than the Sanders Singaporean tech company. [00:04:15]Steve: I mean, they had their success because they are laser focused. They copy to Amazon. I mean, they're executing really, really, really well for a giant. I was on a slack with 2,500 engineers. It was like this giant waterfall that you could dip your toe into. You'd never catch up. Actually, the AI summarizers would have been really helpful there. But yeah, no, I think Grab is successful because they're just out there with their sleeves rolled up, just making it happen. [00:04:43]Swyx: And for those who don't know, it's not just like Uber of Southeast Asia, it's also a super app. PayPal Plus. [00:04:48]Steve: Yeah. [00:04:49]Swyx: In the way that super apps don't exist in the West. It's one of the enduring mysteries of B2C that super apps work in the East and don't work in the West. We just don't understand it. [00:04:57]Beyang: Yeah. [00:04:58]Steve: It's just kind of curious. They didn't work in India either. And it was primarily because of bandwidth reasons and smaller phones. [00:05:03]Swyx: That should change now. It should. [00:05:05]Steve: And maybe we'll see a super app here. [00:05:08]Swyx: You retired-ish? I did. You retired-ish on your own video game? Mm-hmm. Any fun stories about that? And that's also where you discovered some need for code search, right? Mm-hmm. [00:05:16]Steve: Sure. A need for a lot of stuff. Better programming languages, better databases. Better everything. I mean, I started in like 95, right? Where there was kind of nothing. Yeah. Yeah. [00:05:24]Beyang: I just want to say, I remember when you first went to Grab because you wrote that blog post talking about why you were excited about it, about like the expanding Asian market. And our reaction was like, oh, man, how did we miss stealing it with you? [00:05:36]Swyx: Hiring you. [00:05:37]Beyang: Yeah. [00:05:38]Steve: I was like, miss that. [00:05:39]Swyx: Tell that story. So how did this happen? Right? So you were inspired by Grok. [00:05:44]Beyang: I guess the backstory from my point of view is I had used code search and Grok while at Google, but I didn't actually know that it was connected to you, Steve. I knew you from your blog posts, which were always excellent, kind of like inside, very thoughtful takes from an engineer's perspective on some of the challenges facing tech companies and tech culture and that sort of thing. But my first introduction to you within the context of code intelligence, code understanding was I watched a talk that you gave, I think at Stanford, about Grok when you're first building it. And that was very eye opening. I was like, oh, like that guy, like the guy who, you know, writes the extremely thoughtful ranty like blog posts also built that system. And so that's how I knew, you know, you were involved in that. And then, you know, we always wanted to hire you, but never knew quite how to approach you or, you know, get that conversation started. [00:06:34]Steve: Well, we got introduced by Max, right? Yeah. It was temporal. Yeah. Yeah. I mean, it was a no brainer. They called me up and I had noticed when Sourcegraph had come out. Of course, when they first came out, I had this dagger of jealousy stabbed through me piercingly, which I remember because I am not a jealous person by any means, ever. But boy, I was like, but I was kind of busy, right? And just one thing led to another. I got sucked back into the ads vortex and whatever. So thank God Sourcegraph actually kind of rescued me. [00:07:05]Swyx: Here's a chance to build DevTools. Yeah. [00:07:08]Steve: That's the best. DevTools are the best. [00:07:10]Swyx: Cool. Well, so that's the overall intro. I guess we can get into Cody. Is there anything else that like people should know about you before we get started? [00:07:18]Steve: I mean, everybody knows I'm a musician. I can juggle five balls. [00:07:24]Swyx: Five is good. Five is good. I've only ever managed three. [00:07:27]Steve: Five is hard. Yeah. And six, a little bit. [00:07:30]Swyx: Wow. [00:07:31]Beyang: That's impressive. [00:07:32]Alessio: So yeah, to jump into Sourcegraph, this has been a company 10 years in the making. And as Sean said, now you're at the right place. Phase two. Now, exactly. You spent 10 years collecting all this code, indexing, making it easy to surface it. Yeah. [00:07:47]Swyx: And also learning how to work with enterprises and having them trust you with their code bases. Yeah. [00:07:52]Alessio: Because initially you were only doing on-prem, right? Like a lot of like VPC deployments. [00:07:55]Beyang: So in the very early days, we're cloud only. But the first major customers we landed were all on-prem, self-hosted. And that was, I think, related to the nature of the problem that we're solving, which becomes just like a critical, unignorable pain point once you're above like 100 devs or so. [00:08:11]Alessio: Yeah. And now Cody is going to be GA by the time this releases. So congrats to your future self for launching this in two weeks. Can you give a quick overview of just what Cody is? I think everybody understands that it's a AI coding agent, but a lot of companies say they have a AI coding agent. So yeah, what does Cody do? How do people interface with it? [00:08:32]Beyang: Yeah. So how is it different from the like several dozen other AI coding agents that exist in the market now? When we thought about building a coding assistant that would do things like code generation and question answering about your code base, I think we came at it from the perspective of, you know, we've spent the past decade building the world's best code understanding engine for human developers, right? So like it's kind of your guide as a human dev if you want to go and dive into a large complex code base. And so our intuition was that a lot of the context that we're providing to human developers would also be useful context for AI developers to consume. And so in terms of the feature set, Cody is very similar to a lot of other assistants. It does inline autocompletion. It does code base aware chat. It does specific commands that automate, you know, tasks that you might rather not want to do like generating unit tests or adding detailed documentation. But we think the core differentiator is really the quality of the context, which is hard to kind of describe succinctly. It's a bit like saying, you know, what's the difference between Google and Alta Vista? There's not like a quick checkbox list of features that you can rattle off, but it really just comes down to all the attention and detail that we've paid to making that context work well and be high quality and fast for human devs. We're now kind of plugging into the AI coding assistant as well. Yeah. [00:09:53]Steve: I mean, just to add my own perspective on to what Beyang just described, RAG is kind of like a consultant that the LLM has available, right, that knows about your code. RAG provides basically a bridge to a lookup system for the LLM, right? Whereas fine tuning would be more like on the job training for somebody. If the LLM is a person, you know, and you send them to a new job and you do on the job training, that's what fine tuning is like, right? So tuned to our specific task. You're always going to need that expert, even if you get the on the job training, because the expert knows your particular code base, your task, right? That expert has to know your code. And there's a chicken and egg problem because, right, you know, we're like, well, I'm going to ask the LLM about my code, but first I have to explain it, right? It's this chicken and egg problem. That's where RAG comes in. And we have the best consultants, right? The best assistant who knows your code. And so when you sit down with Cody, right, what Beyang said earlier about going to Google and using code search and then starting to feel like without it, his job was super tedious. Once you start using these, do you guys use coding assistants? [00:10:53]Swyx: Yeah, right. [00:10:54]Steve: I mean, like we're getting to the point very quickly, right? Where you feel like almost like you're programming without the internet, right? Or something, you know, it's like you're programming back in the nineties without the coding assistant. Yeah. Hopefully that helps for people who have like no idea about coding systems, what they are. [00:11:09]Swyx: Yeah. [00:11:10]Alessio: I mean, going back to using them, we had a lot of them on the podcast already. We had Cursor, we have Codium and Codium, very similar names. [00:11:18]Swyx: Yeah. Find, and then of course there's Copilot. [00:11:22]Alessio: You had a Copilot versus Cody blog post, and I think it really shows the context improvement. So you had two examples that stuck with me. One was, what does this application do? And the Copilot answer was like, oh, it uses JavaScript and NPM and this. And it's like, but that's not what it does. You know, that's what it's built with. Versus Cody was like, oh, these are like the major functions. And like, these are the functionalities and things like that. And then the other one was, how do I start this up? And Copilot just said NPM start, even though there was like no start command in the package JSON, but you know, most collapse, right? Most projects use NPM start. So maybe this does too. How do you think about open source models? Because Copilot has their own private thing. And I think you guys use Starcoder, if I remember right. Yeah, that's correct. [00:12:09]Beyang: I think Copilot uses some variant of Codex. They're kind of cagey about it. I don't think they've like officially announced what model they use. [00:12:16]Swyx: And I think they use a range of models based on what you're doing. Yeah. [00:12:19]Beyang: So everyone uses a range of model. Like no one uses the same model for like inline completion versus like chat because the latency requirements for. Oh, okay. Well, there's fill in the middle. There's also like what the model's trained on. So like we actually had completions powered by Claude Instant for a while. And but you had to kind of like prompt hack your way to get it to output just the code and not like, hey, you know, here's the code you asked for, like that sort of text. So like everyone uses a range of models. We've kind of designed Cody to be like especially model, not agnostic, but like pluggable. So one of our kind of design considerations was like as the ecosystem evolves, we want to be able to integrate the best in class models, whether they're proprietary or open source into Cody because the pace of innovation in the space is just so quick. And I think that's been to our advantage. Like today, Cody uses Starcoder for inline completions. And with the benefit of the context that we provide, we actually show comparable completion acceptance rate metrics. It's kind of like the standard metric that folks use to evaluate inline completion quality. It's like if I show you a completion, what's the chance that you actually accept the completion versus you reject it? And so we're at par with Copilot, which is at the head of that industry right now. And we've been able to do that with the Starcoder model, which is open source and the benefit of the context fetching stuff that we provide. And of course, a lot of like prompt engineering and other stuff along the way. [00:13:40]Alessio: And Steve, you wrote a post called cheating is all you need about what you're building. And one of the points you made is that everybody's fighting on the same axis, which is better UI and the IDE, maybe like a better chat response. But data modes are kind of the most important thing. And you guys have like a 10 year old mode with all the data you've been collecting. How do you kind of think about what other companies are doing wrong, right? Like, why is nobody doing this in terms of like really focusing on RAG? I feel like you see so many people. Oh, we just got a new model. It's like a bit human eval. And it's like, well, but maybe like that's not what we should really be doing, you know? Like, do you think most people underestimate the importance of like the actual RAG in code? [00:14:21]Steve: I think that people weren't doing it much. It wasn't. It's kind of at the edges of AI. It's not in the center. I know that when ChatGPT launched, so within the last year, I've heard a lot of rumblings from inside of Google, right? Because they're undergoing a huge transformation to try to, you know, of course, get into the new world. And I heard that they told, you know, a bunch of teams to go and train their own models or fine tune their own models, right? [00:14:43]Swyx: Both. [00:14:43]Steve: And, you know, it was a s**t show. Nobody knew how to do it. They launched two coding assistants. One was called Code D with an EY. And then there was, I don't know what happened in that one. And then there's Duet, right? Google loves to compete with themselves, right? They do this all the time. And they had a paper on Duet like from a year ago. And they were doing exactly what Copilot was doing, which was just pulling in the local context, right? But fundamentally, I thought of this because we were talking about the splitting of the [00:15:10]Swyx: models. [00:15:10]Steve: In the early days, it was the LLM did everything. And then we realized that for certain use cases, like completions, that a different, smaller, faster model would be better. And that fragmentation of models, actually, we expected to continue and proliferate, right? Because we are fundamentally, we're a recommender engine right now. Yeah, we're recommending code to the LLM. We're saying, may I interest you in this code right here so that you can answer my question? [00:15:34]Swyx: Yeah? [00:15:34]Steve: And being good at recommender engine, I mean, who are the best recommenders, right? There's YouTube and Spotify and, you know, Amazon or whatever, right? Yeah. [00:15:41]Swyx: Yeah. [00:15:41]Steve: And they all have many, many, many, many, many models, right? For all fine-tuned for very specific, you know. And that's where we're heading in code, too. Absolutely. [00:15:50]Swyx: Yeah. [00:15:50]Alessio: We just did an episode we released on Wednesday, which we said RAG is like Rexis or like LLMs. You're basically just suggesting good content. [00:15:58]Swyx: It's like what? Recommendations. [00:15:59]Beyang: Recommendations. [00:16:00]Alessio: Oh, got it. [00:16:01]Steve: Yeah, yeah, yeah. [00:16:02]Swyx: So like the naive implementation of RAG is you embed everything, throw it in a vector database, you embed your query, and then you find the nearest neighbors, and that's your RAG. But actually, you need to rank it. And actually, you need to make sure there's sample diversity and that kind of stuff. And then you're like slowly gradient dissenting yourself towards rediscovering proper Rexis, which has been traditional ML for a long time. But like approaching it from an LLM perspective. Yeah. [00:16:24]Beyang: I almost think of it as like a generalized search problem because it's a lot of the same things. Like you want your layer one to have high recall and get all the potential things that could be relevant. And then there's typically like a layer two re-ranking mechanism that bumps up the precision and tries to get the relevant stuff to the top of the results list. [00:16:43]Swyx: Have you discovered that ranking matters a lot? Oh, yeah. So the context is that I think a lot of research shows that like one, context utilization matters based on model. Like GPT uses the top of the context window, and then apparently Claude uses the bottom better. And it's lossy in the middle. Yeah. So ranking matters. No, it really does. [00:17:01]Beyang: The skill with which models are able to take advantage of context is always going to be dependent on how that factors into the impact on the training loss. [00:17:10]Swyx: Right? [00:17:10]Beyang: So like if you want long context window models to work well, then you have to have a ton of data where it's like, here's like a billion lines of text. And I'm going to ask a question about like something that's like, you know, embedded deeply into it and like, give me the right answer. And unless you have that training set, then of course, you're going to have variability in terms of like where it attends to. And in most kind of like naturally occurring data, the thing that you're talking about right now, the thing I'm asking you about is going to be something that we talked about recently. [00:17:36]Swyx: Yeah. [00:17:36]Steve: Did you really just say gradient dissenting yourself? Actually, I love that it's entered the casual lexicon. Yeah, yeah, yeah. [00:17:44]Swyx: My favorite version of that is, you know, how we have to p-hack papers. So, you know, when you throw humans at the problem, that's called graduate student dissent. That's great. It's really awesome. [00:17:54]Alessio: I think the other interesting thing that you have is this inline assist UX that I wouldn't say async, but like it works while you can also do work. So you can ask Cody to make changes on a code block and you can still edit the same file at the same time. [00:18:07]Swyx: Yeah. [00:18:07]Alessio: How do you see that in the future? Like, do you see a lot of Cody's running together at the same time? Like, how do you validate also that they're not messing each other up as they make changes in the code? And maybe what are the limitations today? And what do you think about where the attack is going? [00:18:21]Steve: I want to start with a little history and then I'm going to turn it over to Bian, all right? So we actually had this feature in the very first launch back in June. Dominic wrote it. It was called nonstop Cody. And you could have multiple, basically, LLM requests in parallel modifying your source [00:18:37]Swyx: file. [00:18:37]Steve: And he wrote a bunch of code to handle all of the diffing logic. And you could see the regions of code that the LLM was going to change, right? And he was showing me demos of it. And it just felt like it was just a little before its time, you know? But a bunch of that stuff, that scaffolding was able to be reused for where we're inline [00:18:56]Swyx: sitting today. [00:18:56]Steve: How would you characterize it today? [00:18:58]Beyang: Yeah, so that interface has really evolved from a, like, hey, general purpose, like, request anything inline in the code and have the code update to really, like, targeted features, like, you know, fix the bug that exists at this line or request a very specific [00:19:13]Swyx: change. [00:19:13]Beyang: And the reason for that is, I think, the challenge that we ran into with inline fixes, and we do want to get to the point where you could just fire and forget and have, you know, half a dozen of these running in parallel. But I think we ran into the challenge early on that a lot of people are running into now when they're trying to construct agents, which is the reliability of, you know, working code generation is just not quite there yet in today's language models. And so that kind of constrains you to an interaction where the human is always, like, in the inner loop, like, checking the output of each response. And if you want that to work in a way where you can be asynchronous, you kind of have to constrain it to a domain where today's language models can generate reliable code well enough. So, you know, generating unit tests, that's, like, a well-constrained problem. Or fixing a bug that shows up as, like, a compiler error or a test error, that's a well-constrained problem. But the more general, like, hey, write me this class that does X, Y, and Z using the libraries that I have, that is not quite there yet, even with the benefit of really good context. Like, it definitely moves the needle a lot, but we're not quite there yet to the point where you can just fire and forget. And I actually think that this is something that people don't broadly appreciate yet, because I think that, like, everyone's chasing this dream of agentic execution. And if we're to really define that down, I think it implies a couple things. You have, like, a multi-step process where each step is fully automated. We don't have to have a human in the loop every time. And there's also kind of like an LM call at each stage or nearly every stage in that [00:20:45]Swyx: chain. [00:20:45]Beyang: Based on all the work that we've done, you know, with the inline interactions, with kind of like general Codyfeatures for implementing longer chains of thought, we're actually a little bit more bearish than the average, you know, AI hypefluencer out there on the feasibility of agents with purely kind of like transformer-based models. To your original question, like, the inline interactions with CODI, we actually constrained it to be more targeted, like, you know, fix the current error or make this quick fix. I think that that does differentiate us from a lot of the other tools on the market, because a lot of people are going after this, like, shnazzy, like, inline edit interaction, whereas I think where we've moved, and this is based on the user feedback that we've gotten, it's like that sort of thing, it demos well, but when you're actually coding day to day, you don't want to have, like, a long chat conversation inline with the code base. That's a waste of time. You'd rather just have it write the right thing and then move on with your life or not have to think about it. And that's what we're trying to work towards. [00:21:37]Steve: I mean, yeah, we're not going in the agent direction, right? I mean, I'll believe in agents when somebody shows me one that works. Yeah. Instead, we're working on, you know, sort of solidifying our strength, which is bringing the right context in. So new context sources, ways for you to plug in your own context, ways for you to control or influence the context, you know, the mixing that happens before the request goes out, etc. And there's just so much low-hanging fruit left in that space that, you know, agents seems like a little bit of a boondoggle. [00:22:03]Beyang: Just to dive into that a little bit further, like, I think, you know, at a very high level, what do people mean when they say agents? They really mean, like, greater automation, fully automated, like, the dream is, like, here's an issue, go implement that. And I don't have to think about it as a human. And I think we are working towards that. Like, that is the eventual goal. I think it's specifically the approach of, like, hey, can we have a transformer-based LM alone be the kind of, like, backbone or the orchestrator of these agentic flows? Where we're a little bit more bearish today. [00:22:31]Swyx: You want the human in the loop. [00:22:32]Beyang: I mean, you kind of have to. It's just a reality of the behavior of language models that are purely, like, transformer-based. And I think that's just like a reflection of reality. And I don't think people realize that yet. Because if you look at the way that a lot of other AI tools have implemented context fetching, for instance, like, you see this in the Copilot approach, where if you use, like, the at-workspace thing that supposedly provides, like, code-based level context, it has, like, an agentic approach where you kind of look at how it's behaving. And it feels like they're making multiple requests to the LM being like, what would you do in this case? Would you search for stuff? What sort of files would you gather? Go and read those files. And it's like a multi-hop step, so it takes a long while. It's also non-deterministic. Because any sort of, like, LM invocation, it's like a dice roll. And then at the end of the day, the context it fetches is not that good. Whereas our approach is just like, OK, let's do some code searches that make sense. And then maybe, like, crawl through the reference graph a little bit. That is fast. That doesn't require any sort of LM invocation at all. And we can pull in much better context, you know, very quickly. So it's faster. [00:23:37]Swyx: It's more reliable. [00:23:37]Beyang: It's deterministic. And it yields better context quality. And so that's what we think. We just don't think you should cargo cult or naively go like, you know, agents are the [00:23:46]Swyx: future. [00:23:46]Beyang: Let's just try to, like, implement agents on top of the LM that exists today. I think there are a couple of other technologies or approaches that need to be refined first before we can get into these kind of, like, multi-stage, fully automated workflows. [00:24:00]Swyx: It makes sense. You know, we're very much focused on developer inner loop right now. But you do see things eventually moving towards developer outer loop. Yeah. So would you basically say that they're tackling the agent's problem that you don't want to tackle? [00:24:11]Beyang: No, I would say at a high level, we are after maybe, like, the same high level problem, which is like, hey, I want some code written. I want to develop some software and can automate a system. Go build that software for me. I think the approaches might be different. So I think the analogy in my mind is, I think about, like, the AI chess players. Coding, in some senses, I mean, it's similar and dissimilar to chess. I think one question I ask is, like, do you think producing code is more difficult than playing chess or less difficult than playing chess? More. [00:24:41]Swyx: I think more. [00:24:41]Beyang: Right. And if you look at the best AI chess players, like, yes, you can use an LLM to play chess. Like, people have showed demos where it's like, oh, like, yeah, GPT-4 is actually a pretty decent, like, chess move suggester. Right. But you would never build, like, a best in class chess player off of GPT-4 alone. [00:24:57]Swyx: Right. [00:24:57]Beyang: Like, the way that people design chess players is that you have kind of like a search space and then you have a way to explore that search space efficiently. There's a bunch of search algorithms, essentially. We were doing tree search in various ways. And you can have heuristic functions, which might be powered by an LLM. [00:25:12]Swyx: Right. [00:25:12]Beyang: Like, you might use an LLM to generate proposals in that space that you can efficiently explore. But the backbone is still this kind of more formalized tree search based approach rather than the LLM itself. And so I think my high level intuition is that, like, the way that we get to more reliable multi-step workflows that do things beyond, you know, generate unit test, it's really going to be like a search based approach where you use an LLM as kind of like an advisor or a proposal function, sort of your heuristic function, like the ASTAR search algorithm. But it's probably not going to be the thing that is the backbone, because I guess it's not the right tool for that. Yeah. [00:25:50]Swyx: I can see yourself kind of thinking through this, but not saying the words, the sort of philosophical Peter Norvig type discussion. Maybe you want to sort of introduce that in software. Yeah, definitely. [00:25:59]Beyang: So your listeners are savvy. They're probably familiar with the classic like Chomsky versus Norvig debate. [00:26:04]Swyx: No, actually, I wanted, I was prompting you to introduce that. Oh, got it. [00:26:08]Beyang: So, I mean, if you look at the history of artificial intelligence, right, you know, it goes way back to, I don't know, it's probably as old as modern computers, like 50s, 60s, 70s. People are debating on like, what is the path to producing a sort of like general human level of intelligence? And kind of two schools of thought that emerged. One is the Norvig school of thought, which roughly speaking includes large language models, you know, regression, SVN, basically any model that you kind of like learn from data. And it's like data driven. Most of machine learning would fall under this umbrella. And that school of thought says like, you know, just learn from the data. That's the approach to reaching intelligence. And then the Chomsky approach is more things like compilers and parsers and formal systems. So basically like, let's think very carefully about how to construct a formal, precise system. And that will be the approach to how we build a truly intelligent system. I think Lisp was invented so that you could create like rules-based systems that you would call AI. As a language. Yeah. And for a long time, there was like this debate, like there's certain like AI research labs that were more like, you know, in the Chomsky camp and others that were more in the Norvig camp. It's a debate that rages on today. And I feel like the consensus right now is that, you know, Norvig definitely has the upper hand right now with the advent of LMs and diffusion models and all the other recent progress in machine learning. But the Chomsky-based stuff is still really useful in my view. I mean, it's like parsers, compilers, basically a lot of the stuff that provides really good context. It provides kind of like the knowledge graph backbone that you want to explore with your AI dev tool. Like that will come from kind of like Chomsky-based tools like compilers and parsers. It's a lot of what we've invested in in the past decade at Sourcegraph and what you build with Grok. Basically like these formal systems that construct these very precise knowledge graphs that are great context providers and great kind of guard rails enforcers and kind of like safety checkers for the output of a more kind of like data-driven, fuzzier system that uses like the Norvig-based models. [00:28:03]Steve: Jang was talking about this stuff like it happened in the middle ages. Like, okay, so when I was in college, I was in college learning Lisp and prologue and planning and all the deterministic Chomsky approaches to AI. And I was there when Norvig basically declared it dead. I was there 3,000 years ago when Norvig and Chomsky fought on the volcano. When did he declare it dead? [00:28:26]Swyx: What do you mean he declared it dead? [00:28:27]Steve: It was like late 90s. [00:28:29]Swyx: Yeah. [00:28:29]Steve: When I went to Google, Peter Norvig was already there. He had basically like, I forget exactly where. It was some, he's got so many famous short posts, you know, amazing. [00:28:38]Swyx: He had a famous talk, the unreasonable effectiveness of data. Yeah. [00:28:41]Steve: Maybe that was it. But at some point, basically, he basically convinced everybody that deterministic approaches had failed and that heuristic-based, you know, data-driven statistical approaches, stochastic were better. [00:28:52]Swyx: Yeah. [00:28:52]Steve: The primary reason I can tell you this, because I was there, was that, was that, well, the steam-powered engine, no. The reason was that the deterministic stuff didn't scale. [00:29:06]Swyx: Yeah. Right. [00:29:06]Steve: They're using prologue, man, constraint systems and stuff like that. Well, that was a long time ago, right? Today, actually, these Chomsky-style systems do scale. And that's, in fact, exactly what Sourcegraph has built. Yeah. And so we have a very unique, I love the framing that Bjong's made, that the marriage of the Chomsky and the Norvig, you know, sort of models, you know, conceptual models, because we, you know, we have both of them and they're both really important. And in fact, there, there's this really interesting, like, kind of overlap between them, right? Where like the AI or our graph or our search engine could potentially provide the right context for any given query, which is, of course, why ranking is important. But what we've really signed ourselves up for is an extraordinary amount of testing. [00:29:45]Swyx: Yeah. [00:29:45]Steve: Because in SWIGs, you were saying that, you know, GPT-4 tends to the front of the context window and maybe other LLMs to the back and maybe, maybe the LLM in the middle. [00:29:53]Swyx: Yeah. [00:29:53]Steve: And so that means that, you know, if we're actually like, you know, verifying whether we, you know, some change we've made has improved things, we're going to have to test putting it at the beginning of the window and at the end of the window, you know, and maybe make the right decision based on the LLM that you've chosen. Which some of our competitors, that's a problem that they don't have, but we meet you, you know, where you are. Yeah. And we're, just to finish, we're writing tens of thousands. We're generating tests, you know, fill in the middle type tests and things. And then using our graph to basically sort of fine tune Cody's behavior there. [00:30:20]Swyx: Yeah. [00:30:21]Beyang: I also want to add, like, I have like an internal pet name for this, like kind of hybrid architecture that I'm trying to make catch on. Maybe I'll just say it here. Just saying it publicly kind of makes it more real. But like, I call the architecture that we've developed the Normsky architecture. [00:30:36]Swyx: Yeah. [00:30:36]Beyang: I mean, it's obviously a portmanteau of Norvig and Chomsky, but the acronym, it stands for non-agentic, rapid, multi-source code intelligence. So non-agentic because... Rolls right off the tongue. And Normsky. But it's non-agentic in the sense that like, we're not trying to like pitch you on kind of like agent hype, right? Like it's the things it does are really just developer tools developers have been using for decades now, like parsers and really good search indexes and things like that. Rapid because we place an emphasis on speed. We don't want to sit there waiting for kind of like multiple LLM requests to return to complete a simple user request. Multi-source because we're thinking broadly about what pieces of information and knowledge are useful context. So obviously starting with things that you can search in your code base, and then you add in the reference graph, which kind of like allows you to crawl outward from those initial results. But then even beyond that, you know, sources of information, like there's a lot of knowledge that's embedded in docs, in PRDs or product specs, in your production logging system, in your chat, in your Slack channel, right? Like there's so much context is embedded there. And when you're a human developer, and you're trying to like be productive in your code base, you're going to go to all these different systems to collect the context that you need to figure out what code you need to write. And I don't think the AI developer will be any different. It will need to pull context from all these different sources. So we're thinking broadly about how to integrate these into Codi. We hope through kind of like an open protocol that like others can extend and implement. And this is something else that should be accessible by December 14th in kind of like a preview stage. But that's really about like broadening this notion of the code graph beyond your Git repository to all the other sources where technical knowledge and valuable context can live. [00:32:21]Steve: Yeah, it becomes an artifact graph, right? It can link into your logs and your wikis and any data source, right? [00:32:27]Alessio: How do you guys think about the importance of, it's almost like data pre-processing in a way, which is bring it all together, tie it together, make it ready. Any thoughts on how to actually make that good? Some of the innovation you guys have made. [00:32:40]Steve: We talk a lot about the context fetching, right? I mean, there's a lot of ways you could answer this question. But, you know, we've spent a lot of time just in this podcast here talking about context fetching. But stuffing the context into the window is, you know, the bin packing problem, right? Because the window is not big enough, and you've got more context than you can fit. You've got a ranker maybe. But what is that context? Is it a function that was returned by an embedding or a graph call or something? Do you need the whole function? Or do you just need, you know, the top part of the function, this expression here, right? You know, so that art, the golf game of trying to, you know, get each piece of context down into its smallest state, possibly even summarized by another model, right, before it even goes to the LLM, becomes this is the game that we're in, yeah? And so, you know, recursive summarization and all the other techniques that you got to use to like stuff stuff into that context window become, you know, critically important. And you have to test them across every configuration of models that you could possibly need. [00:33:32]Beyang: I think data preprocessing is probably the like unsexy, way underappreciated secret to a lot of the cool stuff that people are shipping today. Whether you're doing like RAG or fine tuning or pre-training, like the preprocessing step matters so much because it's basically garbage in, garbage out, right? Like if you're feeding in garbage to the model, then it's going to output garbage. Concretely, you know, for code RAG, if you're not doing some sort of like preprocessing that takes advantage of a parser and is able to like extract the key components of a particular file of code, you know, separate the function signature from the body, from the doc string, what are you even doing? Like that's like table stakes. It opens up so much more possibilities with which you can kind of like tune your system to take advantage of the signals that come from those different parts of the code. Like we've had a tool, you know, since computers were invented that understands the structure of source code to a hundred percent precision. The compiler knows everything there is to know about the code in terms of like structure. Like why would you not want to use that in a system that's trying to generate code, answer questions about code? You shouldn't throw that out the window just because now we have really good, you know, data-driven models that can do other things. [00:34:44]Steve: Yeah. When I called it a data moat, you know, in my cheating post, a lot of people were confused, you know, because data moat sort of sounds like data lake because there's data and water and stuff. I don't know. And so they thought that we were sitting on this giant mountain of data that we had collected, but that's not what our data moat is. It's really a data pre-processing engine that can very quickly and scalably, like basically dissect your entire code base in a very small, fine-grained, you know, semantic unit and then serve it up. Yeah. And so it's really, it's not a data moat. It's a data pre-processing moat, I guess. [00:35:15]Beyang: Yeah. If anything, we're like hypersensitive to customer data privacy requirements. So it's not like we've taken a bunch of private data and like, you know, trained a generally available model. In fact, exactly the opposite. A lot of our customers are choosing Cody over Copilot and other competitors because we have an explicit guarantee that we don't do any of that. And that we've done that from day one. Yeah. I think that's a very real concern in today's day and age, because like if your proprietary IP finds its way into the training set of any model, it's very easy both to like extract that knowledge from the model and also use it to, you know, build systems that kind of work on top of the institutional knowledge that you've built up. [00:35:52]Alessio: About a year ago, I wrote a post on LLMs for developers. And one of the points I had was maybe the depth of like the DSL. I spent most of my career writing Ruby and I love Ruby. It's so nice to use, but you know, it's not as performant, but it's really easy to read, right? And then you look at other languages, maybe they're faster, but like they're more verbose, you know? And when you think about efficiency of the context window, that actually matters. [00:36:15]Swyx: Yeah. [00:36:15]Alessio: But I haven't really seen a DSL for models, you know? I haven't seen like code being optimized to like be easier to put in a model context. And it seems like your pre-processing is kind of doing that. Do you see in the future, like the way we think about the DSL and APIs and kind of like service interfaces be more focused on being context friendly, where it's like maybe it's harder to read for the human, but like the human is never going to write it anyway. We were talking on the Hacks podcast. There are like some data science things like spin up the spandex, like humans are never going to write again because the models can just do very easily. Yeah, curious to hear your thoughts. [00:36:51]Steve: Well, so DSLs, they involve, you know, writing a grammar and a parser and they're like little languages, right? We do them that way because, you know, we need them to compile and humans need to be able to read them and so on. The LLMs don't need that level of structure. You can throw any pile of crap at them, you know, more or less unstructured and they'll deal with it. So I think that's why a DSL hasn't emerged for sort of like communicating with the LLM or packaging up the context or anything. Maybe it will at some point, right? We've got, you know, tagging of context and things like that that are sort of peeking into DSL territory, right? But your point on do users, you know, do people have to learn DSLs like regular expressions or, you know, pick your favorite, right? XPath. I think you're absolutely right that the LLMs are really, really good at that. And I think you're going to see a lot less of people having to slave away learning these things. They just have to know the broad capabilities and the LLM will take care of the rest. [00:37:42]Swyx: Yeah, I'd agree with that. [00:37:43]Beyang: I think basically like the value profit of DSL is that it makes it easier to work with a lower level language, but at the expense of introducing an abstraction layer. And in many cases today, you know, without the benefit of AI cogeneration, like that totally worth it, right? With the benefit of AI cogeneration, I mean, I don't think all DSLs will go away. I think there's still, you know, places where that trade-off is going to be worthwhile. But it's kind of like how much of source code do you think is going to be generated through natural language prompting in the future? Because in a way, like any programming language is just a DSL on top of assembly, right? And so if people can do that, then yeah, like maybe for a large portion of the code [00:38:21]Swyx: that's written, [00:38:21]Beyang: people don't actually have to understand the DSL that is Ruby or Python or basically any other programming language that exists. [00:38:28]Steve: I mean, seriously, do you guys ever write SQL queries now without using a model of some sort? At least a draft. [00:38:34]Swyx: Yeah, right. [00:38:36]Steve: And so we have kind of like, you know, past that bridge, right? [00:38:39]Alessio: Yeah, I think like to me, the long-term thing is like, is there ever going to be, you don't actually see the code, you know? It's like, hey, the basic thing is like, hey, I need a function to some two numbers and that's it. I don't need you to generate the code. [00:38:53]Steve: And the following question, do you need the engineer or the paycheck? [00:38:56]Swyx: I mean, right? [00:38:58]Alessio: That's kind of the agent's discussion in a way where like you cannot automate the agents, but like slowly you're getting more of the atomic units of the work kind of like done. I kind of think of it as like, you know, [00:39:09]Beyang: do you need a punch card operator to answer that for you? And so like, I think we're still going to have people in the role of a software engineer, but the portion of time they spend on these kinds of like low-level, tedious tasks versus the higher level, more creative tasks is going to shift. [00:39:23]Steve: No, I haven't used punch cards. [00:39:25]Swyx: Yeah, I've been talking about like, so we kind of made this podcast about the sort of rise of the AI engineer. And like the first step is the AI enhanced engineer. That is that software developer that is no longer doing these routine, boilerplate-y type tasks, because they're just enhanced by tools like yours. So you mentioned OpenCodeGraph. I mean, that is a kind of DSL maybe, and because we're releasing this as you go GA, you hope for other people to take advantage of that? [00:39:52]Beyang: Oh yeah, I would say so OpenCodeGraph is not a DSL. It's more of a protocol. It's basically like, hey, if you want to make your system, whether it's, you know, chat or logging or whatever accessible to an AI developer tool like Cody, here's kind of like the schema by which you can provide that context and offer hints. So I would, you know, comparisons like LSP obviously did this for kind of like standard code intelligence. It's kind of like a lingua franca for providing fine references and codefinition. There's kind of like analogs to that. There might be also analogs to kind of the original OpenAI, kind of like plugins, API. There's all this like context out there that might be useful for an LM-based system to consume. And so at a high level, what we're trying to do is define a common language for context providers to provide context to other tools in the software development lifecycle. Yeah. Do you have any critiques of LSP, by the way, [00:40:42]Swyx: since like this is very much, very close to home? [00:40:45]Steve: One of the authors wrote a really good critique recently. Yeah. I don't think I saw that. Yeah, yeah. LSP could have been better. It just came out a couple of weeks ago. It was a good article. [00:40:54]Beyang: Yeah. I think LSP is great. Like for what it did for the developer ecosystem, it was absolutely fantastic. Like nowadays, like it's much easier now to get code navigation up and running in a bunch of editors by speaking this protocol. I think maybe the interesting question is like looking at the different design decisions comparing LSP basically with Kythe. Because Kythe has more of a... How would you describe it? [00:41:18]Steve: A storage format. [00:41:20]Beyang: I think the critique of LSP from a Kythe point of view would be like with LSP, you don't actually have an actual symbolic model of the code. It's not like LSP models like, hey, this function calls this other function. LSP is all like range-based. Like, hey, your cursor's at line 32, column 1. [00:41:35]Swyx: Yeah. [00:41:35]Beyang: And that's the thing you feed into the language server. And then it's like, okay, here's the range that you should jump to if you click on that range. So it kind of is intentionally ignorant of the fact that there's a thing called a reference underneath your cursor, and that's linked to a symbol definition. [00:41:49]Steve: Well, actually, that's the worst example you could have used. You're right. But that's the one thing that it actually did bake in is following references. [00:41:56]Swyx: Sure. [00:41:56]Steve: But it's sort of hardwired. [00:41:58]Swyx: Yeah. [00:41:58]Steve: Whereas Kythe attempts to model [00:42:00]Beyang: like all these things explicitly. [00:42:02]Swyx: And so... [00:42:02]Steve: Well, so LSP is a protocol, right? And so Google's internal protocol is gRPC-based. And it's a different approach than LSP. It's basically you make a heavy query to the back end, and you get a lot of data back, and then you render the whole page, you know? So we've looked at LSP, and we think that it's a little long in the tooth, right? I mean, it's a great protocol, lots and lots of support for it. But we need to push into the domain of exposing the intelligence through the protocol. Yeah. [00:42:29]Beyang: And so I would say we've developed a protocol of our own called Skip, which is at a very high level trying to take some of the good ideas from LSP and from Kythe and merge that into a system that in the near term is useful for Sourcegraph, but I think in the long term, we hope will be useful for the ecosystem. Okay, so here's what LSP did well. LSP, by virtue of being like intentionally dumb, dumb in air quotes, because I'm not like ragging on it, allowed language servers developers to kind of like bypass the hard problem of like modeling language semantics precisely. So like if all you want to do is jump to definition, you don't have to come up with like a universally unique naming scheme for each symbol, which is actually quite challenging because you have to think about like, okay, what's the top scope of this name? Is it the source code repository? Is it the package? Does it depend on like what package server you're fetching this from? Like whether it's the public one or the one inside your... Anyways, like naming is hard, right? And by just going from kind of like a location to location based approach, you basically just like throw that out the window. All I care about is jumping definition, just make that work. And you can make that work without having to deal with like all the complex global naming things. The limitation of that approach is that it's harder to build on top of that to build like a true knowledge graph. Like if you actually want a system that says like, okay, here's the web of functions and here's how they reference each other. And I want to incorporate that like semantic model of how the code operates or how the code relates to each other at like a static level. You can't do that with LSP because you have to deal with line ranges. And like concretely the pain point that we found in using LSP for source graph is like in order to do like a find references [00:44:04]Swyx: and then jump definitions, [00:44:04]Beyang: it's like a multi-hop process because like you have to jump to the range and then you have to find the symbol at that range. And it just adds a lot of latency and complexity of these operations where as a human, you're like, well, this thing clearly references this other thing. Why can't you just jump me to that? And I think that's the thing that Kaith does well. But then I think the issue that Kaith has had with adoption is because it is more sophisticated schema, I think. And so there's basically more things that you have to implement to get like a Kaith implementation up and running. I hope I'm not like, correct me if I'm wrong about any of this. [00:44:35]Steve: 100%, 100%. Kaith also has a problem, all these systems have the problem, even skip, or at least the way that we implemented the indexers, that they have to integrate with your build system in order to build that knowledge graph, right? Because you have to basically compile the code in a special mode to generate artifacts instead of binaries. And I would say, by the way, earlier I was saying that XREFs were in LSP, but it's actually, I was thinking of LSP plus LSIF. [00:44:58]Swyx: Yeah. That's another. [00:45:01]Steve: Which is actually bad. We can say that it's bad, right? [00:45:04]Steve: It's like skip or Kaith, it's supposed to be sort of a model serialization, you know, for the code graph, but it basically just does what LSP needs, the bare minimum. LSIF is basically if you took LSP [00:45:16]Beyang: and turned that into a serialization format. So like you build an index for language servers to kind of like quickly bootstrap from cold start. But it's a graph model [00:45:23]Steve: with all of the inconvenience of the API without an actual graph. And so, yeah. [00:45:29]Beyang: So like one of the things that we try to do with skip is try to capture the best of both worlds. So like make it easy to write an indexer, make the schema simple, but also model some of the more symbolic characteristics of the code that would allow us to essentially construct this knowledge graph that we can then make useful for both the human developer through SourceGraph and through the AI developer through Cody. [00:45:49]Steve: So anyway, just to finish off the graph comment, we've got a new graph, yeah, that's skip based. We call it BFG internally, right? It's a beautiful something graph. A big friendly graph. [00:46:00]Swyx: A big friendly graph. [00:46:01]Beyang: It's a blazing fast. [00:46:02]Steve: Blazing fast. [00:46:03]Swyx: Blazing fast graph. [00:46:04]Steve: And it is blazing fast, actually. It's really, really interesting. I should probably have to do a blog post about it to walk you through exactly how they're doing it. Oh, please. But it's a very AI-like iterative, you know, experimentation sort of approach. We're building a code graph based on all of our 10 years of knowledge about building code graphs, yeah? But we're building it quickly with zero configuration, and it doesn't have to integrate with your build. And through some magic tricks that we have. And so what just happens when you install the plugin, that it'll be there and indexing your code and providing that knowledge graph in the background without all that build system integration. This is a bit of secret sauce that we haven't really like advertised it very much lately. But I am super excited about it because what they do is they say, all right, you know, let's tackle function parameters today. Cody's not doing a very good job of completing function call arguments or function parameters in the definition, right? Yeah, we generate those thousands of tests, and then we can actually reuse those tests for the AI context as well. So fortunately, things are kind of converging on, we have, you know, half a dozen really, really good context sources, and we mix them all together. So anyway, BFG, you're going to hear more about it probably in the holidays? [00:47:12]Beyang: I think it'll be online for December 14th. We'll probably mention it. BFG is probably not the public name we're going to go with. I think we might call it like Graph Context or something like that. [00:47:20]Steve: We're officially calling it BFG. [00:47:22]Swyx: You heard it here first. [00:47:24]Beyang: BFG is just kind of like the working name. And so the impetus for BFG was like, if you look at like current AI inline code completion tools and the errors that they make, a lot of the errors that they make, even in kind of like the easy, like single line case, are essentially like type errors, right? Like you're trying to complete a function call and it suggests a variable that you defined earlier, but that variable is the wrong type. [00:47:47]Swyx: And that's the sort of thing [00:47:47]Beyang: where it's like a first year, like freshman CS student would not make that error, right? So like, why does the AI make that error? And the reason is, I mean, the AI is just suggesting things that are plausible without the context of the types or any other like broader files in the code. And so the kind of intuition here is like, why don't we just do the basic thing that like any baseline intelligent human developer would do, which is like click jump to definition, click some fine references and pull in that like Graph Context into the context window and then have it generate the completion. So like that's sort of like the MVP of what BFG was. And turns out that works really well. Like you can eliminate a lot of type errors that AI coding tools make just by pulling in that context. Yeah, but the graph is definitely [00:48:32]Steve: our Chomsky side. [00:48:33]Swyx: Yeah, exactly. [00:48:34]Beyang: So like this like Chomsky-Norvig thing, I think pops up in a bunch of differ

De talentvolle beachvolleyballers Joppe Van Langendonck en Kyan Vercauteren zijn wereldkampioen bij de U21. De spelers zelf hopen op meer investeringen om verder te kunnen groeien richting de Olympische Spelen van 2028. Voorzitter van Beachvolley België Dries Koekelkoren weet dat ons land al van ver komt.

Migratie en asiel. Het vorige kabinet viel erop, en ook deze verkiezingen is het een belangrijk thema. Prof. dr. Hein de Haas is internationaal toonaangevend migratie-onderzoeker en constateert dat politici links én rechts het thema inzetten voor electoraal gewin, zonder zich al te veel aan te trekken van de realiteit. In gesprek met dr Kelder geeft hij het emotionele debat een feitelijke lading en rekent af met hardnekkige migratie-mythes.  Het boek van Hein de Haas: https://www.spectrumboeken.nl/producten/hoe-migratie-echt-werkt-9789000386857 (https://www.spectrumboeken.nl/producten/hoe-migratie-echt-werkt-9789000386857)

President Biden is net terug uit Vietnam na deelname aan de G20. Maar wat is Amerika's rol in een veranderende wereld? Waarin verandert de wereld? Wat denkt Amerika daar zelf over? In deze aflevering speculeren we over de grote lijnen van Amerika's buitenlandpolitiek, een belangrijk thema in dit seizoen van Amerikaanse Toestanden. Heb je specifieke vragen of suggesties over dit thema voor toekomstige afleveringen? Stuur een email naar podcast@manusama.com of vind ons op Twitter/X: @KennethManusama of @dmdebruijn

Als Amerikaan kun je deze week niet om Zelenski en Oekraïne heen. Hij is in New York bij de Algemene Vergadering van de VN, hij is in Washington in het congres, hij is in het Witte Huis en in het Pentagon. En natuurlijk is hij op de tv en op de radio. Maar waar hij vorig jaar nog als held werd ontvangen moet hij nu hard aan het werk om Amerikaanse steun te houden. Biden heeft hij, maar in het congres werd hij niet overal met getrokken portemonnee ontvangen. En hoe staat het er eigenlijk voor met de welwillendheid onder gewone Amerikanen? Heb je vragen, opmerkingen, kritiek of complimenten, dan kan dat met een tweet naar @janpostmaUSA of @BNRdewereld, of met een mailtje naar dewereld@bnr.nl. Je kunt ook je vraag inspreken of intikken op de Amerika Podcast WhatsApp: 06 28 13 50 20.See omnystudio.com/listener for privacy information.

En we gaan parkeren in Marokko. (00:32) Zelfs Meloni weet het: Italië heeft migranten nodig De Italiaanse rechts-radicale premier Giorgia Meloni sprak in de oppositiebanken nog van een vooropgezet plan "om de Italiaanse etniciteit te vervangen”. Maar nu is ze van plan om  bijna een half miljoen migranten aan te trekken om haar economie een spurt te geven. Ondertussen zet ze juist keihard in op het terugdringen van illegale migratie via de Middellandse Zee. Toch bereikten de afgelopen maanden juist veel meer bootvluchtelingen Italië dan een jaar geleden. Weet Meloni haar kiezers nog tevreden te houden? Te gast is Arthur Weststeijn, Italië-kenner en historicus aan de Universiteit Utrecht. (10:52) Historische rechtszaak in Zweden In Zweden zijn alle ogen gericht op een historische rechtszaak. Twee topmannen van een Zweedse oliereus moeten voor de rechter verschijnen. Zij worden beschuldigd van medeplichtigheid aan oorlogsmisdaden tijdens de burgeroorlog in Soedan, eind jaren negentig. De Zweedse zaak volgt onder meer naar aanleiding van het rapport dat vredesorganisatie PAX schreef over het Zweedse oliebedrijf, en kan mogelijk grote gevolgen hebben voor vergelijkbare zaken. Egbert Wesselink schreef dat rapport en blikt in Bureau Buitenland vooruit op de rechtszaak. (21:13) Buitenland Uitgelicht: Marokko In onze rubriek Uitgelicht aandacht voor opdringerige Marokkaanse parkeerwachters. Daarover correspondent Samira Jadir. Presentatie: Sophie Derkzen