Podcasts about Harness

In honor of Men's Mental Health Month, we're revisiting an episode we've always been proud of from 2022 with Charlamagne tha God (host of the widely popular radio show, The Breakfast Club, bestselling author, philanthropist) as he discusses his journey to discovering his true self apart from his famous radio persona, how CBT therapy taught him to unlearn, and his positive and frightening encounters with the spirit realm. He opens up about his history with panic attacks, the vigilance he developed while selling drugs, and how anxiety can sometimes be his superpower. Charlamagne details growing up Jehovah's Witness, why he believes God is a woman, and the origins of his dark sense of humor. He explains why he uses his authentic, unapologetic voice to touch on touchy subjects especially around mental health gaps in the Black community, including the intergenerational trauma and institutional racism that can prevent minorities from seeking support. Mayim and Charlamagne consider anxiety around returning to our hometowns and bond over their love for Marvel comics and Judy Blume books.Make your summer wardrobe feel easier. Go to https://www.quince.com/breakdown for free shipping on your order and 365-day returns.Go to https://tidd.ly/4uVltMe and use the code MAYIM50 to get $50 off your Elastique order.Follow us on Substack for Exclusive Bonus Content: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠https://bialikbreakdown.substack.com/⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠BialikBreakdown.com⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠YouTube.com/mayimbialik⁠⁠⁠See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Welcome to Part 5 of the Walk Into the Biggest Quantum Jump of Your Life Guided Walking Meditation series. One of the biggest misconceptions about personal growth is that people are lacking something. More confidence. More clarity. More motivation.     But what if the problem isn't that you're lacking power at all?  What if you've simply been directing it in too many different places?    In this quantum walking journey, you'll explore what it means to harness your power instead of leaking it. You'll discover how scattered energy, competing priorities, overthinking, and emotional distractions can keep even the most capable people from moving toward the life they truly want.    Using the Fire Horse and jockey framework, this walk is designed to help you reconnect with your personal power, identify where your energy is currently going, and consciously decide where you want it to go next.  Because the Fire Horse doesn't need more strength. It needs direction.    RESOURCES MENTIONED:    Get Your Fire Horse Identity Journal HERE The first 1,111 people can download this for free during this special Fire Horse activation window.    Special offer for my Quantum Walkers wanting to accelerate their results using my money healing and manifestation landmark program, Make More Work Less: GET IT HERE    >> Join the famous ProjectME Posse Community where dream businesses are built by staying on track while applying my proven growth strategies HERE    CONNECT WITH TIFF:  Tiffany on Instagram @projectme_with_tiffany   Tiffany on TikTok @projectme_with_tiffany  Tiffany on YouTube: ProjectME TV  Tiffany's FREE Email Community: JOIN HERE > The Secret Posse Digest    During Part 5 you'll discover:  • Why most people aren't lacking power, they're simply directing it in too many places  • How scattered energy can quietly slow progress, clarity, and momentum  • The difference between having power and consciously harnessing it  • Where your energy may currently be leaking without you realizing it  • Why direction is often more important than motivation  • How to reconnect with the version of yourself capable of leading your next chapter  • The Fire Horse lesson that transforms power into forward movement  • Why every quantum jump begins with deciding where your energy is going next 

This is episode 855. Read the complete transcription on the Sales Game Changers Podcast website. Watch the video of this podcast on YouTube here. The Sales Game Changers Podcast was recognized by YesWare as the top sales podcast. Read the announcement here. FeedSpot named the Sales Game Changers Podcast at a top 20 Sales Podcast and top 8 Sales Leadership Podcast! Subscribe to the Sales Game Changers Podcast now on Apple Podcasts! Purchase Fred Diamond's best-sellers Love, Hope, Lyme: What Family Members, Partners, and Friends Who Love a Chronic Lyme Survivor Need to Know and Insights for Sales Game Changers now! Today's show featured an interview with Matthew Radomski, Regional Vice President of Federal Civilian at Harness. Find Matt on LinkedIn. MATT'S TIP: "The customer is the North Star. Their success should be your success. Everything else figures itself out. Don't focus on selling. Focus on their value and what matters to them, and then help them along the way."

Our 249th episode with a summary and discussion of last week's big AI news!Recorded on 06/17/2026Note: work has kept me from publishing episodes promptly, apologies! I'll get back on schedule soon.Hosted by Andrey Kurenkov and Jeremie HarrisFeel free to email us your questions and feedback at andreyvkurenkov@gmail.com and/or hello@gladstone.aiRead out our text newsletter and comment on the podcast at https://lastweekin.ai/In this episode:Anthropic cut off access to Fable 5 and Mythos 5 after a US government order tied to alleged jailbreaks, prompting debate over inconsistent policy, export controls, and the practicality of preventing jailbreaks.SpaceX completed an IPO at a roughly $1.75T valuation and then moved to acquire AI coding startup Cursor for $60B, positioning xAI with Cursor's talent, data, and product to compete more effectively in coding.Infrastructure and business updates include Anthropic pursuing direct US data center leases backed by Google, leaked documents showing OpenAI's revenue growth alongside large losses, and chatbot market share shifting with ChatGPT below 50% as Gemini and Claude gain.Projects and policy highlights include OpenRouter's Fusion multi-model synthesis, new open releases from Moonshot, Qwen, and NVIDIA, DOJ support for xAI's unpermitted gas turbines in Memphis, and a Munich court ruling Google liable for false AI Overview statements.Timestamps (note - these don't take into account dynamically inserted ads and therefore may be off by a couple of minutes):(00:00:10) Intro / Banter(00:03:38) Ad break + news previewTools & Apps(00:04:52) Anthropic cuts off Fable 5 and Mythos 5 access following government order | The Verge + All the news about Anthropic's new AI fight with the White House(00:25:53) Facebook's new AI Mode search gets its info from public posts | The VergeApplications & Business(00:27:00) SpaceX to acquire the AI coding startup Cursor for $60 billion(00:35:42) Anthropic pursues data center leases, seeks financial backing from Google, The Information reports | Reuters(00:40:10) Leaked financial docs show OpenAI is losing billions of dollars a year - Ars Technica(00:46:00) ChatGPT's market share slips below 50% for first time | TechCrunch(00:50:34) ‘Tell Him He's a Piece of Shit': Meta's New AI Unit Is a Total Mess | WIRED(00:56:23) Sakana AI Commercializes AB-MCTS in Sakana Marlin, an Enterprise Agent Generating Up to 100-Page Research Reports With Slides - MarkTechPostProjects & Open Source(00:59:36) Surpassing Frontier Performance with Fusion — OpenRouter Blog(01:03:00) Moonshot AI Releases Kimi K2.7-Code: a Coding Model Reporting +21.8% on Kimi Code Bench v2 Over K2.6 - MarkTechPost(01:08:34) Meet Qwen-RobotSuite: Three Embodied AI Models for VLA Manipulation, Video World Modeling, and Navigation - MarkTechPost(01:11:29) Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning(01:17:31) ProCUA-SFT Technical ReportPolicy & Safety(01:20:33) DOJ Lawyers Argue xAI Is ‘Vital' for National Security in NAACP Lawsuit | WIRED + People Living Near xAI's Dirty Data Centers Are Pissed About the SpaceX IPO(01:25:29) A Court Has Ruled That Google Is Liable for False Statements Generated by AI Overviews | WIRED(01:28:47) Why Do Naive SFT Filters For Safety Properties Fail?Research & Advancements(01:34:14) From AGI to ASI(01:39:44) Artificial Analysis Intelligence Index v4.1: a shift toward agentic workloads(01:42:12) SIA: Self Improving AI with Harness & Weight UpdatesSee Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Ed Harness is a graduate of Marquette University School of Law. Prior to law school, he was Police Officer in Milwaukee Wisconsin. he graduated Cum Laude with a Bachelor of Arts in Management of Criminal Justice Operations from Concordia University. In 2015, Albuquerque's Civilian Police Oversight Agency Board selected Ed Harness to be the first Executive Director of the Civilian Police Oversight Agency. Like his previous role in Albuquerque, he again is tasked here in Louisville with directing an agency to provide oversight of the police department. Mr. Harness is a member of the . National Association for Civilian Oversight of Law Enforcement (NACOLE) He is a Certified Practitioner of Oversight (CPO) holder. ED Harness was the 2023 recipient of the NACOLE “Achievement in Oversight Award” and was voted into a three-year term as a Member at Large to the NACOLE Board of Directors. ED Harness is also a member of Association of Inspectors General (AIG). He became a Certified Inspector General in 2023.

O que é GEO e por que sua marca precisa aparecer nas respostas do ChatGPT, Gemini e Perplexity antes dos seus concorrentes? O SEO não morreu, mas o jogo mudou. Com a ascensão das IAs generativas, não basta mais ranquear no Google: é preciso ser a resposta que os modelos de linguagem escolhem quando alguém pergunta sobre o seu mercado. Neste episódio do Papo Social Media, Rafael Kiso e Marcio Silva recebem Diego Ivo, CEO e fundador da Conversion, maior agência de SEO do Brasil, para uma aula completa sobre GEO (Generative Engine Optimization) e o impacto da busca generativa no marketing digital. A conversa explora como funciona a lógica dos tokens nas LLMs, porque o LinkedIn é hoje a principal fonte citada pelas IAs em contexto B2B, como o framework EEAT do Google se aplica diretamente ao posicionamento nas ferramentas de IA, e quais estratégias práticas qualquer marca pode adotar agora para treinar os modelos de linguagem a seu favor. Um episódio essencial para profissionais de marketing, agências e gestores que querem entender o novo cenário da busca e garantir visibilidade na era da inteligência artificial. 00:00:08 Introdução e apresentação de Diego Ivo 00:01:40 O que é GEO, AIO e os diferentes termos para a otimização em IAs generativas 00:05:00 A fragmentação das buscas: Google, YouTube, TikTok, marketplaces e LLMs 00:07:55 Como funcionam os tokens e por que sua marca precisa ser o próximo token mais provável 00:09:24 LLMs consultam o Google em tempo real: por que o SEO está mais vivo do que nunca 00:10:19 GEO vs SEO: o guarda-chuva da busca e a ressignificação do que é otimização 00:13:00 A migração do clique para a resposta: o fim do modelo baseado em last click 00:16:57 Autoatribuição: a métrica mais poderosa para entender de onde vêm seus clientes 00:20:23 Zero click search: buscas sem clique crescem de 56% para 69% no Google 00:21:20 ChatGPT, Claude e o novo cenário competitivo das IAs generativas 00:25:48 Framework EEAT: Experience, Expertise, Authority e Trustworthiness aplicados ao GEO 00:31:26 Por que o LinkedIn é a fonte número 1 das LLMs em contexto B2B 00:33:41 Artigos e newsletters do LinkedIn vs posts do feed: o que as IAs realmente consomem 00:34:20 TikTok e indexação por áudio: o próximo passo das LLMs para vídeos 00:36:10 Branding semântico: como treinar os modelos de linguagem com os atributos da sua marca 00:41:10 Fontes externas que mais influenciam as LLMs 00:44:39 As principais digas técnicas para aparecer nas respostas de buscas 00:54:02 Thought leadership e founder-led growth: por que o executivo precisa criar conteúdo 00:58:31 Conteúdo factual e recência: como funciona para as LLMs 01:02:50 As principais métricas do GEO: autoatribuição, share of search, CAC e LTV 01:09:10 O futuro: de assistentes para agentes que operam processos inteiros 01:10:32 Inteligência vs julgamento: o que pode ser automatizado e o que ainda é humano 01:14:05 Harness proprietário: como criar arquiteturas de agentes que geram diferenciação competitiva 01:23:09 Encerramento  Acompanhe   Diego Ivo: LinkedIn - https://www.linkedin.com/in/diegoivo/  | Instagram - https://www.instagram.com/diegoivo  Conversion: LinkedIn - https://www.linkedin.com/company/agenciaconversion/ |   Instagram - https://www.instagram.com/agenciaconversion/  Rafael Kiso: LinkedIn - https://www.linkedin.com/in/rafaelkiso/ | Instagram -  https://www.instagram.com/rafaelkiso/  Potencialize sua gestão de mídias sociais com a plataforma mais usada por agências e profissionais no Brasil! Teste grátis a mLabs agora mesmo: https://mla.bs/8f82d839

Welcome to ‘Square Gaiters' – The local Harness Racing Show. This is a part of the Super Saturday Sports Show that you can listen to as to keep up to date with all things happening around the place in the world of Harness Racing. This show airs on a weekly basis on a Saturday, throughout the year and is hosted by Mark 'The Stats Man' Owens along with local racing identity Daniel Hibberd, on ONE FM Shepparton Radio. This week's program first aired on Saturday the 20th of June, 2026 on ONE FM 98.5 Shepparton. Contact the station on admin@fm985.com.au or (+613) 58313131 The ONE FM 98.5 Community Radio podcast page operates under the license of Goulburn Valley Community Radio Inc. (ONE FM) Number 1385226/1. PRA AMCOS (Australasian Performing Right Association Limited and Australasian Mechanical Copyright Owners Society) that covers Simulcasting and Online content including podcasts with musical content, that we pay every year. This licence number is 1385226/1.

Shahram Anver is the Co-Founder and CEO of Cleric, the autonomous AI SRE that investigates and root-causes production issues like an experienced teammate — often in under two minutes. Before Cleric, Shahram led MLOps, DevOps, and FinOps platform engineering at Gojek, Southeast Asia's super-app. In this conversation, he breaks down why production operations never kept pace with AI-accelerated development, and why the real unlock for an AI SRE isn't faster triage — it's an agent that *learns* and compounds operational memory across your whole org.In this episode:

Você usa o Copilot para responder perguntas ou para executar fluxos inteiros de desenvolvimento com os padrões do seu time? Neste Snippet, recebemos Breno Gonçalves Barbosa, Desenvolvedor de Software na dti digital. Ele mostra, na prática, como montar um ecossistema completo de agentes no GitHub Copilot, criando instructions que padronizam a geração de código, hooks que bloqueiam comandos destrutivos antes de serem executados, skills que ensinam as convenções do time para a LLM e agentes que orquestram tudo isso em fluxos autônomos de desenvolvimento. Dê o play e ouça agora!Assuntos abordados:Agentes x chat Copilot;Instructions e applyTo;Hooks e guardrails;Skills reutilizáveis;Harness e governança;Criação em linguagem natural;Ecossistema GitHub.Links importantes:Vagas disponíveisNewsletterDúvidas? Nos mande pelo LinkedinContato:  entrechaves@dtidigital.com.brO Entre Chaves é uma iniciativa da dti digital, uma empresa WPP #desenvolvimentodesoftware

In this episode of The Greatest Machine, host Darius Mirshahzadeh interviews John Berkowitz, a serial entrepreneur who built multiple successful companies in the real estate and technology sectors. John shares his journey from failed pharmaceutical sales interviews to co-founding Yodle (a company that grew to 1,000 employees and hundreds of millions in revenue), creating OJO Labs, and eventually merging with Lower. The conversation explores the evolution of entrepreneurship, lessons learned from building and selling companies, and the future of AI in real estate and mortgage industries. In this episode, Darius and John will discuss: (00:00) Introduction and Background (02:04) John Berkowitz's Entrepreneurial Journey (08:37) Lessons from Yodel's Success and Challenges (16:58) Starting OJO and Its Evolution (23:22) OJO's Impact on Real Estate and Technology (24:25) The Journey to Acquiring Movoto (27:36) Integrating Real Estate and Mortgage (30:48) The Merger with Lower (35:29) Understanding the Real Estate Market (39:59) The Impact of AI on Real Estate (48:00) Overcoming Barriers to Greatness John Berkowitz is the President of Real Estate at Lower and General Manager of Movoto, where he leads efforts to integrate real estate search, agent support, and financing into a seamless homeownership experience. A seasoned entrepreneur and real estate technology leader, Berkowitz founded OJO Labs to help consumers make smarter homebuying decisions through personalized technology. He is also an EY Entrepreneur Of The Year Central Texas Award winner, recognized for his impact and innovation in the real estate industry. Connect with John: LinkedIn: https://www.linkedin.com/in/johnberkowitz  OJO Labs: https://ojo.com/ Lower: https://www.lower.com/  Connect with Darius: Website: https://therealdarius.com/ Linkedin: https://www.linkedin.com/in/dariusmirshahzadeh/ Instagram: https://www.instagram.com/imthedarius/ YouTube: https://www.youtube.com/@Thegreatnessmachine  Book: The Core Value Equation https://www.amazon.com/Core-Value-Equation-Framework-Limitless/dp/1544506708 Write a review for The Greatness Machine using this link: https://ratethispodcast.com/spreadinggreatness.  Learn more about your ad choices. Visit megaphone.fm/adchoices

The browser has become the primary gateway to work, data, and AI. In this episode, Arunesh Chandra, Head of Product, Microsoft Edge for Business at Microsoft Edges for Business, will discuss why security and IT teams are rethinking the role of the browser and what sets Edge for Business apart as a secure, enterprise-ready solution. Arunesh cover how built-in security, native integration with existing IT tools, and centralized management can simplify operations, reduce risk, and support modern work across managed devices, BYOD, and contractors. A must listen for IT pros and security experts navigating browser sprawl and AI adoption. This segment is sponsored by Microsoft Edge for Business. Visit https://securityweekly.com/edgeforbusiness to learn more about them! In the leadership and communications segment, CISO role changes as cyber-risk appetites in the C-suite grow, AI is exposing the biggest weakness in cybersecurity: We never built a health model. Until now!, 6 Ways Leaders Harness Stress, and more! Visit https://www.securityweekly.com/bsw for all the latest episodes! Show Notes: https://securityweekly.com/bsw-452

The browser has become the primary gateway to work, data, and AI. In this episode, Arunesh Chandra, Head of Product, Microsoft Edge for Business at Microsoft Edges for Business, will discuss why security and IT teams are rethinking the role of the browser and what sets Edge for Business apart as a secure, enterprise-ready solution. Arunesh cover how built-in security, native integration with existing IT tools, and centralized management can simplify operations, reduce risk, and support modern work across managed devices, BYOD, and contractors. A must listen for IT pros and security experts navigating browser sprawl and AI adoption. This segment is sponsored by Microsoft Edge for Business. Visit https://securityweekly.com/edgeforbusiness to learn more about them! In the leadership and communications segment, CISO role changes as cyber-risk appetites in the C-suite grow, AI is exposing the biggest weakness in cybersecurity: We never built a health model. Until now!, 6 Ways Leaders Harness Stress, and more! Show Notes: https://securityweekly.com/bsw-452

The browser has become the primary gateway to work, data, and AI. In this episode, Arunesh Chandra, Head of Product, Microsoft Edge for Business at Microsoft Edges for Business, will discuss why security and IT teams are rethinking the role of the browser and what sets Edge for Business apart as a secure, enterprise-ready solution. Arunesh cover how built-in security, native integration with existing IT tools, and centralized management can simplify operations, reduce risk, and support modern work across managed devices, BYOD, and contractors. A must listen for IT pros and security experts navigating browser sprawl and AI adoption. This segment is sponsored by Microsoft Edge for Business. Visit https://securityweekly.com/edgeforbusiness to learn more about them! In the leadership and communications segment, CISO role changes as cyber-risk appetites in the C-suite grow, AI is exposing the biggest weakness in cybersecurity: We never built a health model. Until now!, 6 Ways Leaders Harness Stress, and more! Visit https://www.securityweekly.com/bsw for all the latest episodes! Show Notes: https://securityweekly.com/bsw-452

The browser has become the primary gateway to work, data, and AI. In this episode, Arunesh Chandra, Head of Product, Microsoft Edge for Business at Microsoft Edges for Business, will discuss why security and IT teams are rethinking the role of the browser and what sets Edge for Business apart as a secure, enterprise-ready solution. Arunesh cover how built-in security, native integration with existing IT tools, and centralized management can simplify operations, reduce risk, and support modern work across managed devices, BYOD, and contractors. A must listen for IT pros and security experts navigating browser sprawl and AI adoption. This segment is sponsored by Microsoft Edge for Business. Visit https://securityweekly.com/edgeforbusiness to learn more about them! In the leadership and communications segment, CISO role changes as cyber-risk appetites in the C-suite grow, AI is exposing the biggest weakness in cybersecurity: We never built a health model. Until now!, 6 Ways Leaders Harness Stress, and more! Show Notes: https://securityweekly.com/bsw-452

"A Random Podcast"   I sat down with Chris Svanosio to chat about a range of topics, including his five runners in the Inter Dominion at The Creek . We go through each of them, talk about Aldebaran Ada and Kyvalley Diablo in detail, and discuss what Chris would like to see changed. Sit back and enjoy.

Kimberly speaks with nutrition and fitness legend Harley Pasternak who shares his expertise and knowlege on a balanced, evidence-based approach to nutrition, debunking myths about carbs, fats, and supplements, emphasizing moderation and the importance of understanding food quality.Chapters00:00 The Joy of Balance in Diet02:58 The Impact of Social Media on Health Trends05:43 The Politics of Food Guidelines09:02 Lessons from the Healthiest Cultures11:56 The Evolution of Dietary Trends14:51 Understanding Carbohydrates and Health22:01 Debunking Diet Myths28:16 The PATH to Balanced Eating34:32 Hormones and Nutrition36:56 The GLP-1 Phenomenon42:03 Finding Balance in NutritionSponsors: LMNTOFFER: Right now, for my listeners LMNT is offering a free sample pack with any LMNT drink mix purchase at DrinkLMNT.com/FEELGOOD. That's 8 single serving packets FREE with any LMNT any LMNT drink mix purchase. This deal is only available through my link so. Also try the new LMNT Sparkling — a bold, 16-ounce can of sparkling electrolyte water.USE LINK: DrinkLMNT.com/FEELGOODHarley Pasternak Resources: Book: The Carb Reset: Store Less Fat, Burn the Rest, and Harness the Power of Carbs to Lose Weight Website: harleypasternak.com Bio: Harley Pasternak, M.SC., is a celebrity trainer and nutritionist who holds a Master of Science in exercise physiology and nutritional sciences from the University of Toronto. He has served as an exercise and nutrition scientist for Canada's Department of National Defense, and he's a New York Times Bestselling Author whose books include “5-Factor Fitness,” “5-Factor Diet” and “The Body Reset Diet.” Harley's titles have attained global bestseller status, which has led to translation in 14 languages in more than 25 countries around the globe. As a fitness and nutrition specialist, Pasternak has trained many celebrities, including Lady Gaga, Rihanna, Halle Berry, Katy Perry, Megan Fox, Robert Downey Jr., Robert Pattinson, Jessica Simpson, Ke$ha, Hilary Duff and Jennifer Hudson. He has appeared on MTV, “The Oprah Winfrey Show,” “Dr. Oz” and others, and he's been covered in publications from The Washington Post to Shape Magazine. Pasternak has made speaking appearances in more than 30 countries for a diversity of Fortune 500 companies, health and fitness organizations, and government entities. He's a Toronto native and resides with his wife and daughter in Los Angeles. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

As an economic powerhouse, California charges forward. The benefits, though, are distributed and felt unequally, especially in places like the Central Valley. Here, thousands of farmworkers feed the nation while facing food insecurity themselves, rural communities struggle to access adequate health care, the housing market is in an affordability crisis, and neighborhood inequality persists. But the region is changing: with steady population growth, reformed labor union legislation, the promise of California High-Speed Rail, and burgeoning arts and culture scenes. And it's shifting California power dynamics with it, away from the coastal cities and into the Valley's major cities like Fresno, Bakersfield, Merced, and Stockton. How are leaders in Fresno harnessing these changes to transform their region for the better? And what does it mean for the Central Valley and for California? Featured guests:
Danielle Bergstrom (Founder and Editor-in-Chief, Fresnoland)
Betsy McGovern-Garcia (Vice President, Self-Help Enterprises)
Joe Prado (Director, Fresno County Department of Public Health)
Gurdeep Shergill (Radio Host, “Shaan Punjab Di” and City of Fresno Planning Commissioner) This program is co-presented by Zócalo Public Square, Fresnoland, and Arte Américas, with generous support from The James B. McClatchy Foundation, Central Valley Community Foundation, and The James Irvine Foundation, with media partner KVPR. This program is part of Zócalo's series “What Connects California?,” marking the 175th anniversary of California's statehood.

Why do so many businesses hit a ceiling at around 10 employees? Many founders start their business because they're brilliant at what they do. In the early days, decisions are fast, communication is simple, and the founder sits at the centre of everything. Then the business grows. Suddenly, what made the business successful starts to become the thing holding it back. In this episode of ScaleUp Radio, Kevin Brent speaks with Tameron Chappell, founder of  Athinka, a business psychology consultancy that helps organisations build healthier, higher-performing teams using evidence-based psychology rather than management fads and airport business books. Tameron explains why the transition beyond 10 employees is one of the most challenging moments in a founder's journey, how personality dynamics influence team performance far more than technical capability, and why shared leadership is critical for sustainable growth. About Tameron Chappell Tameron is the founder of  Athinka, a consultancy specialising in business psychology and team effectiveness. Working primarily with startups and scale-ups, Tameron combines psychodynamic and systemic approaches to help founders and leadership teams understand the hidden patterns, behaviours and relationships that influence performance. His work often begins when traditional consulting approaches have failed to deliver lasting results, helping organisations uncover the deeper causes of team dysfunction and leadership challenges. In this episode: Why businesses often stall at 10 employees Many founders unknowingly create a business model that relies entirely on them. As the team grows, this becomes unsustainable. The founder becomes the bottleneck for decisions, problem-solving and accountability. Tameron explains why the 10-person mark is a critical inflection point and why leaders must begin building shared ownership and leadership much earlier than they think. The uncomfortable reality of scaling leadership One of the biggest mindset shifts for founders is recognising that they may not always be the best person for their current role. Growth requires leaders to continually evolve and sometimes redefine their responsibilities. Tameron discusses why succession planning, delegation and leadership development should be part of the scaling conversation from day one. Why personality matters more than technical skills Recruitment often focuses heavily on experience, qualifications and technical competence. However, Tameron argues that personality fit, behavioural tendencies and stress responses are often far better predictors of long-term success. Past performance in one environment does not guarantee success in another. Understanding how individuals naturally operate under pressure can significantly improve hiring decisions and team performance. Understanding the psychology behind team dynamics Rather than viewing personality through simplistic labels and categories, Tameron describes personality as a complex mixing deck of traits that interact differently depending on circumstances. Helping team members understand their own preferences and those of colleagues can reduce conflict, improve communication and increase trust. Evidence-based business psychology Athinka's approach is grounded in established psychological theory and research. The consultancy combines: • Psychodynamic approaches to explore the relationship between an individual's inner world and workplace behaviour. • Systemic approaches to uncover hidden organisational patterns and group dynamics. The result is practical insight that helps teams function more effectively and leaders make better decisions. Standout Quote "Most businesses don't stop growing because of strategy. They stop growing because the founder's control model no longer works." Key Takeaways • The 10-employee mark is often the first major scaling challenge. • Founders must evolve their leadership style as the business grows. • Shared leadership creates stronger, more resilient organisations. • Personality and behavioural fit matter more than technical skills alone. • Team effectiveness improves when people understand how others naturally operate. Resources mentioned in the episode: Internal Family Systems - https://ifs-institute.com/ Lumina Splash App - https://luminalearning.com/our-products/lumina-splash-app Co-Pilot - Claude -   From Tameron: If you're a founder and you're curious about the psychology underneath your business — the patterns, the dynamics, the parts of you that show up under pressure — here are some resources I often recommend: Edgar Schein's work on Humble Leadership for the fundamental shift from 'expert' to open-minded curiosity which is the foundation of all relational leadership. Mike Hohnen's practical interpretation of Dave Snowden's Cynefin model, especially for founders navigating complexity, pace and ambiguity. Mike makes complexity human and usable. Richard Schwartz's Internal Family Systems (IFS) for understanding your inner architecture, your triggers, and how to lead yourself with more clarity and compassion. His book No Bad Parts is a great entry point. Systemic thinking for teams and organisations = anything that helps you uncover the hidden patterns around you. John Whittington's blogs (start with his views on Founders and their Origin Story https://www.linkedin.com/posts/johntkwhittington_systemiccoaching-founders-theoriginstory-activity-7452030365994569728-s7wJ?utm_source=share&utm_medium=member_desktop&rcm=ACoAAAC1NiYBYHjcV1QthjsMa96N6IIja61N-Mo ), Jan Jacob Stam's Systemic Leadership, and Tess Cope's Harness and Your Team Is Not The Issue are excellent. Trait‑based personality models such as Lumina Spark, Hogan, or NEO Primary Colours. These help you understand behaviour under pressure and in context. (N.B. Not Type tools like MBTI, DISC, Insights or Strengths, they're fun and ubiquitous, but they don't stand up to psychological scrutiny. If you want something highly practical, David Marquet's intent‑based leadership work (Turn the Ship Around, Leadership is Language) and his short Leadership Nudges videos on YouTube are brilliant for everyday behavioural shifts. And of course… if you've got humans in your business and don't fancy reading all these theories and ideas come and find me - I'm always curious about your world, your successes and challenges. Find me on LinkedIn or at Tameron.Chappell@athinka.com and if you mention you came across me via Kevin's podcast I can offer you a no-strings-attached Diagnostic Conversation where we can focus on your situation, leadership, team and organisation. 

Join Mikee P., Ray Cotolo, Adam Bowden from Diamond Creek Farm and John Rallis from WEG for a look at the North America Cup Card Saturday at Woodbine Mohawk.

Anthropic just dropped a dragon-class model on our laps, but can you steer it without torching your codebase in the process? This week on the Friday Deploy, Ben and Andrew unpack the sudden arrival of Fable 5 and how to leverage it to scrutinize your systems before the massive API paywall hits. They also take aim at the unsustainable trend of tokenmaxxing and explore how intelligent model routing can drastically cut your AI spend. Finally, they tackle the unmaintainable mess left behind by AI rockstar developers and share how they are orchestrating their own agent-to-agent collaboration.OFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

SUMMARY: If the cost of public AI continues to rise, because of various market shortages, should CIOs start looking at backup plans to better own their AI journeys and futures?SHOW: 1036SHOW TRANSCRIPT: The Enterprise AI Show #1036 TranscriptSHOW VIDEO: https://youtu.be/ZgkMF7G3YfoSHOW SPONSORS:OutShift by Cisco - “Scaling Out Superintelligence”  The Internet of Cognition architectureShareGate - ShareGate Protect. Microsoft 365 Governance, we got this!Nasuni - Activate your data for AI and request a demoSHOW NOTES:Andy Weir (The Martian) on Eps. 193Systems of Record Won the SaaS Era - Clearinghouses Will Win the Agents EraHarness Engineering is where Enterprise AI becomes realTHESIS: It comes up as different control points, but CIOs are ultimately trying to figure out how to get the value from Enterprise AI while delivering a set of consistency across different teams and use-cases. Let's explore what this “Enterprise Harness” is starting to look like. Enterprise Clearinghouse Enterprise Intelligence (a.k.a. Middleware)Enterprise Catalog - Models as a Service, Agents as a ServiceEnterprise Skills or Shareable Prompt HarnessesSymantec Routing to ModelsAI Gateway ControlsFEEDBACK?Email: show @ the enterprise ai show dot comeBluesky: @TheEntAIShow.bsky.socialTwitter/X: @TheEntAIShowInstagram: @TheEntAIShow

SpaceX alumni Andrew Redd is betting the ocean has vast amounts of untapped geothermal energy. Also, the funding round was led by Norwest, with participation from S Capital VC, Cerca Partners, and Oceans Ventures. Snowflake Ventures also participated as a strategic investor. Learn more about your ad choices. Visit podcastchoices.com/adchoices

The entire startup ecosystem is racing to build agent harnesses. Logan Kilpatrick, who leads Google AI Studio and the Gemini API, argues that scramble has a roughly 12-month shelf life. Models will absorb the scaffolding and run it natively, so the edge moves elsewhere. Google's own bet runs in parallel: a single agent harness, born from the Windsurf team and now called Antigravity, has become the connective tissue across search, the Gemini app, Cloud, and AI Studio — the role Gemini-the-model used to play. Logan makes the case that coding already feels like narrow superintelligence, and that "jagged" vertical superintelligence (in math, finance, and science) will arrive well before AGI. He argues Google's real goal is maximizing outcomes for users, not eyeball time. He unpacks Omni, the single model built to replace multiple separate systems Google once trained for text, audio, music, image, and video. His throughline: AI is an accelerant for human ambition, not a substitute for it. Hosted by Sonya Huang, Sequoia Capital

We've got mail! Jonathan and Honey answer your questions about cinema, films, family and everything in between. This week, Jonathan pitches his million dollar cinema idea, the pair discuss the Hacks finale, and they head to their DMs to give some New York recommendations and revisit iconic horror moments.Let us know what you think! You can get involved by following us on Instagram and sending us a DM on @reeltalkrossThanks for listening. Listen and subscribe to Reel Talk wherever you get your podcasts.

We talk to Kelly Perkins, Senior Director of Marketing for Sound Control Technologies about what they will have in store for booth C5125 in the Central Hall. We also discuss their work with USB-C for solutions and integration across different devices.See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Birgitta Böckeler, Distinguished Engineer at Thoughtworks, returns to discuss the rapid evolution of AI in software delivery. She touches on the evolution from vibe coding, the changing tools landscape and the more autonomous agents that, besides higher velocity, introduce higher risk. Read a transcript of this interview: https://bit.ly/4o62JHU Newsletter: Subscribe to the Software Architects' Newsletter for your monthly guide to the essential news and experience from industry peers on emerging patterns and technologies: https://www.infoq.com/software-architects-newsletter InfoQ online certification cohorts: Online cohorts for senior engineers and architects, built around QCon talks. Join a 5-week confidential peer group to validate your approach and apply practitioner frameworks to the technical challenges you face at work. Learn more: https://certification.qconferences.com/ Upcoming Events: QCon AI Boston 2026 (June 1-2, 2026) Learn how real teams are accelerating the entire software lifecycle with AI. https://boston.qcon.ai QCon San Francisco 2026 (November 16-20, 2026) https://qconsf.com/ The InfoQ Podcasts: Weekly inspiration to drive innovation and build great teams from senior software leaders. Listen to all our podcasts and read interview transcripts: - The InfoQ Podcast https://www.infoq.com/podcasts/ - Engineering Culture Podcast by InfoQ https://www.infoq.com/podcasts/#engineering_culture - Generally AI: https://www.infoq.com/generally-ai-podcast/ Follow InfoQ: - Mastodon: https://techhub.social/@infoq - X: https://x.com/InfoQ?from=@ - LinkedIn: https://www.linkedin.com/company/infoq/ - Facebook: https://www.facebook.com/InfoQdotcom# - Instagram: https://www.instagram.com/infoqdotcom/?hl=en - Youtube: https://www.youtube.com/infoq - Bluesky: https://bsky.app/profile/infoq.com Write for InfoQ: Learn and share the changes and innovations in professional software development. - Join a community of practitioners. - Increase your visibility. - Grow your career. https://www.infoq.com/write-for-infoq

This week on the Friday Deploy, Ben and Andrew unpack the AI build-versus-buy debate, Microsoft's new independent foundation models, and the growing revolt of mathematicians against unsubstantiated AI-generated proofs. The hosts also explore Stanford's Socratic rulebook for AI coding assistants and discuss Kent Beck's warning that engineering teams need to build "trust factories" to counter the rapid chaos of AI-assisted development. Finally, they close with a defense of Linux primitives and why you should probably be using a systemd timer instead of the latest shiny AI tool. Learn why: LinearB is a Leader in the 2026 Gartner® Magic Quadrant™ for Developer Productivity Insight PlatformsFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:The AI SaaSpocalypse is a mirageMathematicians warn of AI threats to profession as industry encroachesIntroducing MAI-Code-1-FlashAI Agent Guidelines for CS336 at StanfordTrust FactoryYou Don't Love systemd Timers EnoughOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

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

Welcome backkk to the podcast!! Today's episode is one I've been stewing on for a while lolI hope you enjoy, and don't forget to share and tag me on insta @emma.currivan xoxo⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠CHAT TO ME ABOUT COACHING ON WHATSAPP⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠JOIN MY PATREON HERE⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ - just 5.99 a month hehe xTo submit a question for a Q&A episode⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠click here⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Don't forget to subscribe to my YouTube channel!⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Catch you in the next one xoChapters00:00 Introduction and Personal Reflections00:25 Emma's Life Updates and Vaping Journey02:11 The Power of 'Fuck You' Energy03:53 Understanding Reactance and Autonomy05:08 Harnessing Anger and Assertiveness07:21 Balancing Masculine and Feminine Energies09:34 Channeling Negative Emotions for Growth12:21 Defining 'Fuck You' Energy15:36 Reactance and Self-Driven Action16:54 The Activating Power of Anger18:14 The Role of Assertiveness in Success21:00 Women, Power, and Assertiveness26:37 Healthy vs. Toxic Aggression29:28 Self-Reflection and Personal Standards33:40 Pain as a Catalyst for Change36:47 Inner Battle: Old Self vs. Future Self41:27 Evolving Goals and Self-Respect43:45 Using 'Fuck You' Energy Wisely44:43 Conclusion and Final Thoughts

Raffi Krikorian, the chief technology officer of Mozilla, has spent the past few months building an argument that the central question in AI isn't open versus closed, but owning versus renting—whether AI becomes something we control or something we lease from a handful of companies. A technologist by background with stops at Twitter, Uber, and the Democratic National Committee, he writes about all of this in his newsletter, Owners Not Renters, and in other outlets, most recently in a New York Times op-ed on what he called the "Mythos moment." Justin Hendrix spoke to him about the idea that generosity is the hidden infrastructure of the internet, how to expand access to powerful AI tools rather than closing it down for security's sake, how to overcome misaligned incentives to build a better information environment, how to counter surveillance, and why those concerned with AI governance should spend more time thinking about the protocol and harness layers.

I've decided that the biggest challenge we have in AI is now keeping track of the new words being created. Words like harness, layer, mesh, vector, orchestrator, tools, surface, memory – they all mean very special things. And engineers and marketing people keep dreaming up new ones (spine? pattern? control plane? MCP? LangChain? headless? MCP? mesh? ontology?). In this podcast I do my best to explain what these words mean, and give you a non-technical understanding of how all this stuff works. If people like this I'll keep you up to date on all these new words. Additional Information (Note that all our research and podcasts are in Galileo) AI Prices Are Going Up, Up, Up – And What This Means For Enterprise AI The Reinvention of Workday: From System of Record to Platform of Agents Could Microsoft Win The War For Enterprise AI? The AI vs. Labor Economy, Why Benefits Are Being Cut, The Role of Legacy Systems The Context Layer (Semantic Layer) In Enterprise AI (And Where Business Rules Go) Jensen Huang's Taipei Speech (filled with this jargon) The Superagent for HR: Galileo Mars Release Chapters (00:00:00) - The Trouble With Words in the AI Era(00:07:28) - Three Words of the Real-World Model (RAG, M(00:10:16) - Hiring with a Neural Network(00:16:27) - What is the Microsoft SQL Server Fabric or Mesh?(00:18:07) - The issue of governance in the HCM(00:19:36) - A Little More About Machine Learning

The biodiesel industry is expected to continue growing globally, supported by government policy, rising fossil fuel prices, technological advancements in feedstock processing and, of course, the work of the Ohio Soybean Council. Learn about how the dynamic of biodiesel is shifting and how Ohio can play a major role in the industry moving forward on this Ohio Ag Net Podcast. Plus, we check in with AgroLiquid to discuss how tissue sampling can help farmers better understand crop health during the growing season and make more informed nutrient management decisions. Then, The 2026 County Fair season is almost here! The Ohio Harness Horsemen's Association will be at 66 fairs for live harness racing action. OHHA executive director Frank Fraas talks about the importance of the sport to rural Ohio and shares details about a huge national event happening in Ohio later this year.

In today's episode, it's the end of May, Rachel's energy is buzzing, and things are happening all around! Rachel talks about the momentum that this month brings to the Scandinavians, and just how that momentum has met her: it's come bearing so many ideas and epiphanies.Rachel has been initiating a million things lately, and she talks about different projects she has going on the farm, how her day looks juggling the store, podcast, garden, gym, and being a mom, and what her human design tells her about the way she works. It all culminated into a realization: she's spent so much time in the garden lately that she hasn't had any time for real work. But what if spending time in the garden is the real work? What if nature can provide everything that we are looking for? This is a positive episode filled with inspiration and the chance to cultivate a life that meets your needs and uplifts you. To learn more about listener data and our privacy practices visit: https://www.audacyinc.com/privacy-policy Learn more about your ad choices. Visit https://podcastchoices.com/adchoices

Edison Hatter is Live from Sweden for the 2026 Elitloppet Final Answers Show. Joined by usual HPP stalwarts Mikee P and Ray Cotolo - the guys run through all the big races from Solvalla on Saturday and Sunday including the Sweden Cup and Harper Hanover Race on Saturday, as well as the 2 heats for the Elite Race on Sunday. Thomas Svensen stops by with his analysis. Unfortunately international expert Kirsten Petersen had to miss for a family emergency. Catch all the coverage all weekend with Edison on the broadcast.

Matt Williamson, former NFL scout and nationally renowned analyst, breaks down the Pittsburgh Steelers like no one else. Don't miss his insight, every Monday-Friday morning. Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

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

Neste episódio, mergulhamos no uso da Inteligência Artificial na logística e nos bastidores do Magalu Entregas. Falamos sobre onde a IA atua na operação, desafios técnicos de algoritmos em ambientes dinâmicos, impactos na experiência de clientes e vendedores parceiros (sellers), aprendizados práticos e as tendências de dados que estão otimizando as entregas de milhões de pessoas todos os dias.Nos siga no Twitter e no Instagram: @luizalabs e @cabecadelabDúvidas, cabeçadas ou sugestões? Mande um e-mail para ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠cabecadelab@luizalabs.com___Participantes:DOUGLAS ZALTRON: https://br.linkedin.com/in/douglaszaltronMARILIA TAVARES: https://www.linkedin.com/in/mariliagtavares/MARCO AURÉLIO SILVA: https://www.linkedin.com/in/marcomaia-ds/LUCAS LIMA: https://www.linkedin.com/in/lucaslc/MILENE VASCONSELOS: https://www.linkedin.com/in/mmvasconcelos/Indicações:Curso "Generative AI leader"Curso Google "Machine Learning"Livro "O mindset da IA: ela pensa, você decide"Outros:Artigo "Harness engineering for coding agent users"Skills GoogleGoogle Cloud

New findings from the Western Development Commission suggest that Clare could benefit significantly from stronger and more coordinated engagement with its global diaspora, alongside other counties in the Western Region. The report, Connected Communities, Global Relationships, highlights opportunities to boost tourism, enterprise, talent attraction and international links, while also noting that much of the current engagement is driven by community groups and volunteers without dedicated resources or long-term support structures. Dr Aisling Moroney, of Western Development Commission/ Lead Research On The Project, joined us to discuss the project. Image (c) Western Development Commission

Edison Hatter prepares for another trip to Sweden and Solvalla racetrack for Elitloppet 2026z Edison and Mikee P provide a preview for the 2026 eliminations with 16 horses competing in 2 races to qualify for the final on Sunday, May 31st. Heat 11 LUKE THE SPOOK Adrian Kolgjini Adrian Kolgjini SE2 DIVA EK Alessandro Gocciadoro Alessandro Gocciadoro IT3 CHARRON Magnus Teien Gundersen Geir Vegard Gundersen NO4 DON FANUCCI ZET Paul Philippe Ploquin Daniel Redén SE5 IDAO DE TILLARD Clemente Duvaldestin Thierry Duvaldestin EN6 DREAM MINE Mats E Djuse Jörgen Westholm SE7 KEEP GOING Mathieu Mottier Mathieu Mottier EN8 BORUPS VICTORY Daniel Wäjersten Daniel Wäjersten Heat 21 GIO CASH Dexter Dunn Daniel Wäjersten EN2 ALLEGIANT Örjan Kihlström Daniel Redén SE3 JABALPUR Gabriele Gelormini Alain Chavatte IT4 FINE MANNERS Magnus A Djuse Mattias Djuse FI5 GO ON BOY Romain Derieux Romain Derieux EN6 A FAIR DAY Oscar Ginman Elisabeth Almheden SE7 INEXESS BLUE Alexandre Abrivard Laurent Claude Abrivard EN8 JOB POST Björn Goop JörgenJoin the guys for Final Answers Friday at 3:30 EST with Edison Live in Sweden with international experts providing coverage of the racing this weekend from Solvalla. Edison provides an intro to Swedish racing a few years ago here:https://inthemoneypodcast.com/first-over-with-edison-hatter-introduction-to-swedish-racing-2023-elitloppet/As a reminder, you can sign up for the FREE Players' Newsletter at https://www.inthemoneypodcast.com/email - This weekly newsletter, sent on Friday, is a hub for horse racing content from the ITM Team and our partners.If you want even more premium handicapping analysis, including exclusive podcasts, detailed written analysis, and show notes from the free podcasts, please check out ITM Plus - https://www.inthemoneypodcast.com/plus

Google dropped like 197 new AI features this week.

Adam helps a client to be more resolute and to have strong boundaries based on inter-dependency rather than the extremes of independence or dependency on others. A useful session if you want more resolution in your life and clearer boundaries.

Send us Fan MailIn this episode, I sit down with Saurabh Gupta, MD — physician, healthcare technology executive, and Founder & CEO of CorMetrix — for a timely conversation about the explosion of healthcare data and how artificial intelligence can help physicians and healthcare organizations make sense of it. With decades of experience spanning clinical medicine, enterprise healthcare technology, data strategy, and innovation, Dr. Gupta brings a unique perspective to the intersection of medicine, AI, and operational intelligence. We explore how healthcare leaders can move beyond data overload to uncover meaningful insights that improve decision-making, efficiency, compliance, and ultimately patient care. We walk through security concerns, "human in the loop" versus fully autonomous models, and lastly, we take a look ahead at the next 3-5 years.Saurabh can be contacted via email at: sg@cormetrix.com or via LinkedIn at: https://www.linkedin.com/in/gupta-md/ and the CorMetrix website is here: https://cormetrix.com/Please Follow or Subscribe to get new episodes delivered to you as soon as they drop! Visit Jill's company, Health e Practices' website: https://healtheps.com/ Subscribe to our newsletter, Health e Connections: https://share.hsforms.com/1FMup6xLPSpeA8hB77caYQwd32sx?hsCtaAttrib=171926995377 Want more formal learning? Check out Jill's newly released course: Physician's Edge: Mastering Business & Finance in Your Medical Practice. 32.5 hours of online, on-demand CME-accredited training tailored just for busy physicians. Promo pricing available now: https://education.healtheps.com/offers/Ry3zfLYp/checkout?coupon_code=PHYSEDGE3000 Purchase your copy of Jill's book here: Physician Heal Thy Financial Self Join our Medical Money Matters Facebook Group here: https://www.facebook.com/groups/3834886643404507/ Original Musical Score by: Craig Addy at https://www.underthepiano.ca/ Visit Craig's website to book your Once in a Lifetime music experience Podcast coaching and development by: Jennifer Furlong, CEO, Communication Twenty-Four Seven https://www.communicationtwentyfourseven.com/    

如果你喜歡我的內容，歡迎加入會員支持我，讓我把內容做得更深、做得更好，一起把這個頻道做成我們都想看到的樣子！

The squad is complete again, and Sam arrives with a NeuroPod, cold plunge updates, red light therapy, Oura stats, and enough supplements to start a wellness startup. Then into the week's biggest tech stories: Google's new AI device and whether it's the Chromebook of the AI era or another doomed health-tech experiment, Meta's keystroke logging controversy, Microsoft's increasingly awkward OpenAI bet, why OpenAI and Anthropic are now sending engineers directly into enterprises to drive adoption, and what tools like OpenClaw, Py, and Codex actually do. Plus, Anthropic's eye-watering latest valuation, the clean girl aesthetic discourse, Brian Johnson chaos, and Sam personally buying Jackson Hole ski passes like it's 1997Chapters:00:46 Sam's NeuroPod, Oura Results & Biohacking Spiral03:33 Sam vs. Brian Johnson + The Female Biohacker Opportunity05:09 Oura Ring vs. Whoop + Google's Wearables Ambition07:00 Google's AI-First “Book” Laptop + DeepMind's Health Push10:30 Why Local AI Changes Everything (Speed, Cost & Compute)15:00 Where Is the OpenAI Consumer Device?16:00 Voice AI, Recording & the Future of Human-Computer Input20:30 Sam Built His Own Voice-to-AI App22:31 Meta's Keystroke Logging: Spy Games or Honeypot?24:00 Fake AI Jobs + Sam's “Fin Analytics” Prediction27:02 OpenAI & Anthropic's Enterprise Conversion Strategy29:31 The AI Backlash Is Real (Including UCF's Commencement Revolt)31:30 Microsoft's $100B OpenAI Problem39:31 Anthropic's Massive Raise + SF Real Estate Absurdity41:30 OpenClaw, Py & Codex: What Is a Harness?We're also on ↓X: https://twitter.com/moreorlesspodInstagram: https://instagram.com/moreorlessYoutube: https://youtu.be/-O3zyxR-wS0Connect with us here:1) Sam Lessin: https://x.com/lessin2) Dave Morin: https://x.com/davemorin3) Jessica Lessin: https://x.com/Jessicalessin4) Brit Morin: https://x.com/brit

In this episode, Michele Lamoureux sits down with Fredric Marshall, a leading expert in change management, human behavior, and helping people navigate uncertainty with confidence. Over the course of his career, Fred has worked with organizations like Apple, Pfizer, and Genentech, helping teams adapt, grow, and lead through change. But this conversation goes beyond corporate performance. Fred shares why the tools for resilience, adaptability, and growth are not reserved for high achievers or executives—they're essential skills for anyone facing change, uncertainty, overwhelm, or anxiety about the future. Drawing from decades of research and experience training more than 130,000 people across fourteen countries, Fred explains how people can move from fear and overwhelm to clarity, agency, and momentum in a rapidly changing world. We also dive into his book, THRIVE: The Antidote to Future Shock, and explore practical ways people can stay grounded and hopeful during times of disruption.   RESOURCES MENTIONED Join The Newsletter Subscribe on YouTube Follow on APPLE PODCASTS Follow on SPOTIFY PODCASTS Book: Thrive: The Antidote to Future Shock Website: https://thrivefutureyou.com/     *The Good Life with Michele Lamoureux podcast and content provided by Michele Lamoureux is for educational and entertainment purposes only. It does NOT constitute medical, mental health, professional, personal, or any kind of advice or serve as a substitute for such advice. The use of information on this podcast or materials linked from this podcast or website is at the user's own risk. Always consult a qualified healthcare or trusted provider for any decisions regarding your health and wellbeing. This episode may contain affiliate links.

Alan Gregerman shares why the right kind of ignorance is the secret to driving innovation.— YOU'LL LEARN — 1) How to challenge assumptions that are keeping you stuck2) Why not knowing can often lead to better solutions3) Six ways to unlock ignorance as a superpowerSubscribe or visit AwesomeAtYourJob.com/ep1151 for clickable versions of the links below. — ABOUT ALAN — Alan Gregerman is an internationally renowned authority on business strategy, innovation, and hidden potential who has been called “one of the most original thinkers in business today” and “the Robin Williams of business consulting.”As the president and chief innovation officer of Washington, D.C.-based consultancy VENTURE WORKS, a bestselling author, and a sought-after keynote speaker, he focuses on helping companies and organizations unlock the genius in all of their people in order to deliver the most compelling value to their customers. He is also the founder of Passion for Learning, an award-winning nonprofit that teaches girls technology skills as a key to life and career success.His three previous books—The Necessity of Strangers, Surrounded by Geniuses, and Lessons from the Sandbox—challenge conventional thinking about people, the world around us, what it means to be remarkable, and where brilliant ideas actually come from. He's also the author of the critically acclaimed blog Surrounded by Geniuses.• Book: The Wisdom of Ignorance: Why Not Knowing Can Be the Key to Innovation in an Uncertain World• LinkedIn: Alan Gregerman• Website: AlanGregerman.com— RESOURCES MENTIONED IN THE SHOW — • Book: Around the World in Eighty Days (Macmillan Collector's Library) by Jules Verne• Book: Don Quixote by Miguel De Cervantes• TED Talk: Why I train grandmothers to treat depression | Dixon Chibanda• Book: Twenty Thousand Leagues Under the Sea by Jules Verne— THANK YOU SPONSORS! — • Scribe. Book a personalized enterprise demo with scribe.how/awesome• Narwhal. Treat your home to spotless, fresh floors with us.narwhal.com/pete.• Monarch.com. Get 50% off your first year on with the code AWESOME.• Shopify. Sign up for your $1/month trial at Shopify.com/awesomepodSee Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Adam helps a client manage their anger so it works for them rather than against them, to harness the power rather than have the power influence them negatively.