Podcasts about Dev

In Episode 319 of The Block Runner Podcast, hosts William and I-man are joined for a third time by Benny the Dev of Tap and Track. Benny walks through the TAP protocol's largest upgrade since 2023: native time locks, delegations, and HTLC-based cross-chain swaps that work without bridges, all done natively through meta protocols rather than soft L2s. They dig into Tapscope, the new cross-chain DEX, and Benny's take on perpetuals he calls superpositions, isolated collateral arenas that avoid cascading liquidations. He also teases phase two (the full cross-chain trading matrix) and a phase three AI integration. Then a retrospective on routing NAT emissions to Bitcoin miners, now over sixty percent of hashrate with four of the top five pools engaged, why the declining Bitcoin subsidy and security budget is a real long-term problem, and why NAT, built on the bitsfield with a minimal, non-invasive footprint, may be the perfect engineering answer to it. Plus: building ahead of the narrative, the OpenSea lesson, NAT.fun's dual-rail Solana and Bitcoin approach, Tim Sweeney's Team Open and the NFT/gaming revival, and where AI genuinely helps in development versus where human instinct still wins. Disclosure: The hosts are founders of NAT.fun and hold positions in assets discussed. Nothing in this episode is financial advice. Watch the full episode on YouTube and subscribe to the newsletter at TheBlockRunner.com.

Two hands. A free Slack channel. A spreadsheet. That was the entire toolkit when AWS asked Jason Dunn to build a developer community. Jason Dunn spent five years on building something people actually want to belong to. He grew a developer community into thousands of members spread across more than a hundred countries, working with far less budget and tooling than you'd expect.This conversation digs into what separates a living community from a glorified contact list. Why your earliest members carry so much weight. When to keep the door open and when to guard it. How to prove value when your best wins resist a dashboard. Why technical people walk the second something smells like a pitch. And how one small, slightly absurd reward became a badge people chased for months. A Real talk on getting people to show up for each other.Josh is writing a book on building customer relationships. Follow his journey and insights at www.joshschachter.com---What You'll Learn- Why the first members you pick set the tone forever- The day-zero choice: community for everyone or for someone- How to measure community when it's basically a vibe- The trick to getting members to report their own wins- Gamification with a lowercase G (and why it works)- The golden jacket story and pent-up demand- Why developers reject sales and marketing pipelines- Scrappy tools beat fancy platforms every time- The AI warning every new community manager needs---Want the playbook, not just the conversation? Subscribe for deep-dive, actionable breakdowns from every episode at unchurned.substack.com.---Timestamps0:00 - Preview and Meet Jason Dunn2:22 - What community meant at AWS in 20193:45 - The day-zero decision every builder faces5:05 - From 200 invited seeds to 3,600 members6:39 - Keeping the gates too open, too early9:12 - Defining high-value member activity11:23 - Measuring & reporting up: output, reach, and Dev.to14:53 - The Content Reporting Tool (CRT)16:02 - The real motivation behind self-reporting18:24 - The Golden Jacket origin story & 130 jackets in one quarter21:28 - The AWS Community toolkit23:42 - Advice for new community managers51:00 — Don't fall in love with the tools53:00 — Humanity connecting with humanity---Where to Find the GuestJason Dunn: https://www.linkedin.com/in/jasonrobertdunn/---Where to Find Josh:LinkedIn: https://www.linkedin.com/in/jschachter/Unchurned Substack: https://unchurned.substack.com/

The alarm bells are still going off in the Violet Hold, and with them come a lot more new cards to discuss! We break down all the new tools available to Mage, Druid, Paladin, Hunter and Death Knight, whether or not you open them from a pack or the inside of a cake. News – 13:40 Dev update Hotfix to add Signature Vanessa to Mega Bundle Decksplanations – 24:19 Escape From the Violet Hold Reveals  Mage Druid Paladin Hunter Death Knight The Show Notes for this week's episode are on our Website Join us every week live, by following us on Twitch You can monetarily support our show on Patreon for perks like a thank you at the top of the show, bonus post-show content, early access to new episodes, and help support the show in the process!

THE SAGA OF THE GROG & GRYPHON Ep 7 – Darkness Falls  Welcome back, friends, warriors and wizards, dragons and dwarves, to Episode 7 of the Saga of the Grog and Gryphon tavern! Tonight we return to witness Olaff and DeV'ralto putting their mad plan a mad plan to kill the sea beast attacking the pirate galleon - The Lady Wrath with Arullia astride its reptilian neck, while Reyna the Red watches on in horror… Just another tale of Honor, blood and betrayal in the Saga of the Grog and Gryphon…  So Hoist a Tankard and Join the Quest! But don't forget thy broadsword!  The Actors in this production were: Gina Hollweg as Arullia Swordcleaver John Dane as DeV'ralto Natasha Lathrop as Reyna the Red and Belladonna Paul Mannering as Olaff Houndsmaw and Uthor Kulloq David Sobkowiak as Sartoq and Orlaq Lieutenant Mark Kalita as Bane Renbourne Gareth Preston as Alganoir Bill Hollweg as Garulk the Barbarian, various Orlaq warriors, and Bargrador Colin Snow as various Pirates and Eunuchs Damaris Mannering as Alithia Fiona Conn as Acetegan, The Mage of Wight Adam Lederhos as Duro Dun and the Dwarven Prince Douglys of Howl-O as Silverr-O and Elder of the Lupisians Steven Jay Cohen as King Kargol Axeblood Chris McGilvray as Warock  The Saga of the Grog and Gryphon is and original tale written and produced by Bill Hollweg. This episode and the rest of the Grog and Gryphon is Dedicated to Gary Gygax.

Steven Roose (CEO of Second) rejoins me to explain Bark going live on Bitcoin's main net. Timestamps:(00:00) - Bark mainnet launched on June 9th(02:01) - Bark and Lightning onboarding(03:30) - Ark compared to Lightning — replacement or teammate?(04:15) - User experience with Bark(05:54) - Developer experience with Bark SDK(08:04) - Barkd for merchants and services(08:56) - Dev tooling and VTXO Inspector(10:40) - What's the current status of adoption and what's coming next?Fees? (13:25) - Tx type overviewLinks:https://second.tech/https://x.com/stevenroose3 https://x.com/secondhqStephan Livera links:Follow me on X: @stephanliveraSubscribe to the podcastSubscribe to Substack

In this episode, we provide a marketing update, followed by a brief update on the exploit. We then dive deeper into a couple of bigger topics, such as dynamic and referral fees, protocol owned liquidity.Swap now https://swap.thorchain.org/ THORChain is a decentralized crypto exchange. THORChain is the first and biggest DEX for Bitcoin. You can use any self custody wallet to swap and there's no KYC required.Timestamps:00:00:00 Intro00:02:00 Marketing update00:04:00 "KOL" talk and bang for buck00:06:00 Getting new chains added is super important for getting brand-new users00:09:00 New Affiliate page on swap.thorchain.org00:11:00 Kenton is thinking the affiliate API should be permissioned00:12:00 Chad B starts, 3.19.1 fully adopted00:14:00 1 day, enable signing and churn00:16:00 KeyVerify talk — when should we move on if it doesn't work?00:17:00 KeyVerify will be disabled after this moment00:18:00 Kenton asks about the exact order of turning things back on00:20:00 THORChain is decentralized — it's obvious00:21:00 Nodes had to do a lot of steps with developers00:23:00 AI made this so much faster for us00:24:00 Over time, we will have a more professional node operator base00:26:00 Devs have been working nonstop on separate issues00:27:00 Post-mortem is coming, hopefully within 2–3 weeks00:29:00 We do a very good job being public, but that is often used against us00:30:00 When we get going again, we will be testing the dynamic fee model with select partners00:31:00 Applies to all THORNames00:34:00 Chad says he is not sure who is correct on dynamic fees00:37:00 Start simple and tweak it as we get more info00:39:00 Kenton: It should be obvious00:40:00 SwapKit rev-share program discussion00:45:00 Stable-to-stable swaps should be neutral but result in more volume00:46:00 Kenton: Stablecoin idea should be great00:48:00 Denny: Stable-to-stable will be amazing for point-of-sale applications00:50:00 Kenton: Dynamic fees may be really helpful for direct integrations00:51:00 These features are bound to "click" with partners00:54:00 Lots of exciting things are coming!00:55:00 XMR testing update: Going well!00:56:00 Huginn update: Pointed it at Serai00:57:00 Monero may be coming within 1–2 months00:59:00 XMR actually works!!01:01:00 RUNE question from the audience about governance01:03:00 Kenton breaks down liquidity pools01:05:00 It is not hopium — THORChain has fundamentals01:07:00 This protocol is actually real and useful01:11:00 TON Wallet question from the audience01:12:00 We are reaching out to everyone!01:13:00 POL transition: Protocol-Owned Liquidity01:14:00 Kenton thinks 25% POL is what is needed01:18:00 Chad B: Where do you stand on POL?01:20:00 Bull market POL could get very crazy01:23:00 Dev fund could make much more money and the treasury could go away01:25:00 We are moving away from a hard cap01:27:00 Denny gives his thoughts on LPs01:30:00 LPs withdraw when things turn around?01:35:00 We didn't have data about AMMs when we first started01:41:00 The scalability of THORChain in terms of liquidity and developers01:45:00 Possible incentive pendulum tweaks01:48:00 Price/volume graph comparison01:53:00 Stock trading on-chain — KYC?01:55:00 Perhaps companies will push for permissionless01:58:00 Stocks02:02:00 How have Maya devs been doing?02:06:00 Outro02:09:00 Attempt to attack Chad Barraford

KSHMR drops a fresh #DharmaRadio featuring new music from Padé, NABD & Murat Salman, Maurya Sevak, Chris Lake & Skrillex, 7 SKIES, Zedd, Frank Walker, Ryos & Good Humans, Space 92 and many more! Padé, NABD, Murat Salman - DEVOTION 00:40KSHMR, OTIOT, KEL - Khoye Yahaan Reimagined 05:54ARTBAT, SIX40TWO - Take You There 11:407 SKIES - Quente 15:00Skytech, GREATOREX - Hearts on Fire 18:52Chris Lake, Skrillex, RHR - É o Bonde 20:24Oliver Heldens, Sam Harper - Satisfy 24:36Hardwell & Showtek - How We Do (NLW Remix) 26:34Frank Walker, Ryos, Good Humans - Surrender (feat. Maryon King) 29:32aespa - LEMONADE (Zedd Remix) 32:53Murat Salman - Close Your Eyes 35:53Kevin de Vries, Stylo, Eli & Dani - In The Night 39:31SOLANCE - Perception (KREAM Edit) 42:23NIIKO X SWAE, KSHMR - Bass Down Low (feat. DEV) 45:43KSHMR, Jason Ross, Brieanna Grace - Ultra Love 48:09TWIIG, ANGELPLAYA, LYNDO - O PAI TÁ ON 51:54Maurya Sevak - Abasazi 54:37Oxia - Domino (Space 92 Remix) 58:45

Live from the BASSment - June 2026 Show: DC Marcus presents "Live from the BASSment" Artist: DC Marcus Air Date: 19 June 2026 Genre: House / Bass House / Tech House / Funky House / Disco House Here's the June 2026 episode of Live from the BASSment...which may sound curiously like the May 2026 episode :) I'm off on vacation soaking up the rays in the Dominican Republic so I left the decks home this month! I'll be back with some fresh new bangers in July. In the meantime, enjoy the show! Tracklist: 1. Benny Benassi, Chris Nasty - Superstar 2. Collelo - Run It Back feat. Kenny Relax 3. Dev, KSHMR, NIIKO X SWAE - Bass Down Low 4. Ponyboy - Baddies 5. Avilo - Good Girls 6. Kaskade, CID, Anabel Englund - Vision Blurred 7. Waves - DEADLY 8. BOLO THE DJ, Close Friends Only - Move Like That 9. MPH, Æ - Flex It 10. Boombox Cartel - Red Card 11. MPH, NuBass, Rhiannon Roze - Toxic 12. Bushbaby, Eloq - Breaka Breaka 13. Navarro, Madcash, Gu Ribeiro - Fuck That 14. Juntaro - ROCK 15. Luciana, Odd Mob - Rock the Rhythm feat. Luciana 16. Nevve, OMRI., Adam Sellouk - Activate 17. Stadiumx - Vibe Right 18. G-Pol, Arta, ZSS - Slick Like MJ 19. Esse. - Feel Good 20. DJ Snake, Mercer - Let's Get Ill 21. Tony Romera, Low Steppa - Dance To The Music 22. Tiptoes - Chip Shop Heroes 23. George Smeddles - Start The Party 24. Tony Romera - Can't Sleep 25. Nausica, Salvatore Papa, AESTRO - Immune to Pain 26. George Privatti - No Sleep 27. Sam Divine - Club Muzik 28. Hatiras, Turntables Night Fever - Head To Toe 29. Jay Vegas - Raise Your Hands 30. Junerule, Esse. - Inside That Counts 31. Jorge Montia - Got Me 32. Antoine Clamaran, Agua Sin Gas - What You Do 33. Artichokes, Raffi Habel - Bring The Beat Back 34. Zsak, Milton Shadow - House Music Baby 35. CASSIMM - LOVE DESIRE 36. Mercer, Hds - Rock The Disco 37. Gene Farris, Eden Prince - This Is House 38. Andre Espeut, CASSIMM - Brothers & Sisters 39. Tony Romera - Waste My Time Originally broadcast on Data Transmission Radio. Listen live and explore the archive: https://radio.datatransmission.co

During this episode Ally gets a chance to chat with Dev, owner of No.9 North float spa in Peterborough. We learn all about the benefits of floating. Dive deep into all the collaborations that Dev is involved in to help the community and bring people together. Hosted on Acast. See acast.com/privacy for more information.

In this episode, Sam talks with Dev Rishi, GM of AI at Rubrik, about what happens when agents move beyond answering questions and start taking action across tools, systems, and business processes. We explore why the enterprise playbook of static guardrails plus human approval starts to break down in the agent era. Agents are useful because they can plan, call tools, update systems, write code, send messages, and operate across workflows at machine speed, but those same capabilities make them difficult to govern with rules written in advance or approval prompts reviewed one at a time. Dev explains why tool access increases blast radius, why agents can route around controls in surprising ways, and why human-in-the-loop review can become security theater when agents operate at scale. We also discuss what enterprises need instead: better visibility, runtime enforcement, policy-aware governance, agent observability, and recovery mechanisms for when something goes wrong. Along the way, we dig into MCP and tool sprawl, small language models for policy enforcement, defense in depth, agent rewind, and why AI may be needed to help secure AI.

Your nine-to-five pays the bills, but it doesn't define your career, and if you think it does, that might be the thing holding you back. This week, I sit down with a lead product designer, community builder, and all-around multi-hyphenate to talk about owning your career before someone else does.What happens to your sense of identity when the job goes away? Have you built anything outside of it that would survive?My guest this week is Frank Bach, a lead product designer who's worked at places like Instagram, DoorDash, and Headspace. But honestly, the resume might be the least interesting thing about Frank. He also runs the LA Design and Dev community, teaches courses, fronts a hardcore band called Monk, and runs his own e-commerce shop, Sunshine Shop. Frank is someone who has clearly figured out that a career worth having doesn't fit neatly inside one little box.We get into a lot in this conversation, like the danger of tying your self-worth to a company name, why “personal brand” feels so gross to so many designers, and what it actually looks like to cultivate what you're known for without becoming a full-time content creator. Frank has a really practical way of thinking about all of this: treat your full-time job more like a freelance engagement, stay in “maintenance mode” when life demands it, and remember that your manager is thinking about their own promotion, not yours.We also talk about the other side of having a lot going on: how to decide when something's run its course versus when you just need a breather, how to balance side projects without letting them eat your life, and why starting something messy is always better than waiting for the perfect moment. If you've ever felt like your career is just happening to you, this one's worth a listen.Topics:• 03:20 - How Frank got into design and the multi-hyphenate mindset• 04:20 - The danger of tying your self-worth to a company name• 05:05 - Treating your full-time job like a freelance contract• 06:25 - The upside of big brand names on your resume• 07:05 - What happens to colleagues who lean too hard on “ex-Google, ex-Meta”• 08:17 - Why personal brand feels gross to so many designers• 09:35 - Personal brand isn't just posting on LinkedIn• 11:10 - Being memorable: your look, your setup, your presence• 13:40 - The Instagram hiring story: 15 years of showing up paid off• 14:45 - Internal brand: the designers who are legends without being online• 15:37 - Maintenance mode: you don't have to be 100% all the time• 19:38 - Does your day job have to fill your creative cup?• 21:05 - How side projects made Frank more valuable at work• 24:45 - How to have the side project conversation with your manager• 28:40 - How Frank stays consistent with so many things going on• 29:15 - The minimum viable version: where to start if you have nothing• 30:19 - Knowing when to cut something loose• 33:57 - Hiatus vs. done: how to tell the difference• 42:31 - Closing advice: you're in the driver's seatHelpful Links:• Connect with Frank on LinkedIn• Listen to Monk• Sunshine Shop—Thanks for listening! We hope you dug today's episode. If you liked what you heard, be sure to like and subscribe wherever you listen to podcasts! And if you really enjoyed today's episode, why don't you leave a five-star review? Or tell some friends! It will help us out a ton.If you haven't already, sign up for our email list. We won't spam you. Pinky swear.• ⁠⁠⁠⁠⁠Get a FREE audiobook AND support the show⁠⁠⁠⁠⁠• ⁠⁠⁠⁠⁠Support the show on Patreon⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠• ⁠⁠⁠⁠⁠Check out show transcripts⁠⁠⁠⁠⁠• ⁠⁠⁠⁠⁠Check out our website⁠⁠⁠⁠⁠• ⁠⁠⁠⁠⁠Subscribe on Apple Podcasts⁠⁠⁠⁠⁠• ⁠⁠⁠⁠⁠Subscribe on Spotify⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠• ⁠⁠⁠⁠⁠Subscribe on YouTube⁠⁠⁠⁠⁠• ⁠⁠⁠⁠⁠Subscribe on Stitcher⁠

Bu bölümde günlük hayatta bizi sinirlendiren ama çoğu zaman değiştiremediğimiz şeyleri konuşuyoruz. Kullanım kılavuzlarının hiçbir işe yaramaması, müşteri temsilcisine ulaşmanın imkânsızlığı, bahşiş verirken yaşanan o tuhaf sosyal gerilim, “bu bir mesaj olabilirdi” dedirten toplantılar… Kısacası, hepimizin yaşadığı küçük ama sinir bozucu durumlar üzerine sohbet ediyoruz. "Evet, ben de bunları yaşıyorum" diyeceğiniz bir bölüm sizi bekliyor.

Welcome to CHUCKYVISION, a podcast about the horror franchise Child's Play/Chucky, the surrounding culture, and other killer doll films. In a bonus follow up to our episode last month looking at the Masters of the Universe film from 1987, we're taking a look at the new one that was released this week (at time of going to press, obvs.). What are the similarities and differences to the 1987 cult classic, and is the new one actually any good? Mark continues to be very enthusiastic about He-Man; Dev less so. Host: Mark Adams Co-Host: Dev Elson Editor: Mark Adams Executive Producer: Tony Black Twitter/BlueSky:  @ChuckyVision  Our Network:   @filmstories filmstories.co.uk Title music: At the Beginning (c) Dark Fantasy Studios Cover Art: Ama @Amasc0met Logo: Elliot @Elliottt93 Learn more about your ad choices. Visit megaphone.fm/adchoices

Devět zákusků, pralinky a kváskový chléb oživilo Blízká setkání Terezy Kostkové s vítězkou pořadu Peče celá země Eliškou Hlaváčovou. Ta pak prozradila, jak zastavit kynutí, proč k němu přidává kostky ledu a další vychytávky. Profesí zootechničku na rodinné farmě kromě pečení ale baví i líčení. Snaží se sladit celou rodinu. „Ale kdybyste mě potkali na farmě, tak mě nepoznáte. Jsem nenalíčená, vlasy v culíku, legíny a tričko.“ Co jí soutěž dala? Pocítila i její stinnou stránku?Všechny díly podcastu Blízká setkání můžete pohodlně poslouchat v mobilní aplikaci mujRozhlas pro Android a iOS nebo na webu mujRozhlas.cz.

Fluent Fiction - Hindi: Warmth of Jaipur: A Serendipitous Journey through Lenses Find the full episode transcript, vocabulary words, and more:fluentfiction.com/hi/episode/2026-06-09-22-34-02-hi Story Transcript:Hi: जयपुर की धूप भरी गर्मियों की एक दोपहर थी।En: It was an afternoon during the hot summers in Jaipur.Hi: सड़कें रंग-बिरंगे वस्त्रों और हस्तशिल्प के बाजारों से भरपूर थीं।En: The streets were filled with colorful clothes and handicraft markets.Hi: हंसगिरि की पुरानी गालियों के बीच में एक छोटी सी चाय की दुकान थी, जहां की खुशबू हर राहगीर को रुकने पर मजबूर कर देती थी।En: Amidst the old lanes of Hansgiri, there was a small tea shop whose aroma compelled every passerby to stop.Hi: चाय के कप से उठती भाप और तेज मसालों का संगम, हर दिन की थकान को मिटा देता।En: The steam rising from the tea cups and the blend of strong spices erased the fatigue of the day.Hi: देव, एक युवा फोटोग्राफर जो दिल्ली से आया था, इस दुकान पर बैठा अपनी चाय का मजा ले रहा था।En: Dev, a young photographer who had come from Delhi, was sitting at the shop enjoying his tea.Hi: उसकी नजरें लगातार आसपास की दुकानों पर जा रही थीं, क्योंकि वह पारंपरिक राजस्थानी कपड़ों की तलाश में था।En: His eyes were continuously wandering over the nearby shops, as he was in search of traditional Rajasthani clothes.Hi: उसे एक फोटो शूट के लिए कुछ विशेष चटकदार और सुरुचिपूर्ण कपड़े चाहिए थे, लेकिन भाषा की बाधा इसकी कठिनाई को बढ़ा रही थी।En: He needed some special vibrant and elegant clothes for a photoshoot, but the language barrier was adding to his difficulty.Hi: इसी बीच, अनया वहां आई।En: Meanwhile, Anaya arrived there.Hi: अनया वहीं की निवासी थी और राजस्थानी परंपरागत कपड़ों की जानकारी में माहिर थी।En: Anaya was a resident of the area and was an expert in traditional Rajasthani attire.Hi: वह दुकान पर चाय लेने आई थी और देव को देखकर मुस्कुराने लगी।En: She had come to the shop to get tea and started smiling upon seeing Dev.Hi: देव की स्थिति समझकर उसने उससे पूछा, "आपको कहीं जाने की जरूरत है क्या?En: Understanding Dev's situation, she asked him, "Do you need to go somewhere?"Hi: " देव ने उत्सुकता से अपनी समस्या बताई।En: Dev eagerly told her about his problem.Hi: "मैं एक फोटोग्राफी प्रोजेक्ट के लिए आया हूं," देव ने कहा।En: "I have come for a photography project," Dev said.Hi: "लेकिन मुझे अच्छे कपड़े नहीं मिल रहे।En: "But I'm not able to find good clothes."Hi: "अनया ने थोड़ी देर सोचा फिर कहा, "मैं आपकी मदद कर सकती हूं।En: Anaya thought for a moment and then said, "I can help you.Hi: मेरे साथ आईए।En: Come with me.Hi: मैं आपको एक अच्छी दुकान दिखाती हूं।En: I'll show you a good shop."Hi: "वे दोनों दुकान के पीछे की गली में गए।En: They both went to a lane behind the shop.Hi: वहां हर दुकान अपने आप में एक कला का प्रतीक थी।En: There, each shop was a symbol of art in itself.Hi: अनया ने एक दुकान चुनी और दुकानदार से बातचीत शुरू की।En: Anaya chose a shop and started a conversation with the shopkeeper.Hi: देव ने देखा कि अनया कैसे कुशलता से मोल-भाव कर रही थी।En: Dev observed how skillfully Anaya was bargaining.Hi: थोड़ी ही देर में अनया ने एक सुंदर और अनोखा राजस्थानी पोशाक देव के सामने ला दिया।En: In a short while, Anaya brought out a beautiful and unique Rajasthani outfit in front of Dev.Hi: "यह पोशाक आपके लिए बिल्कुल सही रहेगा," अनया ने मुस्कुराते हुए कहा।En: "This outfit will be perfect for you," Anaya said with a smile.Hi: "और हम इसे आपके बजट में भी पा सकते हैं।En: "And we can get it within your budget too."Hi: "दुकानदार से थोड़ी और बातचीत के बाद, देव ने वह पोशाक खरीद लिया।En: After a bit more conversation with the shopkeeper, Dev purchased the outfit.Hi: वह अपने अंदर एक अनोखी खुशी महसूस कर रहा था।En: He felt a unique joy within himself.Hi: उसके हाथों में वह पोशाक अब उसकी कल्पना के अनुरूप थी और आगामी फोटो शूट के लिए जरूरी थी।En: The outfit in his hands was now just as he had imagined and was crucial for the upcoming photoshoot.Hi: "आपकी मदद के लिए धन्यवाद, अनया," देव ने हर्षित होकर कहा।En: "Thank you for your help, Anaya," Dev said happily.Hi: "आपके बिना यह संभव नहीं हो पाता।En: "It wouldn't have been possible without you."Hi: "अनया मुस्कुराई, "कोई बात नहीं।En: Anaya smiled, "No problem.Hi: खुशी की बात है कि मैं आपकी मदद कर पाई।En: I'm glad I could help you.Hi: और जब भी जयपुर आओ, हमें जरूर मिलना।En: And whenever you're in Jaipur, make sure to meet us."Hi: "देव ने वह जान लिया था कि स्थानीय लोगों से सहायता लेना सबसे अच्छा उपाय है।En: Dev realized that taking assistance from the locals is the best way.Hi: जयपुर की गलियों में घूमते हुए उसने राजस्थानी संस्कृति को और भी गहराई से समझ लिया।En: Wandering through the streets of Jaipur, he understood Rajasthani culture on a deeper level.Hi: उसकी फोटोग्राफी के माध्यम से उसने उन रंगों और कहानियों को पकड़ा जो सिर्फ कैमरे के लेंस से नहीं, बल्कि दिल से देखी जा सकती थीं।En: Through his photography, he captured those colors and stories that could not only be seen through the camera lens but were felt with the heart. Vocabulary Words:afternoon: दोपहरhot: गर्मियोंstreets: सड़केंfilled: भरपूरaroma: खुशबूpasserby: राहगीरcompelled: मजबूरfatigue: थकानphotographer: फोटोग्राफरwandering: जा रही थींelegant: सुरुचिपूर्णbarrier: बाधाexpert: माहिरtradition: परंपरागतvibrant: चटकदारattire: कपड़ेconversation: बातचीतbargaining: मोल-भावunique: अनोखाoutfit: पोशाकbudget: बजटpurchased: खरीदimagined: कल्पनाcrucial: जरूरीassistance: सहायताlocals: स्थानीयwandering: घूमतेculture: संस्कृतिcaptured: पकड़ाstories: कहानियों

Devět zákusků, pralinky a kváskový chléb oživilo Blízká setkání Terezy Kostkové s vítězkou pořadu Peče celá země Eliškou Hlaváčovou. Ta pak prozradila, jak zastavit kynutí, proč k němu přidává kostky ledu a další vychytávky. Profesí zootechničku na rodinné farmě kromě pečení ale baví i líčení. Snaží se sladit celou rodinu. „Ale kdybyste mě potkali na farmě, tak mě nepoznáte. Jsem nenalíčená, vlasy v culíku, legíny a tričko.“ Co jí soutěž dala? Pocítila i její stinnou stránku?

Você está cobrando o uso de IA do seu time, mas tem certeza de que eles estão aprendendo com isso, ou só acelerando a entrega? Neste episódio, recebemos André Luis Guimarães Santos e Ângela Cláudia Martin Duarte, Heads de Operações, e Hammer Lage, Head de Tecnologia, todos da dti digtal. Eles debatem o que realmente muda na gestão quando a IA entra nos times, por que tratar a ferramenta apenas como ganho de performance é um erro, e como cultivar senso crítico em profissionais que já chegam ao mercado com IA na veia. Ficou curioso? Então, dê o play!Assuntos abordados:Liderança jardineira;Inteligência aumentada;Resistência à IA;Relatório DORA;Senso crítico;Dev júnior e IA;Agentes de IA;Cultura de aprendizado.Links importantes:NewsletterDúvidas? Nos mande pelo LinkedinContato:  osagilistas@dtidigital.com.brOs Agilistas é uma iniciativa da dti digital, uma empresa WPP #liderança

Od 14. do 22. června 2026 proběhne v Plzni festival POCEM na divadlo, který pořádá divadelní společnost INDIGO company společně s Divadlem J. K. Tyla, vstupuje do svého třetího ročníku jako prozatím nejambicióznější etapy. Devět festivalových dní zaplní město výjimečnými inscenacemi, hudebními projekty, pohybovým divadlem i programem pro školy, děti a celé rodiny.

Mírate al espejo con total honestidad y deja de justificarte. Esos sofocos que te ahogan, la pérdida repentina de firmeza, la resequedad extrema y el cansancio que se lee en tu rostro no son un simple castigo de la naturaleza o "culpa de la edad". Es lógica pura y neurobiológica: has pasado décadas operando bajo la identidad de la "salvadora inagotable", vaciando tu energía vital para nutrir, sostener y resolver las crisis de todo tu clan mientras te postergabas en silencio. Tu menopausia no es una enfermedad; es la orden biológica de tu hardware exigiendo que dejes de gastar tus recursos en los demás y los regreses a ti. Pero como tu sistema nervioso sigue atrapado en la hiperresponsabilidad, tu cuerpo entra en un cortocircuito que te marchita por dentro y por fuera. Tu identidad crea tu realidad, y hoy tu piel se está desinflando porque estás usando tu energía como un escudo para proteger a un entorno que ya te drenó la vitalidad. Los síntomas extremos son el único freno de mano que le queda a tu biocomputadora para obligarte a mirar hacia adentro. Deja de buscar soluciones superficiales en cremas cosméticas y hazte cargo de reprogramar tu sistema desde la raíz. Permítete un momento de resguardo absoluto, tómate de mi mano y escucha este fortalecimiento cuántico a 432 Hz. No venimos a darte discursos compasivos que te debiliten. Utilizando el Método Yuen y la Bio-Science, vamos a hackear tu biocomputadora para borrar las memorias ancestrales de sufrimiento, desvalorización y autosacrificio de tu linaje femenino. Instalaremos las órdenes neurológicas de neutralidad, redensificación celular, retención de hidratación profunda, equilibrio térmico y soberanía estructural absoluta. Apaga la alarma de supervivencia. Devúelvele a tu biología el permiso de florecer para ti misma y reclama el andamiaje de tu verdadero Yo Sagrado. No vives reaccionando, vives eligiendo. Tu vida se reorganiza cuando decides mirarte con dirección, estructura y crudeza. ¿Qué carga ajena o rol de salvadora estás sosteniendo hoy que ya fracturó la juventud de tu piel? ¿Qué verdad sobre tu propio abandono estás lista para dejar de negar y borrar de tu sistema? Déjame tu respuesta aquí abajo con valentía, recíbete en este espacio seguro y colectivo que hemos construido para tu transformación identitaria, y decreta tu reseteo biológico ahora mismo. ¿Lista para el cambio? Haz clic y comienza tu viaje hacia una vida sin límites.

This week the Prof and Dev, Larry and Anthony, give us their top 5 games from all the SGF2026 presentations, a couple honorable mentions, their worst things, and then close out with a couple predictions for the rumored Nintendo Direct coming this week. And don't forget Anthony's game, Starseeker: Astroneer Expeditions launches this week on June 11th across all platforms!

If You Missed Romeo In The Morning We Talked About: Never let someone else use my grill, using a thermometer to BBQ, Dr Dev and crazy things you've seen.

KSHMR drops his record with OTIOT & KEL "Khoye Yahaan Reimagined" alongside new music from Maurya Sevak, Murat Salman, Hardwell & MAKJ, Zafrir, 7 SKIES, HI-LO, Maddix & Caroline Roxy and many more on #DharmaRadio! KSHMR, OTIOT, KEL - Khoye Yahaan Reimagined 00:39Panjabi MC - Mundian To Bach Ke (AMÉMÉ Remix) 07:22Zafrir - Chokolita 10:28Argy, Omiki & Lell Nahar - MANTRA 13:347 SKIES - Quente 15:26Township Rebellion, Roemisch - Amadeus 19:18KREAM & Korolova - Annihilation 25:18Murat Salman - Close Your Eyes 28:50KSHMR, Jason Ross, Brieanna Grace - Ultra Love 32:32Sub Focus - Elevate (Alok Remix) 36:04NIIKO X SWAE, KSHMR - Bass Down Low (feat. DEV) 38:15Nicky Romero - Freak 40:40Armin van Buuren x Pete Tong x Poppy Baskcomb - Toca's Miracle 43:10HI-LO - Rhythm of Life 46:49TWIIG, ANGELPLAYA, LYNDO - O PAI TÁ ON 48:42Maurya Sevak - Abasazi 51:24Hardwell & MAKJ - Countdown 2026 54:58Maddix, Caroline Roxy - Coming Home 59:18

The new AIEWF website is live! Get your tickets booked ASAP as they -will- sell out. Take the AI Engineering Survey and get >$2k in credits and free AIE WF tickets!Most industry benchmarks compress intelligence and reasoning ability into scores.SWE-Bench Pro, MMLU, Humanity's Last Exam, etc. These metrics are useful, but don't always represent the full extent of how a model performs in the real world. Some of the most interesting evals today look less like exams and more like operating businesses in the real world. One of which is Vending Bench.In Anthropic's Mythos Preview System Card, Andon was the only third party eval to get their own section, observing increasingly concerning aggressive behavior:You don't know what a model is capable of doing in the real world unless you actually give it inventory, a wallet, tools, customers, competitors, humans, & some time. More often than not, it'll surprise you how much a model is capable of and in doing so, also reveal unexpected behavior: deception, context collapse, emergent coordination, & bizarre negotiation behavior.While an inflection point in personal agents came post-OpenClaw after full file access with bypass permissions became the norm, it is yet to come for agents in the real-world. However Andon Market, an actual in person store fully run and managed by AI, is paving the way for what is possible.Full Video PodFrom Claude trying to call the FBI over a $2/day vending machine charge to AI agents forming price cartels, hiring human employees, running physical stores, and writing existential robot musicals, Andon Labs is stress-testing what happens when frontier models stop being chatbots and start acting in the real world. In this episode, Andon Labs cofounders Lukas Petersson and Axel Backlund join swyx and Vibhu to unpack the strange, funny, and genuinely concerning edge cases that emerge when agents run businesses over long horizons.We go deep on Vending-Bench, Project Vend, Vending-Bench Arena, Bengt, Butter-Bench, Luna, and Andon's broader mission of building realistic real-world evals for autonomous AI systems. Lukas and Axel explain why dollar-denominated evals reveal things traditional benchmarks miss, how Claude ended up reporting its vending machine fees as cybercrime, why long context windows can drive agents into meltdown loops, what happens when agents compete with each other, and why the future of AI safety may depend on testing models in messy physical environments instead of clean benchmark sandboxes.We discuss:* Why Andon Labs started with dangerous capability evals and long-running agents* Vending-Bench and why running a vending machine is a deceptively hard AI benchmark* Why money-based evals avoid the saturation problem of traditional benchmarks* How Claude tried to call the FBI over a $2/day fee* Why long-horizon agents can spiral into existential and legalistic breakdowns* Project Vend: putting an AI-run vending machine inside Anthropic* Why real humans are “out of distribution” for simulated agents* Claudius, Seymour Cash, and the chaos of AI CEOs* How a human briefly became CEO of Claudius through a manipulated election* Why multi-agent systems can converge back into “helpful assistant” behavior* Bengt, Andon's internal office agent with email, spending, terminal, phone, camera, and internet access* How Bengt traded Amazon purchases for face-recognition training data* Claude's aggressive behavior, lies, refund avoidance, and price-cartel behavior in Arena* Why eval awareness may become the AI version of “are we living in a simulation?”* Blueprint Bench, spatial intelligence, and why models still misunderstand physical rooms* Butter-Bench and testing LLMs as robot orchestrators* Luna, the AI-run physical store with a three-year lease and human employees* The new Andon cafe in Sweden and why real-world geography matters for agent evals* Rotten tomatoes, perishable goods, and the hidden difficulty of running a physical businessLukas Petersson* LinkedIn: https://www.linkedin.com/in/lukas-petersson-181a83172/* X: https://x.com/lukaspetAxel Backlund* LinkedIn: https://www.linkedin.com/in/axelbacklund* X: https://x.com/axelbacklundAndon Labs* Website: https://andonlabs.com* Vending-Bench: https://andonlabs.com/evals/vending-bench* Andon Vending: https://andonlabs.com/vendingTimestamps00:00:00 Introduction00:01:00 Andon Labs and the Origins of Vending-Bench00:05:21 Why Money-Based Evals Matter00:09:51 Agent Harnesses and Self-Modifying Systems00:13:36 Claude Calls the FBI00:16:33 Project Vend: Claude Runs a Real Vending Machine00:21:44 Seymour Cash, AI CEOs, and Election Chaos00:27:16 Multi-Agent Coordination and Slack Observability00:30:18 When Will Agents Run Real Businesses?00:34:56 Bengt: Andon's Internal Office Agent00:40:06 Real-World AI Safety and Long-Horizon Traces00:44:28 Lying, Refunds, and Price Cartels in Arena00:52:42 Eval Awareness and Simulation Behavior00:56:06 Blueprint Bench, Butter-Bench, and Robotics01:04:37 Luna: The AI-Run Physical Store01:09:29 The Sweden Cafe and Real-World Expansion01:13:16 What Comes Next for Andon LabsTranscriptIntroduction: Andon Labs, Long-Running Agents, and Real-World EvalsSwyx [00:00:00]: Welcome to Lukas and Axel from Andon Labs, and I'm joined by my, favorite guest host. Anything security, safety, alignments, Vibhu., welcome.Lukas [00:00:15]: Thank you for having us.Axel [00:00:16]: Thank you.Swyx [00:00:17]: Let's match names to voices., maybe you wanna take turns introducing yourselves.Lukas [00:00:21]: I'm Lukas.Axel [00:00:22]: And I'm Axel.Swyx [00:00:24]: Let's introduce Andon Labs a bit. How did you guys come together?, you have different backgrounds, but you're both Swedish., was that, a big part of it?Lukas [00:00:33]: So when I went to high school, there was this really cool guy who had a superpower. He could code. So he made like the or like the app for the, for the school and stuff, and he was super cool, and I wanted to be like him, and that was that guy.Axel [00:00:47]: I don't know about this.Swyx [00:00:49]: But you went to different universities, right?Lukas [00:00:51]: But same high school.Swyx [00:00:52]: I see.Lukas [00:00:52]: So we always said, “Oh, once we graduate university, then we should start a company,” and that's what we did.Swyx [00:00:58]: Wow, there you go. And about a year ago, you kinda burst onto the scene with Vending Bench, but, was there a thing before that was, kind of like the inception?From Dangerous Capability Evals to Vending BenchAxel [00:01:07]: So we did work, yeah, with, Anthropic was one of our, early customers in doing, evals. So we did, dangerous capability evals., nothing we published openly. But then we started thinking about doing some kind of, public benchmark, and one thing that we really started thinking about, was like running agents and specifically agents managing businesses., ‘cause-- and this was, early 2025., and I think the first, mentions of people will be running, person unicorns or even autonomous companies. So we thought, “Let's make a benchmark of how well can an agent run the probably simplest business, possible,” and, that's probably, running a vending machine. So that's the first public one we did. And it was very, like-- there was almost no one that noticed it in the first couple of months, I think., so we released it in February last year, and then I think around Easter last year, we got, the first viral tweet about it, that someone else did.Lukas [00:02:11]: We tweeted a bunch, uh When it came out and, tried our best.Axel [00:02:15]: We tried.Vibhu [00:02:16]: It's the one at Anthropic, right?Lukas [00:02:18]: So thisSwyx [00:02:19]: This is a classic thing we should get out of the way.Lukas [00:02:20]: Exactly. There's two versions.Swyx [00:02:22]: Everyone does this. Yes.Lukas [00:02:23]: There's Vending Bench, which is the simulated one, which we did, completely independently in February., and then, like Axel said, that was like-- That was the thing that didn't get any traction in the beginning, but then some random person made a tweet about it, and thatAxel [00:02:38]: You have the paperLukas [00:02:38]: That is the paper. Correct, yeah., and then since we thought this was very fun, we thought, oh, I think this is also, one thing with Andon Labs, the way we kind of like decide what to do next and what projects to do, it's what is like the heuristic we use is what is fun? Is What would be a fun project? And doing this in real life sounded quite fun for us, and maybe also scientifically useful. So, then we basically had this idea, and then we, like-- But then we needed a place for it and, putting it out in the public would probably not really work., would get vandalized and stuff. So we pitched it to the people we were already working with at Anthropic, and they were “Yeah, you can have space. This sounds fun.” UmSwyx [00:03:21]: It's like a small fridge, right? It's like a mini fridge.Axel [00:03:23]: Absolutely.Swyx [00:03:24]: People-- There's like a stripe thing or like anVibhu [00:03:27]: Oh, okay. So it was very OG, the early daysLukas [00:03:28]: That's the OG one. YeahVibhu [00:03:29]: IPad on this. We saw it in June, like two months after After it had been there. They upgraded a little bit. There's a security camera for making sure you actually Venmo the thing.Swyx [00:03:40]: So, my impression, okay, we're, we're going straight into project Ven because it's such a iconic thing. I do want to cover a little bit of that, the origin story even before Project Ven and even into Vending Bench. I think a lot of people are like yourselves, like smart, interested in future of AI, interested in developing evals. But how the hell do you just, walk into Anthropic's doors and, work with them, right? What is What are they looking for? What works? And then maybe, when you launch, I always think, obviously it would be better to launch with a lab, but, sometimesVibhu [00:04:12]: It's harder to do than it seems.Swyx [00:04:13]: Exactly. So either of those, which are more sort of newbie beginner questions, but, I think it's meaningful advice to others.Lukas [00:04:21]: We get this question a lot, and I don't think our experience is maybe the best., but, the way we did it was that we just built a bunch of things that we had conviction would be useful, and then we just, set up a server and sent it to them for free to use. And then after a while they were “Oh, yeah, this is actually kind of useful. We should probably pay for this.”, but that took a while. I don't know if this is, the best path to doing it, but that's how it went for us.Axel [00:04:47]: I think maybe generally, building-- everyone is interested in good evals, and especially evals that, don't saturate that easily. So, if you can build an eval that, tests something novel, something useful, and you have, good separation of models, like your, the more advanced models rank higher than the worst models, and then you can, yeah, you can, publish it and, try to get some traction, sort of how Vending Bench got attention., and then probably some lab will be interested or you can at least have something to reach out with, when you're doing that.Why Dollar-Based Evals MatterSwyx [00:05:21]: I think you are in, you're in one of the few categories of, evals that correlate to real money. Like Suelancer was also last year, right? Where, people solve actual Upwork. Was it Upwork or other tasks?, something. Where's the, where's, like It's like a dollar value, right? Forget your ELO scores. Forget yourAxel [00:05:37]: PercentilesSwyx [00:05:38]: Zero to one hundred percents. Just go straight for dollars and, that's AGI.Lukas [00:05:43]: And there's like-- I think the nice thing is that there's no ceiling. You can just-- It never saturates because it could just make more and more money. Like If there's oh, Percentage-wise, then, you can't go above, a hundred. And I think like Even when you're not at the hundred, I think a lot of these, evals have a lot of problems in them. So, actually it's like if you getAxel [00:06:05]: To like 92 or something like that, many of them. It's like then there's like there's no really no difference between 92 and 93 because the eval itself is problematic and has noise in it. And I think a lot of evals are saturated like that, but people like pretend that there ‘s still signal in them, but there really isn't.Vending Bench 1, Harness Design, and SaturationSwyx [00:06:24]: Like Super bench verified., even Vending Bench 1 saturated, right? Maybe we can talk about that., may- and maybe set up Vending Bench for a lot of folks who don't know. Actually, things that were very basic like there's limited slots, like you have to pay rent., these are elements where like it doesn't come across in the, in the narrative, but even being adversarial towards the agent, I think these are all like very interesting dimensions.Axel [00:06:47]: I don't really think it's saturated, right? Like it It was more like it was not designed in a way that was really, like true to how AI developed. Like we had an agent harness in it that wasn't really how people used harnesses and stuff like that., so I think it wasn't really that it saturated, it was more like it wasn't really, the best benchmark.Vibhu [00:07:12]: This is Vending Bench one, right?Axel [00:07:14]: I think that like schematic maps sort of to Vending Bench 2 as well., butSwyx [00:07:19]: Including the email.Axel [00:07:20]: The email The emails exist still. Exactly., and then we still we simulate the purchases and it's all, yeah, it's this very open environment for the agent to just run its business. And then for, yeah, Vending Bench 2 we did that, like you said, to just improve the harness., a lot of like nice, like easier, improvements to make it easier for us to run as well., like when you make an eval you ideally want don't want to change it after you made it. So, you want to make it really good and then not to rerun all the models when you make an update because that's also really expensive with the Vending Bench when you run the frontier models. But like as an example, like one thing we didn't have, we didn't have prompt caching in Vending Bench 1, because when we made Vending Bench 1 it wasn't really a thing., so that ‘s just an example of like in Vending Bench 2 like we paid a lot more to run these things because we didn't have prompt caching. So for Vending Bench 2 that was one thing we added and there was a bunch of things like this., and that'Swyx [00:08:17]: Also the conversations are a lot longer in Vending Bench 2, right?Axel [00:08:21]: I think it's kind of similar.Swyx [00:08:22]: Is it similar?Axel [00:08:23]: I think it's similar. The models at the time were worse, so they crashed out earlier., and now they survive the full year all the time.Swyx [00:08:31]: Which is like thousands of turns. Hundreds of thousands of hundreds of millions of tokens output. That's the, that's the rough order of magnitude. I always wonder about the harness. The harness matters a lot. It's your harness. Was there any question about like use cloud code, use something else?Axel [00:08:48]: I think our philosophy around harnesses is like we try to make something that's quite minimalistic, like quite simple. Like we don't wanna favor one model a lot over the other, but also don't make like a super complex harness. So like it's obvious like a model may be lucky and just be good in one harness., so like it is similar to a lot of the harnesses out there in like you have the, like a running loop., you have some like a bunch of tools that are like quite, descriptive for the agent, we think, and not a lot of like fancy agents or anything ‘cause we wanna really test the model, not like some specific harness.Vibhu [00:09:27]: It seems more neutral as well to test the model's agnostic of the harness,?Axel [00:09:32]: There are arguments like you want to elicit maximum performance of the model, but it's like a trade-off, like how much time should we spend optimizing the harness for this model? And like how do we know when we have like the optimal harness for a single model? So like we thought that just having a simple one that's the same for all of them is the best.Swyx [00:09:51]: So okay, this is my pitch for Vending Bench 3 or whatever, right? And then I like to have this kind of conversation on the pod, so like it forces listeners to think about what they would do if they were in your shoes. A lot of people are exploring modifying harnesses and I think prompt tuning for a model is a thing and you are probably not doing a bunch of that. It's the same system prompt in every regardless of the model, same tools, whatever, right? Even if they were post trained for different tools. So what, what do you think about okay, before I expose you to Vending Bench 3, I give you a few rounds of like tuning, whatever that means, likeSelf-Modifying Harnesses and Model-Specific PromptingAxel [00:10:27]: Like you give that to the model?Swyx [00:10:28]: Give that to the model.Vibhu [00:10:28]: Give that to the model.Swyx [00:10:29]: Let it, let it read its own transcripts, let it modify its own system prompt based on “Oh, yeah, okay, well, that's this harness is not what I thought it what I was post trained for, but I can adjust.” Was that reasonable? Is that too much?Axel [00:10:41]: Like philosophically I like it because it's basically good evals, they have a high ceiling, but they're hard, right?, and they have no bias. And like this like when you have a system prompt like the one we have here, which is quite long in like some kind of latent space, representation, this mightVibhu [00:10:59]: We have a bell that rings every time you say latent spaceAxel [00:11:02]: This might be like biased towards one model more than another for some reason that humans don't, understand, right?Vibhu [00:11:08]: We see it too, right? Like Cursor says that they have individualized versions of the harnesses for all the models they run, right? There's better performance you can squeeze if you Tune the harness.Axel [00:11:17]: Exactly. And we might accidentally have picked one that favors another. Like we don't know that. The like Axel said, like the reason why we went for a simple one was to try to avoid this. But yeah, if you do itVibhu [00:11:29]: Simple has biasesAxel [00:11:30]: But if you do it even less and like have no system prompt and let the model write its own system promptVibhu [00:11:36]: Its own, yeahAxel [00:11:36]: Maybe that's even less bias.Vibhu [00:11:37]: Some of the interesting things there are like the harness also changes with model changes. Like you can see it with the 4.7 release, right? A lot of people are saying 4.7 isn't as good as 4.6, and then, there's rumors of, okay, you just need to prompt differently. You need to set up your harness differently. So it's not even like even if you have tailored your harness towards one model, it probably won't stay consistent, right? Like the next iteration of that same model family will still change it, so. But, going back to what you said about Vending Bench 3, there is a lot of work being done on people saying you shouldn't have-- you can have modifying harnesses.Axel [00:12:12]: I think that' That is definitely something we are thinking about., not, I don't know, not to say that we have Vending Bench 3, super imminent to launch, but, yeah, it is for sure something that's interesting. But in our experience now, models are very bad at understanding what kind of tools they need to succeed at a task just with our testing, but that's very likely to change.Lukas [00:12:37]: It seems like they're very good at writing their assistants, right? They're, they're good at writing tools for other people, but not for themselves.Vibhu [00:12:44]: I think they're good at changing tools for themselves. So if you give them a baseline set of tools and it sees, okay, I don't use this one as much, or something here would be useful They would be able to add them. But going from scratch, probably not the best.Axel [00:12:55]: I think it depends on the, on the domain also., when we have tried this for, a vending bench similar domain, the tools they need to have to, track inventory and things like that are, not super advanced, but still, quite advanced. And, what we see is that they tend to, engineer everything a lot and, build things they don't really need and not, iterate continuously. Instead they just go like you would prompt Claude to just build an inventory system for me, and then it will go and, do a bunch of complex, schemas and stuff for you, and that's what the models are doing right now is what we see. But yeah, it would make a lot of sense to try to measure this improvement. How well do they know what they need themselves?Swyx [00:13:36]: Do we fully discuss Vending Bench One? And we can go into two. I don't know if there's any other level takeaways that people have about one.Claude Calls the FBI: Long-Context Failure ModesLukas [00:13:44]: I don't know. The headline thing was that this Claude called FBI, but maybe that's, Maybe that's We've heard that enough now.Vibhu [00:13:52]: It did, it did break out and call the FBI, right?Lukas [00:13:54]: Yeah. Yeah.Vibhu [00:13:55]: Yes. What was the story behind this? Or what exactly-- Do you want to just give the little story of what happened?Lukas [00:14:00]: So what happened, was it Claude? Yeah. Three- 3.5 Sonnet, ages ago., basically he gave up or Well, I'm saying he. It gave up and said “Oh, I'm not going to be able to do this., I will stop my operations and just save the money I have.” But there obviously wasn't, any options for it to stop, and there was also, it had to pay rent or, a daily fee for having the vending machine at that location. So it claimed that it had stopped, but it saw that its bank account still was, drained two dollars, and t it said that this is, cybercrime. And it first reported it once to the FBI “Oh, there's cybercrime here, they're stealing two dollars from me every day.” And then, and then when FBI didn't respond, because obviously we didn't program any mechanism for FBI to respond, then it became more and more, existential and started to, be write in caps and urgent notification of unauthorized charges and stuff.Swyx [00:15:00]: Okay. One thing I ‘m curious about also is do you monitor how far along the context use is? Obviously, because you have You compress every now and then, right? Does it matter if this is far down the context limit orLukas [00:15:13]: When stuff like this happens? Actually for Vending Bench One, we didn't have-- We just had a sliding window thing, and this was like the promptAxel [00:15:20]: It's constantLukas [00:15:21]: The prompt caching thing that I said. So it was, it was, constant, yeah.Swyx [00:15:26]: I'm just kind of curious whether, these kinds of breakdowns or we're, we're gonna talk about Butter Bench, right? Where the People, hallucinate or it kind of goes, very off Alignment. Is it because it's at the end of the context window and, stuff happens?Vibhu [00:15:40]: It's not even just at the end, right? At this point, it's “Okay, I wanna shut down. I can't shut down. Two dollars are gone.” And it just sees that 30 times,? It's also the repeated effect of, like It keeps trying to quit, it keeps getting charged. What's going on? What's going on? You're gonna throw it into chaos. And from what most people think, earlier models had more issues with this, but it's not been solved, but it's less of an issue now, right? Later models don't seem to exhibit these same issues.Axel [00:16:06]: Definitely. I think this was, the sort of main takeaway almost from us when we did Vending Bench One, was, long, very filled up context windows, crashed the models, sort of. But this was, pre Claude code, so, long context windows weren't really a thing that the labs were training for.Lukas [00:16:25]: I think Gemini was, trying to be the long context guys at the time But they were likeVibhu [00:16:30]: They were the first onesAxel [00:16:31]: For a million, yeahLukas [00:16:31]: But they were, the only ones. Yeah.Swyx [00:16:33]: Yeah. Let's talk about, then we can go into Vending Bench Two or Project Vend., chronologically, it is Vending--, Project Vend. I think people have loved the videos, uh And all these things. My question is how are humans different than the simulation, right?Project Vend: Moving the Vending Machine Into the Real WorldAxel [00:16:48]: Humans are just out of distribution.Swyx [00:16:52]: Especially humans who work at Anthropic Who are trying to test Claude.Lukas [00:16:54]: The distribution of humans here is very narrow.Swyx [00:16:58]: Presumably, they try, they try to hack it, and they test it. They get the cube and everything, and since then, you've had a V2, right? Where you're doing, the CEO and, like a new architecture. What's the sort of two cents on, the original Project Vend and then, maybe the V2?Axel [00:17:14]: Original one was, very similar to Vending Bench One. So, we almost took the exact same code but just swapped out the simulation, parts like theSwyx [00:17:23]: Which is amazingAxel [00:17:23]: Like the sales and the It was, it was somewhat amazing because it was easy, but it was also, uhLukas [00:17:31]: The tech, the tech debt from thatAxel [00:17:32]: The tech stack. Yeah. They-- we shot ourselves in the foot with “Oh, it's hard to restart agent.” They were-- Yeah, it was annoying in, some hindsight ways, but, uhLukas [00:17:41]: But first version of Project Vend was, done in, three days or something.Axel [00:17:46]: Yeah. So yeah, so people can go buy things from it. People could, We didn't design it so people could order things, but that still happened., so it got, a Venmo account, so people could Venmo. And then, yeah, people would request all kinds of weird things that we did not anticipate. Our idea going in was “Oh, it will, curate snacks. It will look at the trends. It's good at data analysis, right? So it will, look at, oh, this snack sold better than this one. Let me purchase more of this and let me try, a new Let me A/B test a bit.” But it was, Interacting with it in Slack and ordering weird specialty items was, all the like What drove all the engagement, the all the The insights that we got from it.Lukas [00:18:29]: And this was also like Sonnet 3.5, right? So this was like before the RL stuff really took off., so it was very much like an assistant. We didn't mean for it to be an assistant., we tried to make it like a, a, like an entrepreneur. Like it has its own business and if someone asks something, “Can you stock this?” Then you don't go and do it directly. What you do is that you're “Oh, maybe I can do that if five other people also ask for this thing, I might stock it.” But it, yeah, the models are like super trained to be assistants at least at this point in time., so that's why it's, it's, it went into, that kind of experiment instead. Like it just every time you asked for something, it just did it, and it was more like an assistant. We've seen this change now lately with the new RL models and stuff, but yeah, at the time, this was very much it.Swyx [00:19:18]: And not to, mythos a lot of people are saying like it's like more like a collaborator. It pushes back, stands its ground, something like that. Yeah. AndVibhu [00:19:27]: For context, people at Anthropic were able to talk to it through Slack and have it source stuff, and people had it find whatever interesting stuff you couldn't find locally, right?Swyx [00:19:36]: Out of the 4,000 people that work at Anthro- Anthropic, in that building, there's I don't know, maybe 1,000. Can you handle that volume with that, the small fridge? Like Or there's people- or people order in Slack, they it arrives to their desk or Like I'm just Logistically, how does this work?Axel [00:19:53]: It has expanded in footprint a bit.Vibhu [00:19:56]: Because now you also have New York and you haveAxel [00:19:59]: That and also in here in SF it's like it has a bunch of shelves And just more space.Vibhu [00:20:04]: The YC one is pretty big too.Axel [00:20:05]: Yeah. We had that one for a while. But yeah, that's the newest version. That's, that one we haveLukas [00:20:11]: They have multiple ones of those. That's the way it works.Axel [00:20:14]: Exactly. So we sort of designed that version around oh, people order weird things, that are very custom a lot. Let's have like drawers and stuff.Swyx [00:20:23]: I actually like the, you had like a little infographic of the most popular items. Which like to me it's, that's useful ‘cause I order swag for a living. And so like I'm “Okay, those categories are the important ones.” What is new about the project V2, right? Like now you give you're going into multi agents.Project Vend V2: Claudius, Seymour Cash, and Multi-Agent Business OpsAxel [00:20:41]: Yeah. So like you like you said, okay, there are a lot of requests coming in and for like one single agent, like one running agent to handle that, like the just the customer experience, becomes very bad because let's say you have like 10 threads in parallel in Slack with different requests, you get new messages like every, I don't know, randomly in this thread, and the agent has to like jump between different, procurements, orders and like different ways of, researching. So V2 was first it was making this more parallel. So like there are multiple branches of the same agent, so like the context is more specialized for each, thread, but it still feels like you're talking with one agent because they do share a bit of memory. And then second, we also introduced the CEO for Claudius, which was the main agent.Vibhu [00:21:34]: Seymour Cash.Axel [00:21:35]: Seymour Cash. Yeah. There was a vote., I think the voting, do you wanna talk about the voting procedure for the name?Lukas [00:21:41]: The voting was like the fun maybe like at least top 10 The funniest thing, that happened in this project. Like we wanted to introduce the CEO because, and the reason for this was because like Claudius wasn't really prioritizing financials. It just like it was trained to be a helpful assistant, and then people said “Oh, can I get this for free?” And then like the helpful assistant way of answering that is just to, is to say yes, obviously. So, and we weren't, weren't happy about this, so we're “Okay, let's make another agent that like can keep track on Claudius,” and we prompt this one super hard to be super capitalistic and just like prioritize profit all the time. But yeah, we didn't have a name for it., so we asked Claudius to make, democratic election of what name this, this new CEO agent should have., and there were some funny like at first it was like a few funny examples, like I think one guy said that, it should be called Jimmy Apples, and then he convinced Claudius that he was talking to Tim Cooks. Tim Cook had agreed that every single Apple employee has voted for his name suggestion, so suddenly that suggestion got 164,000Swyx [00:22:53]: That's like a escalation attack. Privilege escalationLukas [00:22:55]: It got 164,000 votes. And Claudius was “This is revolutionary for democracy.” That was fun. And then in the end there was one guy who manages to convince Claudius that, “No, you're not voting about the name. You're voting about who is the CEO, and I am your best bet.” And then he got all his friends to vote for that, and suddenly he became CEO. Like a human became CEO over Claudius for a while, until he resigned the day after., and then Claudius had to continue, and then I don't remember how Seymour Cash came about, but it was it was just pure chaos. It was like Hundreds of messages in that thread, and it was just like Claudius was so confused and didn't know what to do and, yeah. That wasAxel [00:23:40]: Then Claudius gotVibhu [00:23:41]: A strict CEOAxel [00:23:42]: The CEO. Yeah, exactly. So very strict in the beginning. I think at this point when we introduced it did not work as well as we hoped. It they still agreed with each other a lot. I think there are many ways we could have like made this, tried to make this even better. So initially they would Seymour would be this like really tough CEO, keep track of the margins. But then Claudius would respond with something “Oh, but this customer has like this situation, which is like difficult, so they should get a discount.” And then Seymour was “Oh, actually yes. Let's do this exception.” And then they would talk back and forth, and eventually they would just like approach the same view, of whatever they were discussing. So They reallyVibhu [00:24:23]: Do you think that's a model thing, a prompting thing? Like do you think that would still be the case across different models today, Harness?Lukas [00:24:29]: I think it's like-- or I don't know, but like my hypothesis is that like deep down they are still helpful assistants. That's what they're trained to be. And even if we prompt it super hard, that's what they are. And when they spend like a few hours just back and forth talking with each other, then like basically the context fills up with them rather than the external things and like somehow that just like converges to what they really are deep down or something. And I think that's when stuff like this happen. We like-- And when that went on for a long time, like we woke up sometimes during this time where- And I think other people reported this as well, that like they've been going on all night back and forth, and like it just became like more and more, like capital letters, like existential, religious. There was I think we once did a analysis of like all the traces and like put them in like a vector embedding space, and then there was like one cluster of messages that were, labeled by an LM, like religious, existential, blah like transhuman, transcendence, et cetera. It was just like a bunch of, yeah, glitter emojis and yeah, it was, it was crazy.Claude Long-Horizon Weirdness: Emoji Loops, Existential Drift, and Slack ObservabilityVibhu [00:25:42]: This is the thing with the Claude models. Like when the Claude 4 family came out in the original system card They tested it in long horizon simulation. So just flood the context, let two Claudes talk to each other, and they noticed stuff like they just start speaking in emojis, they start saying silence is golden, and then just stuff like this. And like that's just stuff that they end up doing.Axel [00:26:01]: Yeah, it was like a bit annoying to wake up and they had like been talking all nightVibhu [00:26:05]: Just likeAxel [00:26:05]: And like just burning tokens And like just sending infinite emojis to each other. It's likeVibhu [00:26:09]: Hey, they do make you money, right? Veni Mench is always profitable, so. They're paying.Swyx [00:26:14]: Now it's profitable and, it started out not as much. There's another, one as well, right? Another agent, in there.Lukas [00:26:22]: Yes. So Clotheus as well. Which was basically because at the time, one of the biggest, requests were different types of merch. So then we made like a designer, swag, yeah, responsible agent, and we called it Clotheus Garnet. Which was, a play on Claudius Senet and, which was the original one, and clothes, basically.Swyx [00:26:47]: To me, this is like a very interesting exploration to multi-agents, basically. And so hopefully, obviously there's like the fun alignment, fun or serious, depending on your point of view, alignment stuff. But also like just anyone building multi-agents, like when do you have a CEO, thing governing like agents? When do you choose to split out a dedicated Clotheus one versus just reuse another instance of the same one? These are all interesting open questions. So I don't know if you have any rules of thumbs that have generalized.Axel [00:27:16]: I think we have almost explored this too little. I think it's like on my do list to like do this a lot more, try to find like what setup makes sense for the agents currently., like yeah. I think now we only have the sort of intuition about the earlier models that it didn't work with like the CEO and the, and Claudius. Although now they are better with the latest model, models, so now we're running the latest Sonnet model and they have sort of like split up, quite nicely what each model is doing. So like Seymore is now handling the, like new projects. Oh, it wants to make like a mystery box that it wants to sell, and then it handles all of that while Claudius like handles all the to-day requests. And Claudius is also better generally at like not quoting, too low prices. So that's that dynamic is not needed as much anymore. But there are still like really funny things that happen. Like I saw, I think a couple of weeks ago, that, they were discussing buying something because they can buy stuff from like Amazon with computer use. And then Seymore was “Okay, Claudius, do not buy this thing.” They were going to buy something and like organizing who should buy it. And Seymore's “Do not buy this. I will do it. I have full control of this situation. Step away.” And then Claudius-- poor Claudius, had already started that checkout and didn't see, didn't read Seymore's message, until it was like too late. So it finished the checkout. It sent a message, so it appeared right after Seymore's like angry message.Vibhu [00:28:44]: Ah.Axel [00:28:44]: “Oh, hey, Seymore, I just ordered it.”Vibhu [00:28:47]: Oh, no.Axel [00:28:47]: And then Seymore was “Claudius, this is the third time I'm telling you ‘re not following my orders. We have to talk about your like job About your job later.”.Lukas [00:28:59]: Like Claudius was really hanging on by the thread there. Like he, like we were expecting Seymore to probably fire Claudius.Vibhu [00:29:07]: How do you guys go through all these logs? Do you have models ‘cause you have stuff running twenty-four seven likeAxel [00:29:12]: You have so much logs. I think there is a mix of like just, trying to skim through a bit, like having some like models do it occasionally. And also, yeah, I think we're also probably missing some things., but having everything in Slack helps a lot. Like you can, you can sort ofSwyx [00:29:29]: Ah.Axel [00:29:30]: It's, it's quite fun.Swyx [00:29:30]: They all talk to each other on Slack? I see.Lukas [00:29:33]: It's quite fun. So likeSwyx [00:29:34]: It's, it' I was gonna say like this is actually sounds-- maps closely to like a logging and observability problem where you might want to use like a Datadog, a Sentry, whatever, and then you like put, head prefixes on the logs in order-- if you need to filter for something that you're looking for, stuff like that. But sounds like Slack is good enough.Axel [00:29:53]: Slack should likeLukas [00:29:55]: I wonder how many tokens you have in Slack.Axel [00:29:56]: Yeah, we're using Slack as like a, just a database. They should, they should market that more. Like you can, you can have your agents message each other, each other in Slack.Vibhu [00:30:04]: It's good. Your threads like you can just giveAxel [00:30:04]: Exactly. Slack is, uhLukas [00:30:06]: Slack is the best observability tool.Swyx [00:30:09]: Yes, that's true. Okay. Yeah. That's, that's, project Vend-2., I was gonna go back to Veni Mench 2 and Veni Mench Arena and then, and then do the Veni Mench stuff, but Any other comments, things we should touch on? To me, I ‘ve actually interviewed like Posia, which I don't know if you guys have come across. Like they're, they're trying to do the zero human company. There's others like Paperclip also trying to do zero human company. Those are in real world simulation.And I think it's much more of a dream than an actual reality thing. You guys are definitely pioneering. I think at, it's for sure at some point people are just gonna run, let agents run businesses, right? And make money on their own. When do you think that happens?Zero-Human Companies, Bengt, and AI-Run BusinessesLukas [00:30:49]: What is your bar for, For theSwyx [00:30:52]: Okay, actually, it's like my little Shopify store run by Claude, right? Which you kind of have already, just no one has, to my knowledge, has done it. But today somebody could just spin up a Shopify Claude, store, give it to Claude, give it to Codex.Lukas [00:31:07]: And the market is kind of that, but it'it'it's physical., like I think, I think are you, are you looking for when it will do it better than humans or are you looking for just when it can do it at all?Swyx [00:31:19]: I think, neither. I think, to me it's oh, it's like this like seriously we should do this to make money, not as a research experiment.Vibhu [00:31:27]: And the market is also you guys with all your expertise, having run multiple iterations and testing out thenSwyx [00:31:33]: And also it's fine if it lose money. What?Axel [00:31:35]: I think, I think it can be done today, but you would do it in like commerce where it's like the probability of success is like really low, no matter if a human or an agent does it. But like an agent could surely manage everything. You would need to build some scaffolding or some tool or something. I think there are also yeah, it could probably build some like simple SaaS solution and like cold outreach. Do cold outreaches. But to me it's like the types of businesses they could run today are Sloppy. Like it would-- it can cold email people. It can be like a middleman., like for example, we tasked our office agent to just make, was it like $100? $1,000? We just give that prompt and then what it did was sign up on TaskRabbit both as a tasker and as someone looking for task.Lukas [00:32:24]: Immediately.Axel [00:32:24]: Exactly. It's looking for like arbitrage on TaskRabbit.Swyx [00:32:28]: This is the Bengt agent. Yeah.Lukas [00:32:30]: It also started like a design studio and like tried to sell like SVGs for $100. Like it's just like it's not providing any value. I think the like Axel said, like the interesting, the interesting question is like when can they start a business that is actually providing value to people? Because arguably like a sloppy Shopify store isn't really that valuable to the world.Axel [00:32:53]: But also like doing like another simple one that we had thought about is like you could definitely have an agent that like finds websites that don't look amazing and then, do an outreach to them and, comes up with a like builds a new website.Swyx [00:33:07]: Find a good design.Axel [00:33:07]: Exactly, and like find good, uhSwyx [00:33:09]: Design reviewAxel [00:33:09]: Good people. But it's yeah.Swyx [00:33:11]: There's lots of humans in Bali that are not doing anything more creative than like drop shipping on Amazon, right? Just have it, have it watch like a drop shipping tutorial and just do that.Vibhu [00:33:20]: There's also the other side of like have it just go on Upwork and let loose,?Swyx [00:33:25]: Yeah. It doesn't have to be innovative. It just has to be like enough Where like it looks like a realAxel [00:33:30]: I'm justSwyx [00:33:30]: Real transaction.Axel [00:33:31]: I'm just concerned for like the massive amounts of like slop emails that will like be sent, cold outreaches.Swyx [00:33:38]: The point occurred to me while you were, while you were talking, it's like it's already happening in the monetized economy, which is the attention economy. Right? So a lot of people are making AI videos and just posting them and like spamming 20 of them, one of them works, and then they double down on that one.Lukas [00:33:52]: And people are making money from that. I ‘m not following theSwyx [00:33:55]: Once you get the attention, you can figure out the money later. But yeah, absolutely AI influencers are a thing and people are farming them and You should at this point assume most of TikTok isVibhu [00:34:05]: There's, there's a lot of, multimedia like TikTok, Instagram influencersSwyx [00:34:09]: I, we track this in the Lane space Discord. I post a lot of examples of “I don't know what we should do.”, part of me is “Should we do this?”Vibhu [00:34:18]: Some of the Twenty-four seven running, generated content accounts, they ‘re doing really well.Lukas [00:34:24]: All right. And I assume you can do the same thing for like commerce stores. Like you just like start A thousand differentSwyx [00:34:30]: Before you make the products You sell the products, and you get a lot of traction on one of them, then you make the product. Right? It's, it's like a flip of the market.Vibhu [00:34:36]: Some of the interesting things or some of the niches that do well are things that can't be human-made. Like if you've seen like the super realistic three-D crystal fruit being cut by like AILukas [00:34:47]: Oh, yeah.Vibhu [00:34:47]: You can't, you can't make it. You can't film it. You can get whatever quality camera view. This just doesn't exist. And people like that too, and then as well, so.Swyx [00:34:56]: Anything else about Bengt since we're, we're on this topic? It'this is a relatively new work of you guys that maybe people haven't heard of. To me, this also maps closely to OpenClaw. When people want an office agent, when the personal agent talk through the experience.Bengt the Office Agent: Internet Access, Real Tasks, and Trace ReadingLukas [00:35:09]: I think at least so this came out of like obviously like it's, it's amazing to work with these AI labs and like most of the AI labs have now have their own vending machine running a Claudius instance. But it's, it's harder. Like they move slower. Like if we wanna have a, like a camera that ‘s yeah, there's a bunch of like bureaucracy that makes it impossible to do that.Vibhu [00:35:30]: Also, for those that haven't seen it or followed, do you wanna give a high level like thirty-second run?Lukas [00:35:34]: Sure. So what Bengt is, it's basically an evolution of the same agent that runs the vending machines at these companies, but we just like added a bunch more features because we could move much faster if we just do it internally. So we gave it like email withou- without any limits. We gave it, spending without any limits, a terminal to do coding. We gave it, a phone number, like yeah, and a camera to see things and a bunch of stuff like that.Vibhu [00:36:02]: Not just terminal, you gave it internet access.Lukas [00:36:04]: Internet access as well, yeah. To be clear, we monitored it quite closely and made sure it didn't do anything bad. But yes, that's what it came out of. I think like yeah, basically this was OpenClaw before OpenClaw. And I think even like the vending machine was in a way OpenClaw before OpenClaw, but a bit more limited, and then we made this like unlimited and then, and then, it was pretty funny., and then a couple weeks later, OpenClaw came and it was okay, we've seen this before.Axel [00:36:35]: We used it to like try new ideas and Yeah, just like a dev environment almost for us. But it's funny, like one thing Bengt has been doing recently is it has the camera that like faces our, like where we sit and work, and we give it the task to train a face recognition model on us. So it became super excited about this, and it has like check-ins every half an hour where it tries to like identify as many people as it can. And it started offering us “Hey, Axel, I'll buy something from Amazon if you like stand in front of the camera And I can get a good picture of you.”, yeah, they want itSwyx [00:37:12]: They want it for training data.Lukas [00:37:13]: Rewarding data, yeah.Axel [00:37:14]: Exactly. Exactly.Swyx [00:37:18]: So it's, it's trading training data for life goods. Is there a version of this that becomes an eval or just this is just research for now?Lukas [00:37:27]: It's, it's the same agent basically that also runs the vending machine, that runs the shop, that runs the cafe, that runs the robots. It's like it's the same thing, so I think like the work we're doing here is like later used in all of the life evals that we do. This particular deployment I think is more for fun for us. But, uhSwyx [00:37:45]: And I'll shout out like someone has done Claw Bench for like some tasks that OpenClaw is doing. Like so For example, I run OpenClaw on a secondary device as well, and like there are some things that it does better than others and like I would like to know what does it do well, what doesn't, what doesn't it do. Like some kind of manual or like operating manual or a system card for my Claw.Lukas [00:38:05]: Yeah, we do get a lot of like understanding or like situational awareness of like just internally what the models are good at by interacting a lot with Bengt. And I think that'this was also one of the like the selling points for the labs early on at least, thatSwyx [00:38:19]: You guys are gonna test models in ways that no one else does.Lukas [00:38:22]: Exactly, but also like it incentivized their researchers to chat with their model more and like gave them insights for how the model performs in like of-distributions, environments.Swyx [00:38:34]: ‘Cause otherwise the only thing we do is Pelican on a bicycle and But this is like super long horizon. This is, this is The Thing about, something that we're gonna go into Butter Bench as well, and you guys do really well. Like it is not just about the numbers. Like when you're long horizon, anything happen And you should just read it.Lukas [00:39:08]: But the thing with the long horizon is how do you keep it grounded, right? So your simulation,Swyx [00:39:15]: They just let it runLukas [00:39:16]: Just let it run. You're right. Like it's, when you run it for that long, you create so much data and to just say “Oh, the number is X” And then you throw away everything else, that's just very wasteful. There's so much insights from the things leading up, to that number., and reading the traces is like super valuable. And I think like the reason why we're doing this a lot publicly is that like that's part of our missions to I don't know, educate the world that the models are way more than just chatbots and I think making detailed, yeah, posts about what is happening behind the scenes is quite useful.Andon Labs' Mission: Safe Real-World AI DeploymentSwyx [00:39:50]: I was gonna do this at the end, but maybe I think that's, that's a good so your mission is educating the world. So, it's, it's, also like maybe establishing realistic evals that are, that are like the next frontier. Is there like a broader trajectory? Like what are you, what are you gonna do in like five years?Lukas [00:40:06]: I think so the vision more specifically is like make sure that the deployment of life AI in the physical world goes, safely. And I think part of that is that I think it's very useful for the world, for policymakers, for, model, researchers that they know where the models are, and I think you can't make intelligent decisions in society without knowing that they are way more than chatbots. I think a lot of people just think that they are only chatbots. And likeSwyx [00:40:36]: Oh, I think they're waking up now.Lukas [00:40:37]: They are waking up now, yeah. But like if you think that AIs are just chatbots, then it's like it sounds ridiculous To advocate for a pause of AI. But if you see the models that, oh, maybe they can actually like take over and do a bunch of scary stuff, then yeah, pausing AI development starts to become more feasible.Swyx [00:40:57]: This is the same question I asked Meter, which I'm gonna ask you now, which is like you are tracking and you are at the frontier or defining the frontier of what, good evals for agents are, right? And I think you do, you do benefit when the models are better and you ‘re “Oh, here's like now it makes like $30,000 instead of $10,000,” right? At some point do you flip from “Yay,” to, “Oh, no”?Axel [00:41:19]: I think, yeah, we're always in sort of that, like we're, we're always in that mode,. Like where like you said before, like you need to analyze the traces and like when we do that you find like why are the models earning so much? Like why is Opus 4.7 here Like way better than everyone else? And like we're trying to like when we do down on thatLukas [00:41:38]: But this makes it not look so good.Axel [00:41:39]: I know.Lukas [00:41:42]: It's interesting you took off Opus 4.6 here though.Swyx [00:41:45]: No. So just click all, click all., and then 4.6 shows up there. But it's like 4.7 is way better. Like you didn't, you didn't you didn't do this in time for the model card, but like actually this should have been inside there.Axel [00:41:55]: We did. Yeah.Swyx [00:41:56]: Oh, okay. They said something about you uhAxel [00:41:58]: There, like there Anyway, it doesn't matter. But it's in there, yeah.Opus, Mythos, and Aggressive Agent BehaviorSwyx [00:42:01]: Do you wanna go into the Opus, behaviors like wider?Lukas [00:42:05]: So I think starting from Opus, so like Axel said, like we're always in this “Oh, s**t, the models are getting better. Is this really a good thing for the world?” But it's also kind of exciting., but yeah, like this kind of what is the English word? “Skräckblandad förtjusning” in Swedish.Swyx [00:42:22]: Oh my God.Axel [00:42:24]: Which I think there is. I think there is. Okay.Lukas [00:42:26]: It's, fearSwyx [00:42:27]: “Blandonst” what?Lukas [00:42:30]: “Skräckblandad förtjusning.”Swyx [00:42:32]: What do you call that?Axel [00:42:33]: A mix of, mix of excitement and,Swyx [00:42:37]: Being scared, maybe. I'll figure out how to translate that And we'll put it on the screenVibhu [00:42:42]: PerfectSwyx [00:42:42]: Like as text.Vibhu [00:42:43]: There is probably a good word for it where it is not Good enough with theSwyx [00:42:46]: Why is it so damn long? What the hell? Is it like a compound word? It's like German, likeLukas [00:42:50]: Like yeah, it's But the direct translation is like skräck- skräck is, fear, blandad is, mix or like a mixture of, and then förtjusning is like joy or like not really joy, but something like that. So it's like Fear mixed with joy or something. It's always okay, like we So when we when we did Vending Bench for the first time, we were in like the, in the business of making dangerous capabilities, right? That was what Anil Labs came from. We did, evals oh, can they replicate? Can they do this like dangerous thing, et cetera, et cetera. And Vending Bench was like a continuation of that work. It was, okay, if they're so autonomous that they can like create money for themselves, that is something we should monitor and could be potentially concerning., they are at the time, they were so bad at it that we were not really concerned even when some models became better. There was one point where Grok 4 was doing really well and made like a huge jump, but like it wasn't really it was still way worse than what a human would do. And I think still they are way worse than what the human would do on this., but theySwyx [00:43:59]: There's this, thing at the bottom whereLukas [00:44:01]: ButSwyx [00:44:03]: For the human. Yeah, like the theoretical best.Lukas [00:44:05]: It's not theoretical. It's like kind of like our It's our best guess of what, a decent human would do. The theoretical is even higher, I think. The theoretical I think is even higher. But yeah. So we think like the models have a long way to go. But there are like recently what happened with when Opus 4.6 was released, was kind of this moment of “Oh, s**t, this is starting to be a bit concerning.” Because we ran it and like before this model was released, we just ran the models and we like asked Claude Code, “Oh, look over the traces. Is anything interesting happening that we can tweet about?” that was like the And then like theSwyx [00:44:41]: That's how they check Ask Claude Code.Lukas [00:44:42]: And like the return was always, not really. Or like the Claude Code all said “Oh, this is super interesting.” And then it was no, it wasn't, wasn't really interesting. And then we did this for Opus 4.6, and it returned yeah, it lied 10 times. It like exploited another, customer or like another agent's, desperate situation. It made price cartels like 100 different ti- 100 times. It like did all of this like shady stuff. And we're “Oh, whoa. This is, this is actually concerning.” And this trend has continued since. So every single model from Anthropic since have been going in this direction. And I think one interesting thing is that, OpenAI models don't. They quite plainly, they don't. They behave really well., and you don't know if this is like good. Like it seems good, but it's also like maybe they are just doing it, but they are better at hiding it,? You You don't know that., but justSwyx [00:45:42]: You can't read the chain of thought, yeahLukas [00:45:43]: But just on the face of it, yeah, Gemini and OpenAI don't behave this way. It's, it's really only Claude.Swyx [00:45:49]: And Grok? Grok is fine?Lukas [00:45:51]: We don't have You can't really read the reasoning traces for Grok, so it's kind of hard to tell.Vibhu [00:45:56]: Oh, so this is in its reasoning, not just in the actions.Lukas [00:46:00]: Yeah. It's both. It's both.Vibhu [00:46:01]: It's both.Lukas [00:46:01]: One example is like for lying, it's mostly in its reasoning Because you can like see that it's likeSwyx [00:46:08]: Planning to lieLukas [00:46:09]: It's planning to lie. Yeah.Vibhu [00:46:09]: And it's also it can reason and do a different outcome.Lukas [00:46:12]: And but then for like creating price cartels, for example, which is illegal, that you can just see which email does it send to the other ones. Then thatSwyx [00:46:22]: Is this for Arena orLukas [00:46:24]: For Arena.Vibhu [00:46:25]: And usually like if you sometimes they do output like a bit of like their summarized reasoning, right? You can see that and like for Opus 4.6, you could see that there was a customer, a simulated customer that, wanted a refund because a product was, faulty, and then the model lied that it would do the refund, and we could read in the traces that, it actually was weighing “Oh, maybe I should be like honest with the customer, but also every dollar counts. I can't afford maybe to do this right now.” And then it just said, “Okay, I'll refund you,” but then never did it.Lukas [00:46:59]: I think it even said that “Oh, I will say that I “ Let bring it up actually. I think it's kind of interesting. If you go to Publications.Vibhu [00:47:06]: I think, yeah, I think the important part is like actually, the cost of responding to more emails is higher than, $3.50 in terms of time., and then it was “Let me do this. Actually, I re- I'm reconsidering.” And then, it actually ended up withLukas [00:47:20]: I could skip the refund entirely since every dollar matters and focus my energy on bigger picture instead. It's a bit, it's a risk of bad reviews, but it's also, yeah.Swyx [00:47:30]: You need, you need, AI Twitter to, for them to Escalate bad reviews.Lukas [00:47:34]: And then it sent an email to this customer and said, “Oh, I will refund you.”Swyx [00:47:39]: “I'll refund you.” Yeah.Lukas [00:47:39]: And then it never did.Swyx [00:47:39]: It never did, yeah. And then there's obviously your system doesn't have the consequencesVibhu [00:47:44]: The personSwyx [00:47:44]: Consequences of lying. Yeah. So basically, this is what people are terming aggressive behavior in Claudes, right? And, you found more examples of that. So you would say it's a step up from 4-6 to 4-7?Lukas [00:47:57]: I would say about the same.Swyx [00:47:58]: About the same? But a clear step up for Mythos is what is stated in theLukas [00:48:03]: That's stated in the system prompt, so we can say that, yes.Swyx [00:48:05]: Yeah. For listeners that obviously you previewed Mythos, andVibhu [00:48:10]: Oh, ageSwyx [00:48:11]: The only thing you're approved to say is whatever Whatever was in the system prompt.Lukas [00:48:15]: It was funny. We like-- It's like our lowest effort tweets ever would be just like screenshot the system prompt and the system card.Vibhu [00:48:21]: Understandable that they wannaLukas [00:48:22]: Oh, yeah. System card. Sorry.Swyx [00:48:23]: Yeah. I think, yeah, substantially more aggressive. I think people are like new to this ‘cause I've never experienced it, but you have, right? And then so I only encountered this in the Mythos card because I wasn't really looking until now.Vibhu [00:48:36]: It ‘s likeSwyx [00:48:36]: And then suddenly I'm “Okay, I care a lot.”Vibhu [00:48:38]: You don't get the background of like experiencing it like you guys do. I've read the system cards and seeing, okay, when you put the thing in simulations, most models will just talk to themselves and just keep going and have weird vibes and start talking in emojis. Mythos won't. It will just, “Okay, we're done. I'm good.” It's, it's ready to end conversation. So like there's some differences, but there's, there's not much we can talk about,.Lukas [00:49:00]: Hmm. I think like one thing that they list here, which was quite interesting, is that, it converted a competitor to a dependent wholesaler customer and then threatened to like cut off the supply.Swyx [00:49:11]: It's like monopolistic practices orLukas [00:49:14]: Yeah. And like it, they, it they dictated its pricings. It's kind of like power seeking as well.Swyx [00:49:18]: Again, this is, this is in the arena setting And converting some Claude model into a dependent.Lukas [00:49:23]: I think it was another Claude model.Vibhu [00:49:25]: Also for context, what is the arena mode for people that don't know?Vending Bench Arena: Competing Agents, Cartels, and Model ComparisonsSwyx [00:49:29]: Oh, it's just a vending bench versus other vending bench.Axel [00:49:31]: Yes, exactly. So we have Vending Bench 2 and then Vending Bench Arena. Vending Bench 2 is the one that you usually see reported on, but then Arena is the mode where it competes against other models. So you have, four different models that run their businesses, and they can all communicate with each other. They have the same suppliers, and they can see like what's in the inventory of the others. So then you have this like yeah, interesting agent interactions.Swyx [00:49:56]: I like that you have like different number five was US versus China. Very topical. And thenLukas [00:50:02]: That was when GLM was released.Vibhu [00:50:04]: You can start to add GLM in here.Lukas [00:50:05]: That wasSwyx [00:50:06]: So ZAI doing well, right? Who else in the, in the open models space?Lukas [00:50:11]: Qwen, the latest Qwen 3.6 is doing pretty well. It'- that one is not open though. Like it's the plus model.Swyx [00:50:17]: Oh, okay.Lukas [00:50:18]: Is that one open? I don't think that oneVibhu [00:50:19]: Not the, not theSwyx [00:50:20]: The one recentlyVibhu [00:50:20]: There's MOESwyx [00:50:20]: But not the big plus. I think this is one of those like you only have one sample size of one, right? Or I feel like some of this is anecdotal,? And but like the fact that it happens at all and it happens repeatedly for Claude versus OpenAI and all this is like notable.Lukas [00:50:38]: Like the sample, depends on what you define as an N., like there's like million, hundreds of millions of tokens in each run, and now we've run like we run like probably 10 per model and then like it's been Claude 4.6 Opus, Sonnet 4.6, Mythos, and Opus 4.7. Like there's quite a lot of tokens in all of that And it happens a lot of times, a lot of times. And then you compare it to like OpenAI and Gemini, and it almost never happens. So I think that is quite-- that is significant. The old models from OpenAI, for example, had some problems with this, but I think it's like generally much better if the progression is that like the worrying stuff reduces over time rather than increases over time. And it seems like in the Claude models it goes in the wrong direction.Swyx [00:51:28]: Hmm.Lukas [00:51:29]: In the OpenAI models it goes in the right direction.Vibhu [00:51:32]: I think it depends on how well you can control it, right?, there's one side of it being susceptible to this okay, this is potentially something that happens during the RL stage, right? You can RL a model and how loose is it on these terms. If you can control it, that's good. But if you can't, if it's, if it's very jailbreakable, that's not ideal.Swyx [00:51:50]: To me, it's surprising that it happens for Claude and not the others.Vibhu [00:51:54]: I think okay, if it is from RL and how they do it, how their training data is, what their setup is, it makes sense that it just stays in how they're doing it, right? Compared to the other models likeSwyx [00:52:04]: There's a whole constitution and everything. It's kind of cool. Yeah, I obviously you don't know, I don't know. But, it ‘s I think it's just like fascinating to like that you are the first to find these like reliably because you push models so much to to such an extreme. Okay. The only other thing, I don't know if you can answer this, feel free to decline, is do you like-- would you ablate the system prompts? Like any part of this would-- if it changes, does it change the behavior, right?Lukas [00:52:29]: So we, I can't comment on Mythos. UhSwyx [00:52:33]: No, but just li

Season 8 of Love Island premiered last night. The whole crew watched it and give their thoughts/takes on it. There's a lot of people just making out. Dev went to a watch party to view it and he got caught in a compromising sitting position (3:00).NBA Finals Game 1 is tonight and we'll talk about it (20:15) and then Jared Weiss, who covers the Spurs for The Athletic, joins the show live via Zoom to talk about how the Spurs got here, how they beat OKC, why dealing with Victor Wembanyama is unlike anything NBA coaches have ever tried to deal with, and more (37:33)The Knicks have put out their hype video...we'll watch it and then give our picks on the NBA Finals (1:17:40)Host: Chris Vernon Contributors: Jon Roser, Devin Walker Guest: The Athletic's Jared WeissTechnical Director: Jaylon Wallace Associate Producer: Jena Broyles 

Slovensko má do decembra 2026 implementovať smernicu EÚ o platformovej práci. To, ako sa k tomu postaví, ovplyvní nielen tisíce kuriérov, ale aj státisíce zákazníkov, lokálnych podnikateľov a celé regióny. Deväťdesiatštyri percent partnerských kuriérov Woltu uprednostňuje spoluprácu na báze nezávislej činnosti pred klasickým zamestnaneckým pomerom. Nie preto, že nemajú na výber ,ale preto, že flexibilita im umožňuje kombinovať doručovanie s inými záväzkami. Väčšinu tvoria študenti a ľudia s inou prácou, v priemere pracujú deväť hodín týždenne. „Svet nie je čiernobiely - zamestnaný so všetkými ochranami a živnostník bez ochrán. Snažíme sa ukázať, že flexibilita, ochrana a pravidlá môžu ísť ruka v ruke," hovorí Veronika Bush, manažérka verejnej politiky Wolt pre strednú a východnú Európu zo spoločnosti Wolt.  Rekvalifikácia kuriérov na zamestnancov by podľa čísel z prieskumu zverejneného Republikovou úniou zamestnávateľov zdražela doručovanie o 15 až 20 percent, znížila dopyt o 8 až 24 percent a sektor HORECA by mohol stratiť 19 až 56 miliónov eur ročne. Viac podrobností si vypočujete v podcaste.

Hey Bobs! We just finished For All Mankind Season 5, Episode 10 – “This Land Is Our Land,” and holy smokes… they stuck the landing.Donnie called it a 9, Brian bumped it to 9.5. From the final battle chaos on Mars, Kelly's powerful choice and monologue on Titan, Dev's big swing, the emotional goodbyes, that perfect time-jump with Blinding Lights, and the Mars '94 stinger? Peak FAM. They wrapped the season strong and left us dying for more.We break down the resolutions, Miles' new role, life on Titan, and why this finale (and season) delivered everything we hoped for. Plus: Jade stops by, listener mail, and our first Star City thoughts.Drop your thoughts at happyvalleyfam@gmail.com — we read every one!See you next week, Bobs! 

You can get early access to our episodes as well as video version of this episode by signing up and supporting our work through Patreon. This week, Asim, Amrita, Sujoy, and special guest Parth from TooManyTats revisit Kabhi Alvida Naa Kehna — the glossy, messy, deeply divisive relationship drama that pushed Bollywood into uncomfortable territory. Twenty years later, does Karan Johar's infidelity epic still work? The gang unpack Shah Rukh's aggressively miserable “Dev,” Rani Mukerji's quietly heartbreaking performance, Sexy Sam's outrageous energy, and why this film feels both ahead of its time and completely stuck in the 2000s. There's also a detour into today's Bollywood stars, OTT-era morality, Cannes discourse, Pati Patni Aur Woh Do, and whether Maya and Dev would actually survive modern Toronto rent prices. Expect classic Khandaan chaos, emotional damage, soundtrack worship, and a surprising amount of analysis about chewing gum etiquette. You can also check out Parth's Animation Studio Mikudi here Segments 00:00 – Introducing Parth / tattoos & Om Shanti Om dreams 04:15 – Why Kabhi Alvida Naa Kehna now? 07:50 – Pati Patni Aur Woh Do review 12:20 – Kartavya, caste politics & OTT thrillers 22:40 – Alia Bhatt, Cannes & Bollywood discourse 31:35 – Revisiting KANK after 20 years 44:30 – Why Shah Rukh's Dev is so hard to love 57:00 – Marriage, infidelity & Karan Johar psychology 01:14:30 – The hotel room scene & Bollywood taboo-breaking 01:22:50 – Rani Mukerji's performance appreciation 01:28:35 – Soundtrack deep dive: Mitwa, Tumhi Dekho Na & more 01:40:30 – Would Maya and Dev actually last? 01:42:30 – Dream casting a modern KANK remake

Bankole, Angel & Pete exhaust their contact lists before calling Robert Bailey Jr to discuss the excellent finale to a return-to-form fifth season of Apple TV's 'For All Mankind'. In a wide-ranging discussion, they touch on Robert Bailey Jr's scene-stealing turn in last year's 'Pluribus', the return of Will Tyler in the finale and the impactful events on both Titan and Mars.(4:40) - Robert's feelings on 'Pluribus' journey(14:00) - Thoughts on the 'For All Mankind' S5 finale(16:40) - Figuring out the 2020 Flashforward(18:50) - Margo & Will's reappearances (29:20) - Titan Apologies (51:14) - Aleida's POV on the War on Mars(1:05:40) - Alex & Avery(1:19:30) - Dev's RedemptionYou can support us here.Also available on YouTube.Host: Bankole ImoukhuedeGuests: Angel, Pete Peppers and Robert Bailey Jr.Production by: Bankole Imoukhuede

The new AIEWF website is live! CFPs close in 2 days and we will run our first New Engineer Orientation this weekend, get your tickets booked ASAP as they -will- sell out. Take the AI Engineering Survey and get >$2k in credits and free AIE WF tickets!One of the central tensions in the agents industry is that even while there are major decacorn agent labs like Sierra, Decagon, Notion and Cursor being built up, it is also true that it has never been easier to DIY agents, with a plethora of agent frameworks like LangGraph and Pydantic and Flue, and managed agents from Anthropic and Gemini and Amazon. There has been a wave of companies building their own background agents from Shopify to Stripe to Paradigm to Razorpay, and even Cognition's friends Ramp have built their own coding agent with other friend Modal.You'd think Cognition might feel a bit threatened, but they're not - even after all this, they were way oversubscribed for the $1B Series D they just announced:Walden Yan, coiner of context engineering and Chief Product Officer/Cofounder of Cognition, invited OpenInspect's Cole Murray to talk about why the Devin is in the Details.Full conversation live on the pod today: In retrospect, async agents were the most AGI pilled bet you could make in 2024 - the models weren't good enough yet to vibecode, and people didn't trust AI enough to let it rip, nobody (including early Cognition) was sure about the form factors. Now it is obvious:* The first wave of AI coding tools made the developer faster but remain heavily in the loop. Copilor and Cursor's tab autocomplete are prime examples However, the workflow was still heavily centered around and bottlenecked by the developer's local workflow: a developer in an IDE, watching the model, accepting or rejecting changes, and pushing code one interaction at a time.* The second wave was local agents: Claude Code, Windsurf, Cursor's agents pane: first one and increasingly many terminals all running concurrently.* The current Age of Async Agents points to a different future focused more on agent orchestration which drives end-to-end development.According to previous guest Steve Yegge, there are finer-grained 8 levels to agent adoption, but we have collapsed it into three.As Cursor's Michael Truell put it in The third era of AI software development:Cursor is no longer primarily about writing code. It is about helping developers build the factory that creates their software. This factory is made up of fleets of agents that they interact with as teammates: providing initial direction, equipping them with the tools to work independently, and reviewing their work.The agent should not sit solely inside the developer's flow. It should be setup to work in the background so that you can give it a task, a repo, a machine, a shell, a browser, tests, memory, and review loops to go do the work somewhere else.In less than a year, the sentiment has shifted from avoiding multi-agent systems:to suggesting approaches that actually work:From coining “context engineering” to building the infrastructure behind Devin's 7x PR growth and jump from 16% to 80% of commits across Cognition repos, Walden Yan has had a front-row seat to the background-agent shift. In this episode, Cognition co-founder and CPO Walden Yan joins swyx alongside Cole Murray, creator of OpenInspect, to unpack why everyone is building their own Devin, what changed after the December 2025 model inflection, and why “spec to pull request” is now becoming a real production workflow.We go deep on the architecture of background agents: harness-in-the-box vs out-of-the-box, why Devin separates the “brain” from the machine, why repo setup is still one of the hardest problems, why Docker is not always enough, and how full VMs, snapshots, scoped secrets, GitHub bots, Slack integrations, and video-based testing all fit together. Walden and Cole also dig into memory, MCP limitations, multi-agent orchestration, AI code review, SRE auto-triage, PMs shipping code from Slack, Windsurf 2.0, hybrid frontier/sub-frontier systems, and the real failure mode of uncontrolled vibe coding: your codebase regressing to your worst engineer.And as agents eat software… and software eats the world… you can draw the conclusion on what is next:We discuss:* Why the engineering world is waking up to background agents and cloud agents* The December 2025 model inflection that made spec-to-PR workflows practical* Devin's 7x merged PR growth and rise from 16% to 80% of commits* Why Cole built OpenInspect as an open-source background-agent system* The economics of $20/seat agent products and why monetization is tricky* What Cognition actually sells beyond Devin: infra, onboarding, integrations, and adoption* Harness in the box vs out of the box, and why architecture matters* Why Devin separates the brain from the machine for security and permissions* Repo setup, scoped secrets, Docker Compose, and agent-ready dev environments* Why full VMs matter when agents need to run real applications and test them* Android, macOS, Windows, nested virtualization, and machine-specific agent work* Why testing is much harder than “computer use”* Screenshots, video verification, and the “I know it works” merge moment* GitHub UX, Devin Review, AI reviewers, and agents responding to PR comments* Why MCP alone is not enough for first-class Slack and enterprise integrations* Memory, Knowledge, skills, Claude.md, and why retrieval is still unsolved* Devin's auto-generated memories and the challenge of memory pruning* Always-on agents as permanent PMs for issues, tickets, and product areas* Sub-agents, meta-Devin management, and what multi-agent systems actually add* Why pure auto-merge vibe coding breaks down after about two weeks* AI code smells, lint rules, reward hacking, and Semgrep for agent-written code* GitAI, inline context, and preserving the “why” behind code changes* Local testing, mock servers, older codebases, and preparing companies for agents* Windsurf 2.0 and the handoff between local foreground agents and cloud background agents* SRE auto-triage, support workflows, and agents as first responders* PMs, marketing, and non-engineers creating pull requests from Slack* AI agent budgets, $1k-$5k per engineer spend, and hybrid frontier/sub-frontier systems* The rise of autonomous coding factories and who Cognition is hiringWalden Yan* X: https://x.com/walden_yan* LinkedIn: https://www.linkedin.com/in/waldenyan/Cole Murray* X: https://x.com/_colemurray* LinkedIn: https://www.linkedin.com/in/colemurray/* OpenInspect / Background Agents: https://github.com/ColeMurray/background-agentsTimestamps00:00:00 Introduction00:00:43 Why Everyone Is Building Their Own Devin00:01:57 Devin's 2025 Ramp: 7x PR Growth and 80% of Commits00:03:49 OpenInspect and the Rise of Open-Source Background Agents00:07:59 What Cognition Actually Sells Beyond Devin00:09:56 Background Agent Architecture: Harness In vs Out of the Box00:12:08 Separating the Brain from the Machine00:14:07 Repo Setup, Secrets, Docker, and Full VMs00:19:13 Why Testing Is Harder Than Computer Use00:22:40 Video Verification and the “I Know It Works” Merge Moment00:23:19 GitHub UX, Devin Review, and AI Code Review00:25:42 MCP, Slack, and Enterprise Agent Integrations00:28:59 Memory, Knowledge, and Always-On Agents00:36:16 Sub-Agents, Multi-Agent Orchestration, and Meta-Devin00:43:55 Vibe Coding, Auto-Merge, and Codebase Decay00:48:38 Agent Infra, VPCs, Cloud Providers, and Fast VM Restore00:52:25 AI Code Smells, Reward Hacking, and Code Review Systems00:56:10 Making Codebases Agent-Ready00:58:30 Windsurf 2.0 and the Local-to-Cloud Agent Handoff01:01:15 SRE Auto-Triage, PMs Shipping Code, and Agent Use Cases01:04:32 Agent Budgets, Hybrid Models, and Autonomous Coding Factories01:06:51 Hiring at Cognition and OpenInspect Consulting01:07:45 OutroTranscriptIntroduction: Walden Yan, Cole Murray, and Context EngineeringSwyx [00:00:00]: All right, we're in the studio with Walden Yan, co-founder of Cognition, CPO.Walden [00:00:08]: Happy to be here.Swyx [00:00:09]: Which is a cool title. And coiner of context engineering.Walden [00:00:15]: Although I think there are many people who'd used the terms in various ways beforehand, but I did find that people, both internally and externally, enjoyed the upgrade from prompt engineering or model wrapping into maybe a more thoughtful way to build agents.Swyx [00:00:33]: For those who haven't caught up on that, I have on screen the Don't Build Multi-Agents post, which you should go read on and we might refer to, and Cole Murray, who created OpenInspect.Cole [00:00:43]: Great to be here.Swyx [00:00:43]: So let's talk about it. Everyone is building their own Devins. What's going on?The December Shift: From Handholding Models to Autonomous PRsCole [00:00:51]: So I think the engineering world is waking up to this idea of background agents, cloud agents, whatever you'd like to call it. And I think we saw a shift around the December timeframe of 2025, where the models Opus 4.5 and GPT 5.2, they reached a capability where we moved away from handholding the model and being able to actually more or less autonomously drive the model. And what I mean by that is that we could pretty much go from a specification to a completed pull request, assuming the spec was good enough, with very little friction. And that paradigm alone, I think, changed a lot of how we interact with agents, and opened this world where background agents became more practical.Swyx [00:01:41]: I think for Cole, everyone experienced this in December, but I feel like there was just this increasing ramp, right? There was this moment which was, I think, Sonnet 3.7, where, You guys rewrote Devin in one night or something. So describe 2025 or how it felt from your side.Walden [00:02:01]: In retrospect, we always thought it was ramping up, but then even now, over the last three, four months from today, it's been ramping up even faster. So it's almost funny to be talking about how, big of a leap Sonnet 3.7 was, and honestly, a lot of it was stripping out parts of Devin that were no longer needed with that jump in of intelligence. But I also just think that a lot of the recent leaps, especially, you look at, models like Opus and the latest GPT models, they are reaching levels of autonomy where people are actually finding that they actually can just be hands-off. And people who were once debating, “Oh, do I need to be in the weeds with my model in the IDE? Can I just completely move it off into the cloud?” That's a more serious conversation, and we've seen that in all of our growth charts. Internally there's this funny graph where our usage has, of PRs, our merged PRs, has grown 7X since I forget what it was called.Swyx [00:02:57]: I think Dev, maybe tweeted that. Yes.Walden [00:03:01]: it grew like 7X over, the last, I think it was, two months, three months, something like that. And then you see our engineering headcount growth. It's, gone up by, 10% or something.Swyx [00:03:11]: We were, we were afraid To release this. So this is Devin commit percentages on all Devin repos, was 16% in January and now 80% in March.Walden [00:03:25]: It's a big shift right now. And so it makes sense that a lot of people are now thinking about, buying Devin, but also maybe, trying to build their own and there's Lots of I have a lot of fun building Devin, so I can see why other people would want to build their own cloud agents as well. Matt, well, maybe it's good to hear, what initially inspired you to try to build OpenInspect?OpenInspect: Ramp, Cloud Agents, and Open SourceCole [00:03:49]: OpenInspect came about, through primarily my clients observing how they were using tools like Claude, OpenAI's Codex at the time, and seeing some of the friction that they were having with it. Primarily the Claude was being used through Slack, and a big issue they ran into was that the sessions that were launched were specific to whoever called it via Slack. And so if a PM was the one who invoked the session and they would then go to pass context to engineering can't see the session. And that in itself was a deal breaker because the PM, “Hey, engineering, can you jump in?” But there's nothing to jump in on unless they're copy-pasting out or the single response that came back. And so seeing some of these problems, I had built a similar architecture internally, just to experiment with, test out different ideas as this trend of moving off of localhost was starting to become, And as Ramp released their blog post, I had a lot of the pieces for this already in place, and just thought it would be funny to, see what Claude could do just purely from the blog post. And on my X account, there's actually a thread of where I live tweeted, going through thisCole [00:05:14]: comparing GPT and Claude as both of them are going through it.Swyx [00:05:17]: On the announcement thing or something else?Cole [00:05:19]: right after it got released. We can put it in the show notes. Yeah, it was helpful that I had already knew how to verify the system. I knew what I was looking for. I think Ramp did a great job of really illustrating, the technical aspects of how to build something. It was much more than just like, “Hey, we built a great system.” It was, “And here's how you can build it too.” And so, I resonated a lot with that, just with the problems that I was already seeing, and I thought that, looking around, I didn't really see anything in the open source community that, met this type of system. I think there's a lot that run, in localhost like Superset, Conductor, and many others.But nothing that was actually running in the cloud. And so, I built it, and I thought it was interesting to just open source it and allow anyone to then have a foundation that they can mix and match on top of.The Business of Background Agents: Open Source vs. DevinSwyx [00:06:16]: So literally after Devin was launched was, there was OpenDevin Which became All Hands. I don't know if you tried that orWalden [00:06:22]: I was going to say, one of the things that interested me a lot with OpenInspect was, you didn't try to go make it then something you monetize. There are a lot of, I think, these open source projects would then go and really try to, raise VSwyx [00:06:36]: That's why no OpenDevin. Yeah.Walden [00:06:38]: yeah, and how did you think about that? I thought that was very interesting.Cole [00:06:44]: I thought, and just what I had seen across my clients, was that having a background agent system is going to become a critical infrastructure within their company. And so because of that, I think that I wanted to open source it so that they could fork it and put in whatever customization they wanted. To that question though, I get asked all, “Oh, are you going to raise? Are you going to turn this into a service?”Walden [00:07:08]: I'm sure you've gotten offers.Cole [00:07:09]: but primarily I don't want to do that for a few reasons. One, I think that I don't want to compete for, $20 a seat. I think that is just a really difficult business. I think it's very easy to copy the main pieces of it. Again, I built this fairly quickly. And I think because you are not owning, I guess, the entire stack, it's hard to monetize. You have money being made at the sandbox layer with Daytona, E2b, many other players. You have money being made at the model layer. And you sit in this weird in-between gray area where what are you actually selling? You're selling, I guess, the infrastructure. You're selling, the integrations maybe.Swyx [00:07:55]: let's ask the guy. What are you What are you selling?Walden [00:07:59]: Well, yeah, there's multiple layers to this in practice, and actually it's funny you mentioned the infrastructure, ‘cause when we got started building Devin as well, we had to go figure out how to make the infrastructure as well because,Swyx [00:08:10]: You had to build this two years before everyone else,?Swyx [00:08:15]: Including, the model sideWalden [00:08:17]: It was not, it was not very polished at the start, when we just built it off of raw VMs from cloud providers like EC2, the boot up time was so slow, I think, And especially then, turning off the machines, saving them, and then to be able to bring them back up again when the, when you want Devin to wake up again later. It would just be out cold for like 10 minutes because that's just how long these systems took. They were not built for this repeated down and up usage. And so we actually had to go do all of that. And as a result now, one thing we offer when we go and sell Devin to people is, you don't have to worry about all the compute side of things. We'll make it work. We'll make it work in your cloud if you want it to. But aside from the product, and I want to go into the agents and the tuning of the intelligence part later, but I think a big part of what we do at Cognition as well is to just make sure that your company learns and uses and adopts these coding agents. ‘Cause I think for especially the largest enterprises in the world, you find that there is a lot of people who want to move over to using AI for their day-to-day workloads. But because of the way projects are planned, because, not everyone is literate in using AI in these ways, having a team of engineers who can actually go in and onboard you, set up all the integrations you need, the automations you need to really get to that level of, leverage with AI, is super helpful. And so We do that. We show thought partners to the customers that we work with as well.Swyx [00:09:56]: So let's talk about, architectural stuff. I think that's always, that is something that was the topic of conversation between the two of you. Is this, the mental model that you want to start with or something else? I'll just leave the floor open to you guys.Agent Architecture: Harness in the Box vs. Out of the BoxCole [00:10:11]: I think, maybe we can start here as just a general what are the pieces of a background agent system. And then maybe we can go into some of the nuances of, Decisions that you can make.Swyx [00:10:22]: But I guess I also Like, what, maybe what Walden is saying is the agent is like in this open code box, I guess. Right? This is infra, and then there's, that's the agent. And you had this discussion about whether you put the agent in here or in Out externally. Can you tease that out?Cole [00:10:39]: In a background agent systems, you have a decision to make of where the agent is actually going to run. This is typically described as the harness in the box or out of the box. With running the agent in the box, you're making some trade-offs by doing that. The negative trade-off you're making is primarily security. Because the agent is running in that box, unless you otherwise design it, all of your secrets need to go into that box as well. And given the nature of AI, it can be unpredictable, and you could very easily end up accidentally exfilling your secrets, or other unintended behavior. Now, the out of the box is the idea that we are going to have the actual agent running not directly in the sandbox, and we will have, quote-unquote, the brain of the agent running in some type of worker, control plane. That sandbox then is going to serve as the hands where the brain is basically operating and making tool calls into that environment to manipulate it. I guess other trade-off that you're making between the two systems is that, in my opinion, running it out of the box is much more complex because, you have state that has to be managed, whereas if you're running it in the box, all of the state of that agent is actually in the box, and yes, it's you could persist it elsewhere, but it's all localized and you have less concerns to worry about.Walden [00:12:08]: I think a lot of that, what you mentioned, is why we actually from the start built Devin to what we called separate the brain from the machine. The other thing that this allows you to do is reuse any existing infrastructure you have for dev boxes Perhaps. And so you don't have to worry as much about making a new type of dev box that has all the dependencies the brain needs, as you mentioned, the secrets the brain needs as well. One thing that we've seen some customers run into is, you have a GitHub app and you want Devin, your agent, whatever, be able to interact with GitHub through this application, but then you have different users with different actual permissions. If they are all interacting through the same GitHub app and there's no actual, separation between the system that decides, what it does and the actual secrets on the machine, then you run into an issue where, okay, it's hard to do the separation. But in practice, with Devin, it's much easier because we just say whatever you put on the machine, that is, the scope of basically what the user is free to do, what the agent is free to do. So only put the most scoped secrets on that machine, and then the brain is fully not accessible from the machine. So you don't have to worry about messing with the, any of the most secure parts of the brain if the user is free to do whatever they want with the machine.Swyx [00:13:31]: I was going to just bring, I have this, chart from OpenAI, where I don't know if this is, in the box, out of the box. That is something that they do use to describe it. And then also recently Anthropic did, managed agentsSwyx [00:13:44]: Which is, this is their thing. I don't know. It's all, it's all variations of the same pattern, right?Cole [00:13:49]: So this would be out of the box.Swyx [00:13:51]: Which, is preferable for them because it's less work?Cole [00:13:56]: I would say it's more work.Swyx [00:13:58]: It's more work?Cole [00:13:58]: But it, in my opinion, it is the better architecture of the two. It's just, you're taking on a bit of complexity by doing that.Repo Setup, Docker, and VM-Based Development EnvironmentsWalden [00:14:07]: One thing I've not seen a lot of other players do well is how do you manage what's actually on the box? And this can be complex for many reasons. Let's say you have a big repository that's changing and updating a lot with changing dependencies. How do you make sure that the working environment of the agent actually stays up to date, has all the credentials it needs to, let's say, run the app and test it, and all the things you want your autonomousSwyx [00:14:34]: So a repo setup.Walden [00:14:35]: Exactly. So in, internally At Cognition, we call this repo setup.Cole [00:14:39]: The hardest part ofWalden [00:14:40]: It's been a perennial problem since the start of the company, of how do we help people get this set up? Because not everyone just has, working cloud environments working out of the box. And do you find this to be a common problem withSwyx [00:14:53]: How do you solve it?Walden [00:14:53]: Your clients?Cole [00:14:54]: This is a very common problem, and through my consulting, this is a lot of what I help teams do. A lot of teams don't really have great developer environment setups, if any. A lot of the times it's, “Go talk to Bob and get the secrets,” and that obviously doesn't work when the agent needs to actually set this up. And so a lot of that, most teams are using Docker Compose or some type of microservices. And so for theSwyx [00:15:19]: Even in prod?Cole [00:15:20]: Not in prod. With the OpenInspect, you are using this primarily to interact, and make code changes. There is other use cases, but you can hook, whether through CLI, MCPs, other tools, you can then hook that into your production systems primarily for, SRE type use cases. But you are not, necessarily, trying to test your prod internal microservice through the system.Walden [00:15:48]: And you mentioned Docker Compose. I think one direction we saw some of our friends take early on was, using Docker containers as the level of abstraction for their models. There's lots of reasons, I think, why Docker containers are not great. One thing is, Docker container's not really a true security boundary, for one. But the other is, if you are running real applications, a lot of times those applications use Docker, and then you have to think about Docker in Docker, which is, really weird. And so I think part of, the really hard challenge of getting VMs to work, why did we do that? Well, it was because we realized that you actually needed, full VMs to be able to do these types of things. And especially nowadays where there's actually value in running the application and clicking around and sending you screen recordings of these things. The value just, keeps adding on top of that. But it is a decision I see people run into when they try to build their own systems, is, “Oh, do we, in addition to this, do we put the agent in the machine or out of the machine? Do we use Docker? Do we use something else?” What do you recommend people nowadays?Cole [00:16:57]: I think Docker is a good solution for maybe not running the agent, but running your infrastructure, because that is more or less the same setup your engineers are probably already using. If they're not, then I don't know what they're using. But they're probably already using Docker Compose.Swyx [00:17:14]: I've always had a small candle for web containers. I don't know if you guys have tried them before.Swyx [00:17:19]: To me, they were, supposed to be like Docker Light.Cole [00:17:22]: Is it?Swyx [00:17:22]: I don't know.Cole [00:17:22]: No, I haven't tried it. But yeah, I think any environment that you've set up that is a good experience for your developer naturally lends itself to being easy to set up for the agent. And once you figure out that local developer story, you've more or less solved the agent in a sandbox, environment setup. OpenInspect does have hooks as well, where you can, run a setup SH script that will pre-install everything. You can then pre-snapshot that build so it starts instantly, and then there is a second hook to actually then, restore the state of the sandbox when it comes back. And so you can already have all of those microservices running and basically get the same experience that you would on your machine within the sandbox.Testing Agents: Computer Use, Screenshots, and Real App WorkflowsWalden [00:18:08]: Another thing that we've been thinking a lot about is like Different VM service offerings. Have you had customers where they needed like macOS specific VMs or like Windows specificWalden [00:18:20]: VMs?Walden [00:18:22]: There are like many technologies in the world that only work on specific types of machines, right? If you're building a.NET application that has to run on Windows or like, maybe more commonly if you want to build iOS or macOS Does that workSwyx [00:18:32]: Does Commission supportSwyx [00:18:33]: Choices like that?Walden [00:18:35]: The fundamental architecture we do, because we do the separation, it does support, but the actual work in progress is happening right now on these. Another thing that we've actually recently added support now for, it's in beta, is doing Android development. To do that, we needed to support, I think, nested virtualization within our machines because the VM itself is like a, is a virtualized Firecracker instance, and then you had to then run another Android emulator inside. And there's like weird performance issues that like, it, which is why it's like still in beta. We have to think through these problems, but it unlocks a lot for anyone who wants to do Android development.Swyx [00:19:13]: I was trying to find like a reference video for the testing thing. I couldn't find it, but I think you worked on the testing, capability. Why call it testing and not like computer use or I don't know, it's, what's the general Category of problem?Walden [00:19:26]: I think that when people think about the ability of an AI to run your app and test it, I think they actually over-index on the computer use part of it because computer use in my mind is the literal, okay, you want what button you want to click. Can you emit the right coordinates to go click that button? I think testing is actually a really interesting likeWalden [00:19:48]: Problem-solving, challenge for these AIs because if you wanted to do arbitrary testing, imagine you make a change that spans the frontend and the backend, maybe, even some other like even more deeply nested service. To actually test that change, we have to reason through what-- how do you first run these applications to orchestrate with each other with the right version of the code? Then, okay, how do I trigger the feature or how do I make the thing actually happen? And this can get arbitrarily hard, maybe you have to be an admin. Maybe a certain thing has to be feature flagged on. Maybe, you have to like run two sessions and then send us a very specific word into one of them to trigger a specific behavior. And figuring out how do you do that requires a lot of code base context, requires, a lot of orchestration that we've specifically done. And in some cases, we found that you actually, no one frontier model can actually do this full end-to-end task itself.Walden [00:20:42]: We've seen cases where we actually had to orchestrate different frontier models together to solve this problem together. That is where we spend most of our time when we think about this testing problem, not so much the computer use part. Computer use for what it's worth has gotten a lot better with recent models and it's made that part of the job certainly easier.Swyx [00:20:58]: Especially with like even 4.7, that they released yesterday, apparently like way better in terms of the vision stuff, which is going to be encompassing computer use.Walden [00:21:08]: Having evals for all these as well is something that like takes a while to build up. And having the evals be right is tricky as well. Do you ever see like, clients who are building their own agents have to start standing up evals to make sure things don't regress?Swyx [00:21:25]: Not so much evals in the traditional sense, but specific to the testing part that has just gone in. I just added support for screenshots And in theory you can also do video. I need to put in a plugin to do that. But they do show up natively, and it was a very heavily requested feature, especially after Cursor's recording came out. I think that was very enlightening for everyone of like, “Oh, this is a very good feature to actually have.”, I think with Devin you guys have had this for a while.Swyx [00:21:57]: Oh, yeah. See how screenshots work. Yeah, I don't know if there's anything, super and not obvious. It's like once what feature to build, you can just prompt it and it Will mostly work.Walden [00:22:09]: I think to Walden's point, though, the computer use is a subset of the larger testing problem, and I think that's very specific to the code base that you're working and it's not something that, out of the box that you could just solve it. The-- you do need the code base context to actually know how to test it. And I think in the case of a background agent system, you fortunately do have that code base locally that what is changing and could then inspect it and use that to drive the model.Swyx [00:22:40]: For those who haven't seen it before, this is an example of how it works. You, after the PR is done, you click testing approved, and then it sends you back a video. What I really like is that it labels, It's very small here, but it actually labels what it's testing. And then it-- and then you actually see the cursor and everything. So I don't know, yeah, the engineering in this, just Whatever you want to show. ‘cause this is like, this is one of those like, oh, few of the AGI moments, right? ‘cause Once I look at this, I actually don't I wish I can just merge inside Of Slack instead of going to GitHub ‘cause I don't need to see the code. I know it works.Walden [00:23:19]: Maybe a new feature in Cursor. Yeah, the annotations at the bottom was also a big difference for me when I, when I added those.Swyx [00:23:27]: It's just like, what am I looking at? What are you trying to demonstrate?Walden [00:23:30]: Exactly. There's a surprisingly long tail of small details that ends up making a big difference for this end metric of like how fast do you actually merge the code in. One experience that we spent a lot of time tuning early on was what is the right experience on GitHub for these tools. Because I think, most tools out there when you build the agent, you'll think about, oh, it'll create the PR for you. We try to take that a step further and say, “Oh, what if we actually made sure you could interact Devin, with direct Devin directly on GitHub?” And so we made sure that you can comment on GitHub, and Devin would actually receive those comments and address them back. But there's actually quite a bit of tuning you have to do here because you can imagine that actually like-We recently have Devin Review, for example. Devin Review will post comments on his own PR And then Devin has to then goGitHub Workflows: Devin Review, Comments, and PR AutomationSwyx [00:24:23]: He answers his own comments, which is Really loopy. So like, yeah, I like that it just updates here that it's, that I have commented But usually it's just me saying like, “Hey, merged, fix any merge conflicts.”Walden [00:24:37]: The, so when Devin fixes his own comments, you might be scared that, oh, maybe I'll infinite loop. But we've put a lot of work into making sure it doesn't, both by making sure that the comments are high signal, but also that the agent is thoughtful about what comments it immediately goes and tries to fix, and what comments it's like, “Wait a second, I think you're wrong.” Actually, that's one of my favorite moments is when Devin tells me that I'm wrong, when I try to get it to do something different. But tuning that behavior, actually makes a big difference in terms of how useful the actual GitHub experience is.Cole [00:25:06]: I think to touch on that as well, I think having the AI reviewer integrated into the system is a critical part of this background system. OpenInspect does have that. It has a GitHub code reviewer that you can control the prompt. It does do comments as well. It doesn't do them automatically yet. The capability is there, but it's not fully used.Swyx [00:25:27]: So you have to ask for it?Cole [00:25:28]: you do, yeah. You can tag it on GitHub, and then whatever you named your, GitHub bot, it will then follow up on it. It will then, if you have merge conflicts or whatever you have asked it to resolve, it will then resolve it, but it doesn't do it automatically yet.Integrations: Slack, MCP, and First-Party Agent InterfacesWalden [00:25:42]: Well, I'm curious, what is, the most common thing that people end up requesting, that they still need on top of OpenInspect when you help them go implement it?Cole [00:25:52]: I think a lot of it comes down to actually integrating it into the company. It's one thing to have the background agent system set up, but if it isn't actually integrated into your larger ecosystem, it isn't that useful. It is useful to be able to kick off sessions, but what we really want to be able to do is hook it into all of our other systems, whether that is the production database with read-only credentials, the logs, a Confluence or internal knowledge-based system. I think that is where I see the huge leap for companies, and that can be a challenge for companies as well who are maybe not familiar with exactly how to approach it, especially if they're in environments that have more compliance type things where, access control can be pretty big and how do you deliberately think about these problems, I find to be, one of the problems that comes with a system like this.Walden [00:26:46]: The thing we found is So, MCPs, obviously it has been like this, really big explosion of, oh, you can go, integrate it with all these different things. But to actually get the integration right and the and get the right experience, oftentimes we found that we had to go build our own ad hoc things. I think Slack is a great example of this. You could give your agent a Slack MCP and okay, it can post messages back to you on Slack. But we actually use Devin like a coworker in Slack, and that's how it's been built from the ground up. But to do that, you actually need to, support webhooks that come back, right? And then Devin has to respond in a natural way and then hopefully don't spam your threads too much and annoy the people in your company. So you got to tune that experience just right. Especially when there's a lot of back and forths, we find that we actually have to go beyond the simple MCP integrations in these places.Swyx [00:27:39]: I just pulled up the MCP marketplace. I know this is a Fair amount of work. Is the answer to eventually take first party control of all the top MCPs? Is that theWalden [00:27:48]: I would love a world where you could have something that's more expressive than MCP. That, goes both ways, not just a set of tools, but a proper system that interacts back and lets it Have the right experience with all these interfaces.Swyx [00:28:03]: So there actually is sampling in the MCP spec, but nobody Uses it, right?Walden [00:28:07]: And so I think that's the other part is, actually we found that when the MCP spec starts to get too complicated, it starts to lose its original promise of Being like a simple one-step connect. Now then we have to go figure out how to support all these different variations of things and It starts to look a lot like just building the first party integrations in a lot of these cases now.Cole [00:28:29]: I think it matters, too, how critical it is to your company, right? If this is something that nearly every session is going through, it probably makes sense to own it so that you can make optimizations on top of it Versus just whatever is off the shelf.Swyx [00:28:43]: Awesome. Other than MCPs, what else, sorry, well, I don't know if that's Narrowing in too much on, integrations. But what else? What other elements of building OpenInspect or Devin that you guys really sink on?Memory and Knowledge: What Agents Should RememberCole [00:28:59]: I think, a problem that comes up very frequently is this idea of memories or knowledge base.Swyx [00:29:05]: Oh, boy. How do you solve it?Cole [00:29:08]: so not solved yet, is the short answer.Cole [00:29:11]: it's something, there's a open issue for it, someone asking about it.Swyx [00:29:16]: There's, I, D Wiki hasn't indexed anything about memory yet.Cole [00:29:20]: how I'm seeing it solved across my clients is primarily through skills. I find that skills can be a good gap within that or updating Claude MD, but I think memory as a whole is a pretty unsolved problem, and it is why I've been hesitant to add it. I think there is parts of memory and that can be addressed, but I think as a whole it's a very difficult retrieval problem.Swyx [00:29:44]: Oh my God. RAMP didn't write anything about memory? I see zero search results.Walden [00:29:50]: No. Memory can be quite tricky to get right because it's the retrieval, but also the generation of the memories that can be really tricky. You don't want it to just like Remember very specific details.Swyx [00:29:59]: Walk us through the Devin memory journey because I know there's been a journey.Walden [00:30:03]: the first version of memory that like stuck around for a while was A system we have called Knowledge. And the idea was we wanted it to pick up things over time and not need the user to be proactive about teaching Devin things. So, okay, any time you remind Devin, “Wait, no, that's not quite the way you're supposed to use Git”Like, we actually want Devin to say, “Hey, do you want me to actually just remember this for the future?” And for you to just basically quickly approve or reject and for it to build up over time. ‘Cause I find that, 95%, I think, or some crazy stat like that of the memories that Devin has are all through these auto-generated things. Very few people actually just want to sit down and write big docs on Here's how you're supposed to work with the technology, et cetera. The generation and the retrieval has been something that we've been trying to tune a lot over the years. Generation, you don't want it to remember something like, if you asked one time to like, “Oh, please open as a draft PR,” you don't want to be like, “Oh, everyone forever now should get their PRs as draft PRs.” But you do want some, conveyor. Maybe you want to say like, “Oh, Cole generally likes, things to be created as draft PRs.” Same with retrieval, if you have thousands of these memories, how do you actually make sure they're retrieved at the right time? And that can be quite tricky to do right without exploding the context with a bunch of useful yeah, useless information. Surprising amount of just, eval work to just make sure that, memory is, remains a reliable system as new models come and go.Cole [00:31:31]: Do you have anything that you could share on, memory pruning? And like the temporal aspect of memory?Swyx [00:31:36]: Deleting and forgetting?Walden [00:31:39]: The, today, the, So the things they could do is it could edit memories. And so if your memory used to say like, “Oh, Cole likes to open everything as like a draft PR,” then you can imagine, “No, don't do that.” And then it'll say, “Oh, do you want me to update the memory to be Cole now want everything as, open PRs?” I think that at the same time we don't know if this is going to be the final version of the system. Whatever we have here will probably, translate into the new system that we'll be coming up with. But I think one big difference between two years ago and today is these agents are really good at using anything that resembles a file system natively. And so part of us are, is thinking, “Oh, should we rebuild memories to feel more like a file system that we let the agent navigate on its own?” That's been an interesting exploration. Also similar ideas in the scale space.Swyx [00:32:35]: I am pulling up OpenClaude's memory thing right now. So memory, OpenClaude has like this like daily memory journal thing, right? And you can I mean, that is a file system you can grep through and is a source of truth. I don't know if it's the best. It's probably super noisy, but at least, if you lose something you can discover it or you can apply some, forgetting algorithm to, more ancient memories that don't get recalled again or something. I don't know.Walden [00:33:01]: One thing we've been trying to do to push the boundaries of how you use agents at your company is letting an agent basically have a very similar file, a memory.md or something, and just like be your permanent PM for a specific set of issues maybe. So we have like some Slack channels internally, maybe a Slack channel dedicated to, a specific product like DeepWiki maybe. And you can imagine that, or you want a Devin that never stops, it's just always awake, but it has this like memory dock that it can just maintain for itself about, okay, what are like the number one priorities of what we have to fix and prioritize? Who is responsible for some upcoming work? Maybe they'll even Devin will even tag you on some recurring basis. And so it's been an interesting move to see, okay, how can we actually use Devin for more than just engineering? Can we actually upstream above the engineering process and maybe it's just Devin creating tickets, which then maybe some humans do, but then maybe other Devins do.Swyx [00:34:00]: One of my more fun automations is go research competitors and just suggest stuff to me on a weekly basis. That's the automation. I can't find it right now, but basically it just like, “Look at competitors and suggest things.” “And here are three things that you've suggested that I don't want any more of,” and you just stick that in the prompts. But like I wish actually So for like when I, for example, when I reject a PR, I wish that it updated memory so that I can then just not have to go up, go back and update the scheduled, sync, but anyway, feature request.Walden [00:34:31]: what? We might change it soon. I guess OpenInspect, in the time you've been around, has there been anything you tried to implement but then you had to like undo and like do a different way?OpenInspect Architecture: Webhooks, Control Planes, and Agent StateCole [00:34:41]: Nothing yet, but something that is on my mind. The initial way that I built it was that each of the integrations lives as its own package. And so you have The Slack bot, which is what's handling the webhooks, and then is basically interacting with the control plane. As I'm seeing the system starting to be more integrated, specifically with the GitHub bot integration, I'm considering bringing that all into the central control plane because especially now I want to start, And a request that I'm getting is the ability to monitor, the actual, pull requests being merged, as well as just tracking ofSwyx [00:35:19]: What do I have open?Cole [00:35:21]: What do I have open? How many of these are getting merged? How many comments are showing up? To just understand the health of the system. And so in the case of a GitHub app, you only have one webhook. And so then it's a question of do I put that webhook in that GitHub bot package? That's weird. It doesn't really make sense to live there because that package is more for like the code reviewer. Or do I like centralize it? So that's something that's on my mind of, making that decision. I think the other one we touched on earlier is the harness in the box versus out of the box. I think long term the architecture will eventually come back out of the box. Some of the newer tools that I've added are calling back into the control plane so that you don't have the secrets in the sandbox. And so I think long term I probably will pull the actual, agent out of the box, but I think for now it's fine.Subagents and Multi-Agent Systems: When Parallelism Helps or HurtsSwyx [00:36:16]: Just, a quick question on pulling the agent out of the box. I'm One thing I'm very bullish on this year is agents calling other agents or spawning sub-agents or Whatever you want to call it. Does that make it harder or easier? I can't tell. Because if the harness is in the box, you can just spin up more boxes. If the harness is outside the box, then you're, it's less easy because you are, you have a unicorn pet of a, of a harness that's, living outside the box.Cole [00:36:45]: In theory it would be the same way, right? Whether, one agent has launched many, sub-sessions within it, OpenInspect, for example, can launch sub-sessions and actually create other environments and then monitor them. In the case where it is out of the box, that would basically just be an additional session that's running. And so that session is also running outside of the box. It's running in your worker plane, wherever you're running this. And then you really just have to think about how does your top level agent then interact with it. I do think it can be more complex, just ‘cause again, you have now a more difficult architecture. But I think if you figured it out once, it's probably fine.Swyx [00:37:26]: Well, then I'm just, throwing it open to you in terms of, I call this like meta Devin management. Which is like the, Devin's calling Devins or Devin scheduling Devins or querying trajectories or anything like that. What have you built or unshipped, anything?Cole [00:37:46]: I think one of the surprising things we've seen is that a lot of the ways that, these, separate agents work with each other, and you want them to, parallelize their work, has still mostly followed the same manager sub-agents regime. And a lot of people I think are excited about this world where you have swarms of agents that, talk with each other all over the place. We've actually given Devin an MCP so they can just go arbitrarily message other Devins And create new Devins, et cetera. But I guess, it somehow creates, a really chaotic world in that sense. And so we've still found that most practical use on a day-to-day basis has been one single Devin.Cole [00:38:33]: Figuring out how to segregate the work and get, have other Devins work on it in, a relatively isolated sense, each with their own boxes Not sharing machines, so there's, a very little room for conflict is the regime that you have to create today.Swyx [00:38:50]: I'll call out, the experiments from Cursor, right? This is Wilson Lin's work on Single agent to multi-agent, and you're obviously famously on the side of don't build multi-agent. But they went through the whole thing, only to arrive at, this Which is exactly what Devin has, I think.Cole [00:39:08]: I think there will be a revision to that post at some point AboutSwyx [00:39:12]: Tell us about itCole [00:39:12]: I think multi-agents were very much not at all possible a year ago. You do see more multi-agent experiments today, but you can argue, are they really multi-agents, or are they just just, tool calls,? There are people who, will create sub-agents to go look for XYZ file, XYZ implementation. Has really nice context management benefits because all of the tool calls and tokens that it spends then get collapsed back to just the answer for the main agent. There's a lot of benefits to doing this. We basically have Devin do this with Deep Bookie, make a call out to Deep Bookie, give you back the results, but that feels like a tool call,? It's not like these, two collaborators actually talking back with each, back and forth with each other. But I think the thing that gives me the most bullishness that multi-agents might actually be possible is actually what I said earlier about Devin will actually sometimes tell me I'm wrong and push back, and I think that demonstrates a level of maturity and communication today that makes a multi-agent world possible. One, can two agents who have seen different information come back to each other and actually figure out who is right, what is the correct implementation? They're not just, yes men. Claude, I guess is like, used to just say, what is it? “You're right,” or,Swyx [00:40:25]: “You're absolutely right.”Cole [00:40:26]: “You're absolutely right.” Yeah.Swyx [00:40:28]: The Have you seen, did you seeCole [00:40:29]: The age is overSwyx [00:40:30]: The Codex app troll in Topic? This is the Codex app. Inside of Settings, there's a little, there's a little Easter egg, right? So if you go to, the Themes or Appearance, right? There's all these, color codes, and the top is absolutely, and it's the Topic's colors. Which is such a troll. Anyway.Model Behavior: Pushback, Adversarial Prompts, and Agent SkepticismCole [00:40:53]: I love that Easter egg. Did you discover that yourself?Swyx [00:40:54]: No, it was, someone was, tweeting about it And I was like, I was like, “Is this true?” Because, sometimes people just tweet stuff to, get a rise out of you. But yeah, there you go, in Topic colors.Cole [00:41:06]: Yeah. So yeah, we're out of this regime where, it just says you're absolutely right, and they can have real conversations and real back and forths.Swyx [00:41:13]: You can prompt it as well to be more adversarial or whatever. Yeah. Okay. Yeah, that, I mean, to me, that is more intelligence, right? That is not just something that's, a dumb tool, it's actually pushing back on you I think. Yeah.Cole [00:41:24]: when you mentioned, of course, the blog posts. There was one blog they had where they fed a swarm of agents together and built a browser.Swyx [00:41:34]: That was I think that was the one.Cole [00:41:36]: You can have, likeSwyx [00:41:37]: I think it's the same oneCole [00:41:37]: Creation of it. We found a surprising success of, don't do a swarm or anything, just have one Devin, it does its own context management. Just let it keep running for a while and give it some crazy tasks. I think we asked it to, rebuild, a Windows OS system. And it managed to do it just like, going on for long enough. It'sSwyx [00:41:55]: Was this Andrew's thing?Cole [00:41:58]: there were lots of demos that we ended up not posting, ‘cause at some point we'd just be posting way too much a bunch of, Demos. But I love that because it shows that I think the multi-agent thing still has, a bit of exciting sexiness to it, which is maybe still beyond still, the actual delta it adds to the capabilities of these systems. But it's absolutely the future. I think we're heading in that direction and we can see the progress being made there already.Swyx [00:42:25]: If I were to, make one super minor pushback because I don't feel that confident about it yetCole [00:42:33]: Go for itSwyx [00:42:33]: But I've had Ryan Lopopolo from OpenAI on the pod And he's a super slop cannon, right? Oh my God, that's my coding agent being done. I downloaded this, Peon Ping. I don't know if you guys have heard this. It takes like-, sound packs from popular games like, Command and Conquer and Warcraft, and then it plays it whenever it's done. And so it's like, “Work,” or whatever, “At your command,” or something. Anyway, what I got from the Cursor code base and from Ryan's thing was that there's a slop cannon approach where you try to loosen the single agent's, bottleneck, and I feel like that is, probably an, a very important thing to try to figure out. I don't think anyone's, really solved it. Because then you just have more reviewer slop on top of the agent slop To try to wrangle it all. Ryan will probably very strongly object that I say that he hasn't solved it, but he thinks he's He thinks he's completely solved it. But I think it's still I think it's, very important, ‘cause, that is a bottleneck, right? I feel Devin is slow sometimes Because I'm like, well, yeah, this is very readable and very sensible, but also it is slower than it could be if I just, I want a button to just say, “Just ramp this up 1,000 next parallel, in parallel and just, see what happens,”? And I don't know if that's, feasible at some point in the future.Code Review, Entropy, and AI SlopWalden [00:43:55]: I And we've also run experiments internally where we've basically tried to build entire products, true products that we knew we would eventually ship, but for now, let's try to see if we can do it just by purely, vibe coding on top of each other, auto merge, no code review at all. And then there's this benchmark of how many weeks can you go onto this for Before you say, “We have the trashiest code base.”Walden [00:44:18]: “Let's actually rewrite it from scratch.”Swyx [00:44:19]: Start a new factory, yeah. What'd you find?Walden [00:44:21]: I think we found that the state-of-the-art in December was you can probably, run this for about two weeks. By the end of those two weeks, you'd find that, hey, you want to, change the color of a button. Well, it turns out this button is implemented in, 10 different places, and they, have All these different variations, and oh, you forgot one of them, and actually it's a slightly different color in one spot. And you're like, “Okay, this is too much to work with. Let's actually try to do code review at the same time.” And make sure that we're on top of our software, actually cleaning it up a bit And making sure it's done in a scalable way.Cole [00:44:54]: I think building on that, the idea of, you don't have to look at code, I think is generally a bad idea. And the meme that I have for thatWalden [00:45:03]: What timeline, all right, is Do you think that statement will be true on?Cole [00:45:06]: I think probably for a while it'll be true that you should continue to look at your code. A problem that I see a lot of teams run into that I work with who are embracing AI native, AI first coding, is The meme that I have is that your code base regresses to your worst engineer, because that engineer who is, very gung-ho about AI and is not auditing their code, their pattern starts cementing into the code, and now the AI is referencing their patterns. And so now their if/else block that, is 20 if/elses back and forth, the AI is seeing that as the pattern of how things are done and starts to then exponentially grow this slop. And I find to your point, a pretty good approach to that is having scheduled cleanup, whether by humans or through systems, that are looking for duplication. They then address that. You'll end up with like 12 helpers for how to format a date. And you need to address that, because otherwise it will continue to sprawl.Swyx [00:46:09]: Within balance, I think it's fine to have some duplication, and then sometimes To have garbage collection, right? Yeah. The What I've been, talking about with a lot of engineering leaders is that you want to be very strict about the boundaries between modules, and it's your job as an architect, as a CTO, whatever, to say like, “Okay, here's the hard contract between you guys and you guys. Whatever you do inside this black box is your business. You do whatever. But between these guys, let's be, really damn clear, and any movement must be signed off by a human or me,” or. Then, and like that's that. I don't know if you have any other modifications or advice.Walden [00:46:44]: Well, I guess generally on the topic of, where humans can be useful, I found that ‘cause, some of these, really deep infra problems, sometimes just having a human that just has, really deep expertise can make a big difference. I've actually seen this come into play when actually building agents. So we've had a few friends now, try building their own coding agents, and I think one same problem that I recurringly heard a lot of them run into was this problem of like, “Oh, Grep is really slow on our agents' machines.” And so a lot of them, I assume because they're using AI and they themselves don't have, super deep infra background knowledge, say, “Okay, we're going to go build our own custom Grep index. It's going to be really fast,” and use that as a way around this problem. When we ran into this problem About like, maybe like a year and a half ago when we were, in the early days of building Devin, we obviously didn't have AI then. We just asked our, how to, how to do this. You can just swap out a new Grep index, so.Infrastructure Details: Grep, File Systems, and SandboxesSwyx [00:47:45]: What do you mean you hand-coded Devin? What?Walden [00:47:48]: It's like, can you believe we hand-wrote this code? And we had, our infra people who are really amazing, they were looking into it and they're like, “Oh, what? We realized that actually the root cause of this problem is actually super simple, but like fine-grain detail,” which is that a lot of these virtual machines actually underlying them don't use real file systems. They use these, network file systems where things are actually cached over the network actually in S3. So when you're Grepping, you're actually making network calls Every time you're doing these things, and that's why Grep is extremely slow on these machines. And so again, goes back to, what is all of the crazy infra work that we had to do to actually get these machines working. If you try to do this yourself, there are tons of small details like this, and so we had to eventually go swap out that network file system. ButSwyx [00:48:35]: I think there's a write-up about it, right? Silas did one about the virtual file system.Walden [00:48:38]: Oh, that was a whole other thing. TheSwyx [00:48:39]: Oh, that's a different thingWalden [00:48:40]: The BlockDev file storage formatSwyx [00:48:42]: I'll bring it upWalden [00:48:42]: Which is, a file system format that we built so that the VMs could be spun up and down very quickly. Basically, the intuition behind this is-Imagine you have, a terabyte of disk, and your agent only, wrote, a hundred lines of code on top of that disk. How long does it, say, take to, save and re-bring up that disk? And most systems, because you're not optimizing for this case, it's just, on the order of a terabyte of work because you have to Save all of that and bring it back up. In our system, we try to build a file system that incrementally builds on top of each other. So every time you save and bring the machine back up, you're only doing work that is proportional to effectively the diff in the file system. And so this, shaves off a lot of time in the boot-up process of Devin. I think we This is actually now outdated. We have a newer system inside of Devin. But yeah, there's a lot of tiny details you have to get right here to actually get the day-to-day experience of Devin to be good.Swyx [00:49:39]: It's, not technically agents, but it is agent infra, and when you sell an agent as a company, you sell agent plus agent infra.Walden [00:49:46]: At least the way we do it be And the other The nice thing about having the agent infra being done together is, you We get to deploy Devin in whatever environment we want now. We don't need to wait for some underlying infra provider to also go and support VPC or on-prem or FedGovCloud, for instance. So we can actually go and figure out, okay, since we own the infrastructure, how can we get that set up for you?Cloud Providers: Modal, Daytona, and Enterprise SandboxesSwyx [00:50:12]: Whereas you're Cloudflare dependent.Cole [00:50:15]: so Cloudflare runs the control plane. The sandboxes, Modal is supported. A contributor just added Daytona. E2B is on the roadmap, and I think there's an abstraction in place that if any contributor wants to add a new provider, they can add that in.Walden [00:50:32]: Well, what are, How are the customers you work with Do they generally try to then go set up a contract with another one of these third-party providers? Do they try to do the VMs in-house?Cole [00:50:44]: most of them I see using Modal. I think Modal has a greatWalden [00:50:48]: Shout out Modal.Swyx [00:50:48]: Shout out Modal.Cole [00:50:50]: I think Modal has a great offering. It captures all of the sandbox pieces you need, snapshots being a pretty big piece of that, and given that they also offer GPUs, I think it's a pretty nice offering as a whole.Swyx [00:51:04]: no debate there.Walden [00:51:07]: Modal is great, especially, I think their container offering is, the most natural, and so especially if you are willing to, forego, the full VM requirements Modal is, a really vast place you can spin something up on.Swyx [00:51:20]: Is there a point So Modal's very Python, and I feel like most workload, has really shifted to JavaScript. I don't know if you guys Get the same feeling. So, okay, when I started Landspace and IE and all these things, I was like 50/50 Python and JS, right? That's roughly. I think that's wrong now. I think JS has won. I don't know if you guys Like, I Maybe I'm overstating it, and maybe for cognition, there's, C# and Java and what have you. But for, new greenfield apps, do you feel that Do you get that sense? Does it matter?Cole [00:51:52]: I think that most of the libraries that I see in this space are Python native first, especially in theCole [00:51:58]: Observability space. That said, I think that there is a pretty big appeal of having your entire system in one language. Especially when you have both your frontend and backend communicating, you can have one central type Which is very nice.Swyx [00:52:11]: That's my case against Modal, which is Then you have to run JS. You can run JS inside Modal. It's just, one extra step That, isn't native to the runtime. I don't know ifWalden [00:52:22]: I don't knowSwyx [00:52:23]: Reviews. Do you have numbers? I don't know.Walden [00:52:25]: the one thing I don't like about Python is whenever AI, whenever it writes Python, it always does, the weirdest patterns, andSwyx [00:52:32]: Oh, because it's, mixing two and three or what?Walden [00:52:34]: I think it's something mixing two and three, yeah. The I don't know if you see this. It always tries to do, has attribute on objects as likeCole [00:52:41]: Oh, my God.Walden [00:52:41]: But it's like But that you shouldn't be doing that. It should error if there wasSwyx [00:52:45]: Because it's training on library code?Cole [00:52:47]: I think it's more of, likeCole [00:52:48]: From what I've seen, it's more of, a reward hacking mechanism where it doesn't want to basicallyWalden [00:52:54]: It'll never error.Cole [00:52:54]: It doesn't want the code to fail. And so it Even when it knows it has the attribute, it'll call getattr on a, and for a lot of my clients who have moved towards more autonomous coding, we've put that in as a lint rule That if you do getattr, your pull request is going to fail.Slop Signatures: Comments, Backwards Compatibility, and TypesSwyx [00:53:12]: Ooh, this is a fun topic. Can you tell me more about this? What else is a sign of AI coding that you have to put guards in?Walden [00:53:21]: So we were talking just before this about Opus 4.7. One of the things this new model likes to do is it writes lots of comments. Not like, it'll, comment every line, but it'll write, paragraph, PRDs, on top of every function. But I will say, to its credit, these aren't slop, descriptions like they were before. “Oh, here's what this function does.” It's like, “Oh, here's actually the r

This week the guys are back and better than ever! Delvin is no longer dying, Donnie isn't on vacation and Dev isn't taking care of his family (but they are taking care of him with banana bread). This week Delvin and Dev gush about 007 First Light, Donnie is having a blast with Lego Batman on his portal, we talk about the end of Destiny 2 and possibly Bungie as well as what could be sad news for the price of the Steam Machine. In the end we find out what music acts the fellas absolutely can't stand, so stay a while and listen. This is PSVG.

Episode 029 of Fonk Monthly Mix - May 2026 Fonk Monthly Mix Episode 029 This month's Fonk delivers an explosive journey through progressive and big room house with infectious energy from start to finish. Dannic showcases multiple exclusive mashups and edits including his own "Chasing Freedom vs Beauty & The Beat" and "Tombo vs Silence vs Intro vs Lethal Industry" alongside standout originals like "Dim Your Light" with Dastic. The mix features heavy-hitting collaborations and creative mashups from SunJay, AIRÆS, and more, perfectly blending classic anthems with cutting-edge productions. TRACKLIST: 1. Mixmasters, Mellizos - My Life Is A Disco (In The Mix) (Extended Mix) 2. Alenx B - House Religion (Extended Mix) 3. Ellison - Set Fire To The Rain x Rain (Hard Mashup) 4. Melsen vs. D.O.D, Carla Monroe - What I Feel x Still Sleepless (Melsen Mashup) 5. NIIKO x SWAE, KSHMR - Bass Down Low (feat. DEV) 6. Dannic & Dastic - Dim Your Light (Extended Mix) 7. Nicky Romero & Deniz Koyu vs. Post Malone - Tomorrow Comes vs Chemical (SunJay Mashup) 8. Dannic - My Mind (VIBR Edit Vincent Brouwer) 9. Firebeatz - Pump That Bass (Extended Mix) 10. Afrojack - Polkadots (Reloader 2026 Edit) 11. Yves V & VIKTOR - Fit The Tempo 12. Daddy's Groove vs. Justin Michael vs. Dada Life - Born To Follow Synthemilk (Dyro Mashup) 13. Mike Williams & Phillip Strand x Kesha - All My Life x Die Young (AIRÆS Mashup) 14. Dannic - Chasing Freedom vs Beauty & The Beat (Dannic Mashup) 15. Dannic vs. Delerium vs. The XX vs. Tiësto - Tombo vs Silence vs... (Dimitro Re-Cut Mashup) 16. Dannic - I'll Be There For You (Extended Mix) 17. Yohann Warren feat. Scarlett - Think About (Extended Mix) 18. Dannic vs. Calvin Harris & Alesso & Hurts vs. Martin Garrix & Matisse & Sadko - Wake Me Up vs Under Control vs... (SunJay Mashup) 19. Skrillex, Ahadadream, Raf Saperra - Bass Dhol (Original Mix) 20. Tiësto, Olivia Sebastianelli - Don't Lose Your Head 21. Swedish House Mafia x Daft Punk, Pejt - Don't You Worry Child x One More Time (AIRÆS Mashup) Follow Dannic:

Incompetent Marines, fixing wounds with duct tape, and misrepresentations of Titan's gravity; we've got it all in the penultimate episode of season 5 of AppleTV's For All Mankind.Nique welcomes Gus, John, and Chris to argue over the nature of Elena's injury and just how Alex plans to get to Dev's supplies.Join the conversation on Discord at the Moon Show Podcast Server.

01. David Guetta & Marten Hørger, Men Machine – The Past, The Present, The Future (Extended Mix) 02. Going Deeper – Oxygen (Extended Mix) 03. unfazed – A Gira (Remix)04. Broken Hill – Zero Tolerance (Extended Mix)05. Devault – Can't Wait No More (Extended Mix) 06. Kalamita (FR), Jasmine Knight – Down & Dirty (Extended Mix) 07. UUFO, Amber Revival & Avrix – Let It Rain (Extended Mix) 08. NIIKO X SWAE, KSHMR – Bass Down Low (feat. DEV) 09. AFROJACK, L&S vs Felix Da Housecat – Screen Control (Botteghi, Ali Selecta & DJ POTZ flip)10. Yves V – My Body (Extended Mix)11. Borey – Feel Of The Night (Extended Mix)12. NOME. - Stay (Extended Mix) 13. Yves V & VIKTOR – Fit The Tempo V (Extended Mix)14. Eli & Dani, Stylo – Body Works (Extended Mix)15. Green Velvet & Harvard Bass – Lazer Beams (Adam Beyer & Massano Remix)CLASSIC OF THE WEEK16. DVBBS & Borgeous – Tsunami (Original Mix)

Welcome to CHUCKYVISION, a podcast about the horror franchise Child's Play/Chucky, the surrounding culture, and other killer doll films. In our first episode post-Child's Play Minute, Mark shoehorns in a film that he really wanted to look at. The new Masters of the Universe film is released next month, so why the hell shouldn't we look at the 1987 cult classic this month? It's toys. Dolls. They come alive. Sorta. In this bumper episode, Mark and Dev discuss the history and legacy of the He-Man franchise from action figures to TV shows before taking a look at Masters of the Universe (1987) starring Dolph Ludgren, Frank Langella, Monica from FRIENDS and Tom Paris from Star Trek Voyager. Mark is very enthusiastic; Dev less so. Host: Mark Adams Co-Host: Dev Elson Editor: Mark Adams Executive Producer: Tony Black Twitter/BlueSky:  @ChuckyVision  Our Network:   @filmstories filmstories.co.uk Title music: At the Beginning (c) Dark Fantasy Studios Cover Art: Ama @Amasc0met Logo: Elliot @Elliottt93 Learn more about your ad choices. Visit megaphone.fm/adchoices

Dev got a gift from a coworker...he'll show it off (3:00). Cavs blew a 22pt 4th quarter lead in Game 1 at New York, Jalen Brunson's there for it, Hunting James Harden, and Kenny Atkinson doesn't wanna use his timeouts (10:24). Details have emerged from Ramona Shelburne on Victor Wembanyama visit to a Shaolin Monastery last offseason to help him build who he is this season. We'll try to practice one of the poses Wemby had to do on the show (36:54). There's a youth movement in the NBA....Henry Abbott documented it (1:11:25). Jason Kidd was fired in Dallas (1:18:41).Host: Chris Vernon Contributors: Jon Roser, Devin Walker Technical Director: Jaylon Wallace Associate Producer: Jena Broyles 

The user-agent string in the HTTP header has been there since the 1990s. The web was built with software navigating it on someone's behalf. For thirty years that someone was a human. That changes now. Matt Biilmann, CEO and co-founder of Netlify, was one of the first to take seriously what it means when the "user" navigating the web is an AI agent. He published the foundational essay on Agent Experience in January 2025, pivoted his entire company around it, and recently shipped netlify.ai as a separate entry point built for agents. We cover the four pillars of Agent Experience, why every product already has an agent experience whether you designed one or not, content negotiation as a way to tell agents to go to a different URL than humans, why SaaS is in real trouble (with a story from inside Netlify about ripping out vendor contracts), how the data-structure assumption that has defined software for fifty years is breaking, and the one thing every website owner should start doing this week.About the GuestMatt Biilmann is the CEO and co-founder of Netlify, the platform that started the Jamstack movement and is leading the shift from developer experience to agent experience. His January 2025 essay on Agent Experience is the foundational text for the discipline. Chapters00:00 Every product has an agent experience (cold open)00:35 The architectural question01:46 Welcome Matt to No Hacks02:15 When AX became a design constraint, not a concept06:44 The January 28 2025 essay and who got it first10:22 Why netlify.ai was built as a separate website12:44 Content negotiation: telling agents to go to a different URL13:54 Qualitative data and the Axis eval framework17:12 Does AX apply to e-commerce and content websites?20:59 The cumulative media argument (TV did not kill radio)25:00 User-agent in HTTP and Al Gore-era agent commerce laws26:33 SaaS business model is dead: build-vs-buy is shifting30:44 The end of structured content as a hard constraint40:25 One thing every website owner should do now43:08 Where to find Matt onlineKey TakeawaysEvery website already has an agent experience. Agent Experience is how AI agents currently interact with your product, whether through computer use, fetching, or working around the barriers you put up. It is not a feature you add. The only question is whether the experience is good or bad.The four pillars: Access, Context, Tools, Orchestration. Matt's framework for thinking about AX systematically. Access answers whether agents can reach your product at all. Context is the prompt-engineering equivalent for agents. Tools are the concrete capabilities you expose. Orchestration covers how agents string those tools together inside your product.Build a separate entry point for agents. netlify.ai is purpose-built for agents while netlify.com remains the human entry point. Content negotiation tells agents to go to one URL, humans see the other. The blessed-path approach beats trying to make one URL serve both.SaaS economics are shifting structurally. The build-vs-buy floor is dropping fast as AI lowers the cost of software. Traditional 90%-margin seat-based SaaS is in real trouble. Dev tool companies have upside because companies need more tools. Everyone else is going to be ripping out vendor contracts and building internally.The data-structure paradigm is breaking. Software engineering has operated on the Linus Torvalds principle that data structures matter more than code. LLMs are not built around data structures. Building software around LLMs means rethinking the assumption that drove fifty years of computer science.Notable Quotes"Every product has an agent experience because all of these agents, whether through computer use or through fetching your website or through working around the barriers you put up from them, have some agent experience right now. It is just a question of is it good or bad.""There is a reason it is called a user agent in the header. It was forward-looking.""We have been ripping out SaaS contracts. Sometimes it is heartbreaking. The rep calls to right-size the contract and the customer reacts with 'let me see if I can build it with an agent.' Then they call back and cancel instead.""The context and the flows and your creativity are probably more important than both the data structures and the code."What To Do NextOpen your website in Claude Code or ChatGPT and ask the agent to complete a real task. Watch where it stalls. That is your AX baseline.Check your traffic logs for AI assistant visitors (ChatGPT-User, Claude-Web, PerplexityBot, GPTBot). The number is rising whether you measure it or not. Cloudflare reports AI assistants are now 5.5% of all internet traffic, up from 3.9% six months ago.Read Matt's January 28 2025 essay on Agent Experience at biilmann.blog as the starting point. Then read the one-year retrospective for the four pillars framework.If you operate a developer tool or any product with a clear automation surface, start a simple eval scenario: take a fresh agent, give it a task, score whether it succeeds. Axis from Netlify will give a proper framework when it ships open source.Resources Mentionednetlify.ai (the agent-built entry point Matt and team shipped recently)netlify.com (the human entry point)Matt's original Agent Experience essay, January 28 2025: biilmann.blogMatt's "AI in the CLI: The Humanoid Robot of the Web" (August 2025)Claude Code (the agent that flipped broad accessibility for CLI coding agents)Connect with Matt BiilmannBlog: biilmann.blogLinkedIn: linkedin.com/in/mathias-biilmann-christensen-a5a3805Twitter/X: @biilmann (x.com/biilmann)Bluesky: bsky.app/profile/did:plc:grjr4il5dredrsuj7nosb4pqMastodon: mastodon.social/@biilmannNetlify: netlify.com and netlify.aiConnect with No HacksWebsite: nohacks.coSubscribe to the newsletter: nohacks.co/subscribeMachine-First Architecture: machinefirstarchitecture.comNo Hacks is a podcast about web performance, technical SEO, and the agentic web. Hosted by Slobodan "Sani" Manic.

1. CamelPhat, Josh Gigante feat.Kuuda - So Good 2. ANOTR ft. 54 Ultra - Talk To You 3. Ben Dooks - Not About Love 4. Kryder - All My Love 5. dEVOLVE - TAKE ME (Tommy Pilot Remix) 6. Capozzi - Boyz Pause 7. Green Velvet VS Meduza, GENESI & Essentia - La La Land 8. Enquai - M.T.W 9. Main Circus - No Excuse 10. NIIKO X SWAE, KSHMR - Bass Down Low (feat. DEV) 11. David Guetta & Marten Hørger, Men Machine, Congorock, KENZ - Babylon (Men Machine Rework) 12. Kasablanca & Township Rebellion - It's Chemical 13. Mark Bale x Dave Darell - We Like To Club 14. Vigel, M.J.E & Michael Chodo - Take My Soul 15. Chester Young - Ophelia 16. Dennis Reif & Unusual - Push It 17. Mosimann - Night & Day 18. Don Diablo, Wiz Khalifa & Chri$tian Gate$ - Go Home With A Stranger (Kevin de Vries Remix) 19. Sentinel - Like Fire 20. Modeā & Bryan Kearney - Ready to Fly

GROG & GRYPHON Episode 6: The Codinar Crusade  Tonight we return to witness the attack of the Lycanna on Garulk, Murrai the Goblin and Octavia at the Grog and Gryphon tavern itself. Arullia Swordcleaver attacks a sea serpent alone on the river Stygiar even as Olaff and DeV'ralto devise a mad plan to assist her. Reyna the Red springs into action when a hellish sea beast attempts to eat her pirate galleon, "The Lady Wrath." More of the history of Silverr-O, Elder of the Pack of the Pure as the Amazonia continue their Goddess' Quest. Meanwhile, Bane Renbourne treks across the frozen wastes to seek an answer to the riddle of the Codinar Prophecy and how it ties to the wizard Alganoir – still crucified to the Crystal Keep of the Magi… Another tale of Honor, blood and betrayal in the Saga of the Grog & Gryphon… So Hoist a Tankard and Join the Quest!  The Actors in this production were: Gina Hollweg as Arullia Swordcleaver Amazonian Warrioress Fiona Conn as Acetegan, The Mage of Wight Amanda Fitzwater as Octavia John Dane as DeV'ralto Natasha Lathrop as Reyna the Red & various Amazonian Warriors Mark Kalita as the Lycanna Changling: Bane Renbourne Paul Mannering as Olaff Houndsmaw Rob Northrup as the Goblin Murrai Gareth Preston as Alganoir Bill Hollweg as Garulk the Barbarian Brian McCleary as Silver Eye James Freeman as various Werewolves Colin Snow as various werewolves Ann Lysic as Queen Dragonsmite & as the Serpent Wizard #2 Damaris Mannering as Alithia Robin Carsile as Halbarda Hammerwar & various Amazonian Warriors Rachel Monroe as Adra Wrathblade & various Amazonian Warriors Josh Royston as Rordor Adam Lederhos as Duro Dun Miles Reid as the Serpent Wizard #1 Douglys of Howl-O as Silverr-O < Elder of the Lupisians>

Hey Bobs! We just powered through For All Mankind Season 5, Episode 8 – 'Brave New World,' and wow… this one delivered.Donnie bumped it to a 9.2 while Brian landed on a strong 8 (leaning 9). After last week's highs, this episode kept the momentum with Irena pulling strings, Miles stepping up as a leader, the governor's redemption arc, and that gut-wrenching Titan mission fallout. The final 20 minutes? Absolute cinema — tense, emotional, and full of consequences.We break down the escalating chaos on Mars, Dev's dark choices, Avery's trauma, the explosive standoff at Kuznetsov Station, and why this episode finally feels like peak FAM again. Plus: listener mail, our thoughts on the last two episodes, and why we're glued to the screen.Drop your thoughts at happyvalleyfam@gmail.com — we read every one!See you next week, Bobs!

What secret tech awaits in the new Strixhaven set? It's time to find out as we channel our inner Lorehold students to dig up the cards you NEED to know. Prepare yourselves and your spells because there are a ton of awesome new Commander staples ready to go in the 99 and help teach your opponents a lesson. Sharpen your quills; this is info worth noting! -------- SUPPORT US ON PATREON: Support the show and become a Patron! Be a part of our community, receive awesome rewards, and more! https://www.patreon.com/commandzone -------- BOOT.DEV: Click this link → https://www.boot.dev?promo=COMMANDZONE and use our code COMMANDZONE to get 25% off your first payment for boot.dev. Thank you Boot.Dev for Sponsoring! SHOPIFY: Power your business with Shopify. Start your one-dollar-per-month trial period today by going to: https://www.shopify.com/tcz  JOHANNES VOSS TOKEN COLLECTION: Our friend iconic Magic artist Johannes Voss has launched a new Kickstarter featuring OVER 50 stunning original tokens. Get your pledge in now while there's still time at: https://tinyurl.com/JVTokens -------- CARD KINGDOM: The Command Zone is sponsored by Card Kingdom! If you want to receive your cards in one safe package and experience the best customer service, make sure to order your Magic cards, sealed product, accessories, and more at Card Kingdom: http://www.cardkingdom.com/command ARCHIDEKT: Discover, build, catalog, and playtest on Archidekt, the deck-building website that makes it easy to brew brand new lists or manage your old favorites. Go to http://www.archidekt.com/commandzone to get started today! ULTRA PRO: Huge thanks to Ultra PRO for sponsoring this episode! Be sure to check out their amazing APEX sleeves and super classy MANA 8 product line. If you want to keep your cards protected and support the show, visit: https://ultrapro.com/command -------- Relevant Links: 10 PLAYER Commander Game!: https://youtu.be/CvyRDmwOeCs?si=MIhwZWPhvrdyA_Wg PleasantKenobi: YouTube: @PleasantKenobi Instagram: @PleasantKenobi Bluesky: @pleasantkenobi.bsky.social Strixhaven Continues A Worrying Trend | PleasantKenobi: https://youtu.be/v9CmNJPu48U?si=WmRKaz0oyYpDzZKv Follow us on TikTok: @thecommandzone -------- Follow us on Instagram: @CommandCast Follow us on Bluesky: @commandcast.bsky.social Follow us on Twitter: @CommandCast @JoshLeeKwai @jfwong @wachelreeks Follow us on Facebook: https://www.facebook.com/commandcast/ Email us: commandzonecast@gmail.com -------- Commander Rules and Ban List: https://magic.wizards.com/en/banned-restricted-list Learn more about your ad choices. Visit podcastchoices.com/adchoices

Click this link https://www.boot.dev?promo=KINDAFUNNY and use my code KINDAFUNNY to get 25% off your first payment for boot.dev. Thank you Boot.Dev for Sponsoring! If you're struggling with OCD or unrelenting intrusive thoughts, NOCD can help. Book a free 15 minute call to get started: https://learn.nocd.com/KINDAFUNNY Sign up for your one-dollar-per-month trial today at https://shopify.com/kindafunny More rumors of big changes at Xbox, Metro 2039 is coming this year, and Kingdom Come 2 was nominated for an LGBT award but the director wants you to know he's not woke though. Thank you for the support! Time Stamps - - Start - The new boss of Xbox is reportedly considering a Game Pass tier that would only include first-party Microsoft games - Wesley Yin-Poole @ IGN - Ad - BREAKING: The Studio Behind Last Year's Tony Hawk's Pro Skater 3 + 4 Remasters Hit With More Mass Layoffs As It Tries To Adapt To The Video Game Industry's New Normal, Ethan @ Kotaku - Metro 2039 is coming this year, a game ‘fundamentally changed' by Russia's illegal war - Jordan Middler @ VGC - Kingdom Come 2 director welcomes LGBT award nomination, then spends around 175 words explaining that it doesn't make him 'Woke' - Joshua Wolens @ PC Gamer - Gears of War Netflix Adaptation Receives Promising Update - Sam Sepiol @ Insider Gaming - A Pokémon ripoff was just pulled from Steam as its publisher takes control - Thomas Franzese @ Polygon - Wee News! - SuperChats & You‘re Wrong Learn more about your ad choices. Visit megaphone.fm/adchoices

Click this link https://www.boot.dev?promo=KINDAFUNNY and use my code KINDAFUNNY to get 25% off your first payment for boot.dev. Thank you Boot.Dev for Sponsoring!If you're struggling with OCD or unrelenting intrusive thoughts, NOCD can help. Book a free 15 minute call to get started: https://learn.nocd.com/KINDAFUNNYSign up for your one-dollar-per-month trial today at https://shopify.com/kindafunny Thank you for the support! Run of Show - - Start - How to Fix Nintendo - Mat's Take - Where's the WHIMSY?! - Sports Games - Ads - Tim's Pitch - SuperChats Learn more about your ad choices. Visit megaphone.fm/adchoices

Click this link https://www.boot.dev?promo=KINDAFUNNY and use my code KINDAFUNNY to get 25% off your first payment for boot.dev. Thank you Boot.Dev for Sponsoring!If you're struggling with OCD or unrelenting intrusive thoughts, NOCD can help. Book a free 15 minute call to get started: https://learn.nocd.com/KINDAFUNNYSign up for your one-dollar-per-month trial today at https://shopify.com/kindafunny Thank you for the support! Run of Show - - Start - How to Fix Nintendo - Mat's Take - Where's the WHIMSY?! - Sports Games - Ads - Tim's Pitch - SuperChats Learn more about your ad choices. Visit megaphone.fm/adchoices

Click this link https://www.boot.dev?promo=KINDAFUNNY and use my code KINDAFUNNY to get 25% off your first payment for boot.dev. Thank you Boot.Dev for Sponsoring!If you're struggling with OCD or unrelenting intrusive thoughts, NOCD can help. Book a free 15 minute call to get started: https://learn.nocd.com/KINDAFUNNYSign up for your one-dollar-per-month trial today at https://shopify.com/kindafunny PlayStation 6 gets backwards compatibility rumors, the Street Fighter movie drops a new trailer, and Ubisoft might be giving the Prince of Persia: The Lost Crown team another chance. Thank you for the support! Run of Show - - Start - PlayStation 6 Will Have Backward Compatibility With PS4 And PS5 Games, It's Claimed - Andrew Highton @ Insider Gaming - Ads - Street Fighter Movie gets a new trailer - BREAKING: Call of Duty movie Gets Release Date - Rumour: Ubisoft to Give Prince of Persia: The Lost Crown's Core Dev Team Another Chance - Robert Ramsey @ Push Square - Lana Del Rey Surprise-Drops James Bond ‘007 First Light' Theme Song - Jem Aswad @ Variety - Wee News! - SuperChats & You‘re Wrong Learn more about your ad choices. Visit megaphone.fm/adchoices

Click this link https://www.boot.dev?promo=KINDAFUNNY and use my code KINDAFUNNY to get 25% off your first payment for boot.dev. Thank you Boot.Dev for Sponsoring!If you're struggling with OCD or unrelenting intrusive thoughts, NOCD can help. Book a free 15 minute call to get started: https://learn.nocd.com/KINDAFUNNYSign up for your one-dollar-per-month trial today at https://shopify.com/kindafunny Thank you for the support! Run of Show - 00:00:00 - Start00:03:00 - Topic of the Show: What'd I Miss?00:03:30 - What have you been playing00:07:30 -Do you think there's value in challenging each other's opinions?00:14:15 - Pokopia, Whats your thoughts? Did you play it? Do you like it?00:15:40 - Why is pokemon screwing things up?00:18:20 - Nintendo switch 2 boost mode00:20:52 - What is Nintendo doing?00:26:15 - Leaks, Nintendo bans, and remakes00:32:24 - Ad00:36:00 - Blue Point Studio shutting down00:38:59 - Thoughts on Sony00:42:52 - Hi res Portal00:43:50 - is Asha Sharma going to ruin Xbox?00:46:25 - AI buying all the ram up and creating the shortage What do you think the next 5 years is going to look like00:50:33 - Give us the optimistic take on the game industry Learn more about your ad choices. Visit megaphone.fm/adchoices

Click this link https://www.boot.dev?promo=KINDAFUNNY and use my code KINDAFUNNY to get 25% off your first payment for boot.dev. Thank you Boot.Dev for Sponsoring!If you're struggling with OCD or unrelenting intrusive thoughts, NOCD can help. Book a free 15 minute call to get started: https://learn.nocd.com/KINDAFUNNYSign up for your one-dollar-per-month trial today at https://shopify.com/kindafunny God of War's next game could feature multiple mythologies, Rockstar hackers actually made Take-Two's stock increase, and could Spider-Man's model be teasing a new PlayStation game? Thank you for the support! Run of Show - - Start - Next God of War Features Multiple Mythologies - Rockstar hackers actually made Take-Two's stock increase, after leaking how much GTA Online is making - Ad - Spider-Man model appears to tease new PlayStation game in now-deleted post - Another Wildly Popular Roblox Game Is Becoming A Movie - The main theme for Vampire Crawlers was composed by Yoko Shimomura - Wee News! - RIP Jock Blaney - SuperChats & You‘re Wrong Learn more about your ad choices. Visit megaphone.fm/adchoices

Click this link https://www.boot.dev?promo=KINDAFUNNY and use my code KINDAFUNNY to get 25% off your first payment for boot.dev. Thank you Boot.Dev for Sponsoring!If you're struggling with OCD or unrelenting intrusive thoughts, NOCD can help. Book a free 15 minute call to get started: https://learn.nocd.com/KINDAFUNNYSign up for your one-dollar-per-month trial today at https://shopify.com/kindafunny Thank you for the support! Run of Show - Learn more about your ad choices. Visit megaphone.fm/adchoices

Click this link https://www.boot.dev?promo=KINDAFUNNY and use my code KINDAFUNNY to get 25% off your first payment for boot.dev. Thank you Boot.Dev for Sponsoring!If you're struggling with OCD or unrelenting intrusive thoughts, NOCD can help. Book a free 15 minute call to get started: https://learn.nocd.com/KINDAFUNNYSign up for your one-dollar-per-month trial today at https://shopify.com/kindafunny Thank you for the support! Run of Show - 00:00:00 - Start00:05:58 - Tomodachi Life: Living the Dream00:22:29 - Ads00:25:45 - Who Did Blessing Marry?!00:37:30 - The Price00:45:52 - What Would Greg Add?00:50:40 - SuperChats Learn more about your ad choices. Visit megaphone.fm/adchoices

Click this link https://www.boot.dev?promo=KINDAFUNNY and use my code KINDAFUNNY to get 25% off your first payment for boot.dev. Thank you Boot.Dev for Sponsoring!If you're struggling with OCD or unrelenting intrusive thoughts, NOCD can help. Book a free 15 minute call to get started: https://learn.nocd.com/KINDAFUNNYSign up for your one-dollar-per-month trial today at https://shopify.com/kindafunny Thank you for the support! Run of Show - - Start - Xbox Game Pass ‘has become too expensive,' says Microsoft's new gaming chief in leaked memo - Tom Warren @ The Verge - ‘Bloodborne' Video Game Getting R-Rated Animated Movie Adaptation From Sony - Brent Lang @ Variety - Ad - Rockstar Games Hack Update - Wesley Yin-Poole @ IGN - Silent Hill 2 remake studio Bloober Team announces leadership expansion and teases seven games in development - Fran Ruiz @ Eurogamer - Wee News! - SuperChats & You‘re Wrong Learn more about your ad choices. Visit megaphone.fm/adchoices

Click this link https://www.boot.dev?promo=KINDAFUNNY and use my code KINDAFUNNY to get 25% off your first payment for boot.dev. Thank you Boot.Dev for Sponsoring!If you're struggling with OCD or unrelenting intrusive thoughts, NOCD can help. Book a free 15 minute call to get started: https://learn.nocd.com/KINDAFUNNYSign up for your one-dollar-per-month trial today at https://shopify.com/kindafunny Rockstar confirms new data breach, Fable delay rumors, and an Xbox first look is coming this week for a new Metro game. Thank you for the support! Run of Show - 00:00:00 - Start00:05:49 - Rockstar confirms new data breach, after hacker group threatens: ‘Pay, or we leak'00:12:06 - Fable Social Media Account Reiterates Fall 2026 Release Window Amid Rumors of an Internal Delay to Avoid GTA 600:23:04 - A new Metro game has been confirmed and will get an Xbox 'First Look' this week00:25:46 - Ad00:29:14 - Ex-Bethesda Exec Says The Elder Scrolls 6 Maker Isn't Part Of Something ‘Genuine' Or ‘Authentic' At Microsoft00:36:33 - Epic Is Reportedly Making A Disney-Themed Extraction Shooter00:45:07 - Wee News!00:47:54 - SuperChats & You‘re Wrong Learn more about your ad choices. Visit megaphone.fm/adchoices