Podcasts about Spec

Jeroen Gordijn and Jeroen Dee: two frontrunners who stopped writing code months ago and say software development is already solved. Typing code is no longer necessary, but what matters more now? If you're an engineer that loves coding, you're in a tougher spot than you might realize.In this video, we cover:- Why writing code is "solved" but engineering isn't- Spec-driven development and how to get it started in your team- The "Dark Factory" and why code review is a huge bottleneck- Model vs harness: what matters more, and why- The unhealthy side of agentic codingIf you write software for a living and you're trying to work out what your job becomes next, start here.Timestamps:00:00:00 - Coding Is No Longer Necessary00:00:43 - Why "Software Development Is Already Solved"00:02:57 - Should You Even Read the AI's Code?00:05:05 - What Is a "Dark Factory"?00:06:52 - If You Can Regenerate It, Why Care About Quality?00:07:49 - Spec-Driven Development Explained00:11:32 - Adopting Specs Without Starting From Scratch00:13:23 - Model vs Harness: What Matters More?00:17:27 - Is Your Harness the New IDE?00:20:18 - Why Everyone Plateaus (and the Innovation Token)00:22:50 - Where to Actually Spend Your Time00:24:57 - The Unhealthy Side: "It's Free Cocaine"00:28:00 - Is This Sustainable, or Just Subsidized?00:30:33 - Should You Run Models Locally?00:34:31 - Looping, Scale, and Automating Review00:37:53 - What's Left for Engineers to Do?00:39:13 - If You Love Writing Code, You're in Trouble00:41:18 - Why Teams Are Getting Smaller00:43:03 - What an "Agentic Company" Looks Like00:46:25 - How to Start: Find Your Spark00:50:13 - The One Habit That Keeps You AheadGuests: Jeroen Gordijn: https://www.linkedin.com/in/jeroengordijnJeroen Dee: https://www.linkedin.com/in/jeroendee#AgenticEngineering #SoftwareEngineering #Agents

Building Your Dream Home: What Buyers Need to Know About New Construction There is something special about being the very first person to live in a home. Fresh paint. Brand-new appliances. Modern layouts. Energy-efficient systems. And perhaps most importantly, the opportunity to create a space that reflects your lifestyle and vision from day one. On a recent episode of Talk Real Estate Roundtable, Melissa Wallace and Boston Connect Real Estate agent Tracy Grady discussed everything buyers should know before purchasing a newly built home. From understanding the differences between custom homes and spec homes to navigating the building process and selecting finishes, they shared valuable insights for anyone considering new construction. Why Buyers Love New Construction One of the biggest draws of new construction is simple: everything is new. For many buyers, the appeal lies in being able to choose finishes, personalize features, and move into a home that has never been lived in before. Rather than spending years updating an existing property, buyers can often start with a clean slate and create a home that fits their needs from the beginning. Whether it's selecting cabinetry, countertops, flooring, paint colors, or designing a floor plan that works for your family, new construction offers a level of personalization that existing homes often cannot match. Understanding the Different Types of New Construction Not all new construction homes are created the same. Buyers should understand the different options available before beginning their search. Custom Homes A custom home is built specifically for the buyer. Typically, buyers select the lot, work with builders and architects, review plans, and make decisions about nearly every aspect of the home's design. From room layouts to finishes and upgrades, the customization possibilities are extensive. Custom homes offer the most flexibility but often come with longer timelines and more decision-making throughout the process. Semi-Custom Homes Semi-custom homes provide a balance between personalization and convenience. Builders often begin with a proven floor plan and allow buyers to modify certain elements, such as finishes, layout adjustments, and selected structural options. This approach allows buyers to personalize the home without starting entirely from scratch. Spec Homes A spec home is built before a buyer is identified. The builder selects the floor plan, finishes, and design elements based on market demand and current trends. Once construction is complete, the home is listed for sale. Spec homes are ideal for buyers who may not have the vision to imagine a home from plans alone and prefer seeing a finished product before making a decision. Model Homes Model homes showcase a builder's craftsmanship and available upgrades. These homes often include premium finishes, upgraded fixtures, custom millwork, enhanced kitchens, specialty tile work, and other features that help buyers visualize possibilities for their own home. When touring a model home, it's important to ask what features are included in the base price and which items represent upgrades. While model homes can provide great inspiration, not every feature may be included in the advertised starting price. The Importance of Buyer Engagement During Construction One of the most important takeaways from the discussion was the need for buyers to stay actively involved throughout the building process. Regular site visits, attending builder meetings, reviewing plans, and confirming selections help ensure that expectations remain aligned throughout construction. Communication matters. Builders, agents, and buyers all benefit when decisions are documented and confirmed throughout the process. Even small misunderstandings can become costly if they are discovered after construction has progressed. Staying engaged allows buyers to address concerns early and helps keep projects moving smoothly. When Is the Best Time to Buy in a New Development? Many buyers wonder whether they should purchase at the beginning or near the end of a development. While every situation is different, there are several advantages to purchasing early: More Lot Choices Early buyers typically have access to the most desirable lots and locations within the development. Greater Customization Opportunities When construction has not yet begun, buyers often have more flexibility to customize floor plans, finishes, and upgrades. Potential Equity Growth As developments progress, construction costs and pricing often increase. Buyers who purchase early may benefit from appreciation as additional homes are completed and sold. Of course, buying early also means living through some ongoing construction activity while the neighborhood is being completed. For many buyers, however, the long-term benefits outweigh the temporary inconveniences. Building More Than a Home, Building a Community One unexpected benefit of new construction developments is the sense of community that often develops before homeowners even move in. Future neighbors frequently meet while visiting construction sites, attending builder meetings, and watching their homes take shape. By the time move-in day arrives, many residents have already formed relationships and friendships with the people who will become their neighbors. The Advantages of New Construction Beyond personalization and modern design, new construction offers several practical benefits: Brand-new systems and appliances Energy-efficient windows, insulation, and HVAC systems Lower maintenance costs in the early years of ownership Builder warranties on workmanship and structural components Modern floor plans designed for today's lifestyles Updated building codes and construction standards Many builders also provide warranty coverage that gives buyers added peace of mind during their first years of homeownership. Is New Construction Right for You? New construction isn't simply about buying a house it's about creating a home that fits your lifestyle, goals, and future plans. Whether you're a growing family looking for space, a homeowner looking to right-size into a home designed for your next chapter, or someone who simply wants the opportunity to personalize every detail, new construction offers possibilities that existing homes often cannot. The key is understanding your options, asking the right questions, and working with experienced professionals who can help guide you through the process. At Boston Connect Real Estate, we've helped buyers navigate every stage of new construction—from selecting lots and floor plans to final walkthroughs and closing day. If you're considering building your dream home, our team is here to help you make informed decisions every step of the way. Because every move should be a moving experience. Watch our live video on Youtube!

Fredrik snackar hastighet och kognitiv skuld med Benny Andrén och Jakob Wolman. Allt handlar inte om hastighet. Eller åtminstone inte om hastighet i de steg som språkmodeller kan göra snabbare. Vi diskuterar nya typer av teknisk skuld som lätt ökar extremt snabbt med språkmodeller, och nyttan med friktion. Friktion har sina stora poänger. Allt ska inte förenklas bort. Och vad gör vi här och nu? Mitt i alla förändringar? Från prisändringar till vad man tillåter och håller koll på det. Det går att göra väldigt många saker väldigt snabbt, men man måste ju hålla koll över tid också. Vi är fortfarande i hobbyfasen. Vad är internet för oss, som man undrade på nittiotalet. Likformighet - alla pratar om AI på ungefär samma sätt, alla känner att de måste springa åt samma håll lika snabbt. AI: inte ett verktyg för innovation? Som eftersnack: lite uppvärmda grafikkort och oväntat bra mikrofoner i hörsnäckor. Ett stort tack till Cloudnet som sponsrar vår VPS! Har du kommentarer, frågor eller tips? Vi är @kodsnack, @thieta, @krig, och @bjoreman på Mastodon, har en sida på Facebook och epostas på info@kodsnack.se om du vill skriva längre. Vi läser allt som skickas. Gillar du Kodsnack får du hemskt gärna recensera oss i iTunes! Du kan också stödja podden genom att ge oss en kaffe (eller två!) på Ko-fi, eller handla något i vår butik. Länkar Benny Alla avsnitt med Benny Jakob Aller media Storytel Click Datastudion Datastudion 46, med Jakob Datastudion 49, med Martin Mazur Vattenfall Agila manifestet Lean Theory of constraints Spec-driven development Margaret-Anne Storey - legendarisk inom developer experience SPACE framework From technical debt to cognitive and intent debt - Margaret-Annes artikel om tre typer av teknisk skuld Your brain on Chatgpt - artikel som började diskutera kognitiv skuld Monkey island Civilization 1 Konsonans och dissonans Stöd oss på Ko-fi! Brädgårdschiffer ARC-AGI Øredev Bennys och Jakobs session på Øredev 2026 Odysseus - Pewdiepies nya stora språkmodell Titlar Vi måste spela in oftare Jag måste uppdatera min nuvarande position Det handlar aldrig om hastighet Låtsasutvecklare Nästa tillfälle för audiens Tre typer av teknisk skuld Den klassiska tekniska skulden Kognitiv teknisk skuld Kognitiv skuld Koll på specarna En ny raketmotor Fortfarande samma problem Sov på saken Det finns ett värde i friktion Uppmärksamhetshållare Livssnack Humor som gick mig helt förbi Friktion för friktionens skull Ett här och nu Vi ska ha en app! Tab-based development En lång mening på danska

Red light therapy is now at Target. It's on Amazon by the thousands. And with that explosion comes a mountain of marketing claims, spec sheet arguments, and consumer confusion that has Freddie and Scott Kennedy — founder of Light Path LED and one of the most science-grounded voices in photobiomodulation — more motivated than ever to cut through the noise. In this fifth conversation across seven years together, they break down exactly what happens at the cellular level when red and near-infrared light hits your body: how cytochrome C oxidase absorbs photons, why that turbine in your mitochondria spins faster, how nitric oxide release drives vasodilation and blood flow, and why the gap between 700 and 800 nanometers is essentially a dead zone. They also get real about power, irradiance, pulsing frequencies, and why the best panel in the world won't save a business model built on charging $100 a session for red light alone. The second half of this episode is a full product walkthrough of what Scott has been building — including the new Titan, a six-foot full-body panel with an electric adjustable stand designed to deliver what $60,000 red light beds do at a fraction of the cost, and the TLC dork cap — three years in development, covering the full head, jaw, cervical lymph nodes, and occipital region with red, near-infrared, and blue light at 10 and 40Hz pulsing. Freddie and Scott also explore the torch, intranasal red light delivery, dental and gum applications, stacking red light with peptides for injection site activation, and the honest conversation about what a sustainable red light business model actually looks like in 2026. Use code BEAUTIFULLYBROKEN at lightpathled.com for a discount.   Episode Highlights   [00:00] – Red light therapy goes mainstream and why consumer confusion is exploding [02:10] – Scott's dental laser background and how he discovered photobiomodulation [04:32] – Why red light supports the body instead of directly “treating” conditions [06:22] – How light increases ATP, blood flow, oxygenation, and downstream cellular benefits [10:00] – The difference between red light and near infrared light [12:11] – What happens at the cellular level with mitochondria, cytochrome C oxidase, and nitric oxide [18:45] – Why irradiance and power claims can be misleading for consumers [24:32] – Therapeutic dose, joules, timing, and why more is not always better [30:53] – The problem with too many wavelengths and marketing-based panel design [36:05] – Lightpath LED's wavelength choices, pulsing features, and near infrared focus [44:11] – The Titan panel and why Scott designed a simpler full-body red light option [45:51] – The Dork Cap, blue blockers, torch attachments, and practical red light tools for daily use   Upgrade Your Health   LightPathLED: https://lightpathled.pxf.io/c/3438432/2059835/25794 Code: beautifullybroken   MaxGen Labs: https://maxgenlabs.com/BEAUTIFULLYBROKEN Code: beautifullybroken   The Biological Blueprint Course: https://www.beautifullybroken.world/biological-blueprint Earn 200 in BitCoin + Change your health   BEAM Minerals: http://beamminerals.com/beautifullybroken Code: BEAUTIFULLYBROKEN   Silver Biotics Wound Healing Gel: https://bit.ly/3JnxyDD 30% off with Code: BEAUTIFULLYBROKEN   StemRegen: https://www.stemregen.co/products/stemregen?_ef_transaction_id=&oid=1&affid=52 Code: beautifullybroken CONNECT WITH FREDDIEWork with Me: https://www.beautifullybroken.world/biological-blueprintWebsite and Store: (http://www.beautifullybroken.world) Instagram: (https://www.instagram.com/freddie.kimmelYouTube: https://www.youtube.com/@beautifullybrokenworld Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

In this week's Overdrive Radio podcast, dig into Overdrive Senior Editor Matt Cole's talk with Colorado headquartered 5S Express owner-operator Ron Schreiner, leased to Pejsa Family Transportation pulling the company's tankers out of the oilfield on mostly short dedicated runs. Schreiner's got many decades of experience that started with a 1950s family business he got involved in growing up in the 1980s and, after his time in the Marine Corps, went hauling leased to in a W900A with a special family history itself. Cole first told Schreiner's story attendant to the owner getting the nod as May Trucker of the Month, putting Schreiner in the running for the 2026 Trucker of the Year award: https://overdriveonline.com/15826121 You can nominate an owner-operator you admire, or enter your own business, for consideration via this link: https://overdriveonline.com/toptrucker Owner-operator Schreiner's experience in his current business reboot, following his father's early-century passing, sees him following his own best piece of advice for all manner of aspiring or new-to-the-business owners. Namely, find the right used truck for the job you'll doing. More about that in the podcast this week, and perhaps more importantly, he said, make sure your family fully supports you in your drive to success. "You really have to have your family on board," he said. "It's important to have your family be able to back you ... to understand your time will be dedicated to that truck, to getting that business running." Schreiner's in gear in that regard, no doubt, with his wife, Kay, and three children helping make a challenging overnight oilfield schedule work efficiently as possible -- and he's home most days in the afternoons. He's hauling in a 2007 Pete 379 in tip-top shape after a some recent front end repairs. As told in Cole's feature and in the podcast in his own words, Schreiner had an unfortunate wee-hours run-in with a cow on the way to load. Though the fleet he's leased to was able to offer use of an idle truck to continue his daily runs, Schreiner was fast to move with his go-to maintenance partner on the repair. As he well knows, as is the case for any one-truck operation, "the grocery getter gets attention first," he said. That's right, "grocery getter," his phrase for the 379 that powers the biz, and the family behind it. No, he's not pulling a reefer. "She's the one that puts a roof over our head," he said of the truck, "and she comes first." 547c1b50-6809-11f1-a0eb-5be553a488df

Hans Frees of Outdoor Escapes has been in business 25 years, filed Chapter 7 bankruptcy, lost money on a spec home during the 2008 crash, and came out the other side with better relationships, a better location, and a much healthier respect for staying in his lane. He and Mark swap war stories about building spec homes they probably shouldn't have, losing sleep over unpaid subcontractors, and why the small-town bank that bet on them at rock bottom is still their bank today. It's 32 minutes of hard-won wisdom from someone who learned most of it the expensive way. Support the show - https://www.curiousbuilderpodcast.com/shop See our upcoming live events - https://www.curiousbuilderpodcast.com/events The host of the Curious Builder Podcast is Mark D. Williams, the founder of Mark D. Williams Custom Homes Inc. They are an award-winning Twin Cities-based home builder, creating quality custom homes and remodels — one-of-a-kind dream homes of all styles and scopes. Whether you're looking to reimagine your current space or start fresh with a new construction, we build homes that reflect how you live your everyday life. Sponsors for the Episode:  Pella Website: https://www.pella.com/ppc/professionals/why-wood/  Where to find the Guest:  Website: https://www.outdoorexcapes.com/ Instagram: http://www.instagram.com/outdoorexcapes Facebook: https://www.facebook.com/outdoorexcapes/ Where to find the Host:  Website - https://www.mdwilliamshomes.com/  Podcast Website - https://www.curiousbuilderpodcast.com Instagram - https://www.instagram.com/markdwilliams_customhomes/  Facebook - https://www.facebook.com/MarkDWilliamsCustomHomesInc/  LinkedIn - https://www.linkedin.com/in/mark-williams-968a3420/  Houzz - https://www.houzz.com/pro/markdwilliamscustomhomes/mark-d-williams-custom-homes-inc

We sat their listening slack-jawed, and it just kept...getting...better.

Join the #1 real estate community for agents and investors: https://www.skool.com/offmarketmethod/about?ref=791b3644f63045c9a6d3d8634e57c1f1Want to SCALE your real estate business to $100k/month? Go here: https://easybuttonrealestate.com/Join Easy Button Real Estate LIVE in San Diego: https://easybuttonrealestate.com/liveSummary:We're back after a little hiatus, and we're not holding back. In this episode, Tucker and I catch up on what's been going on in our worlds: Tucker's pushing through his $5-6M spec build in Naples, I recently welcomed my first kid (and survived the first two weeks), and we both weigh in on where this market is actually headed right now: interest rates, the 10-year bond, geopolitical tension, and all the weird signals that make it nearly impossible to read the tea leaves right now.But the real conversation? We get into the Brandon Turner situation, one of the biggest real estate syndication stories circulating online right now. Whether you've been following it or this is your first time hearing about it, we break down the real lessons behind it: what happens when you skip too many rungs on the investment ladder, how social media celebrity can fast-track your way into deals you're not ready for, and why the people who truly build lasting wealth in this game rarely, if ever, make the news. If you're wholesaling, flipping, or thinking about raising capital, this one's for you.Connect with Cole Ruud-JohnsonInstagram: https://www.instagram.com/coleruudjohnsonTwitter: https://twitter.com/coleruudjohnsonLinkedIn: https://www.linkedin.com/in/coleruudjohnsonTikTok: https://www.tiktok.com/@coleruudjohnson

Gościnnie: Michał „Elessar” Mańka (YT: Find Your Next Game) + Michał Pisarski (YT: Michał Pisarski Tech) + Adam „Adzior” Saczko (https://twitch.tv/adzior)#Wesprzyj nas, będziemy turbo wdzięczni + co tydzień dostaniesz pół godziny naszej gadaniny ekstra:https://www.youtube.com/channel/UCLLO-H4NQXNa_DhUv-rqN9g/joinStreamujemy na:https://twitch.tv/cdactionDiscord:https://discord.com/invite/TwFpFKumNyWszystkie inne linki, których szukasz:https://www.goladupa.comTo my:Krzysztof „Bastian” FreudenbergerDawid „spikain” BojarskiMontaż: Krzysztof „Bastian” Freudenberger

Gościnnie: Krzysztof „NRGeek” Micielski (https://youtube.com/NRGeek00)#Wesprzyj nas, będziemy turbo wdzięczni + co tydzień dostaniesz pół godziny naszej gadaniny ekstra:https://www.youtube.com/channel/UCLLO-H4NQXNa_DhUv-rqN9g/joinStreamujemy na:https://twitch.tv/cdactionDiscord:https://discord.com/invite/TwFpFKumNyWszystkie inne linki, których szukasz:https://www.goladupa.comTo my:Krzysztof „Bastian” FreudenbergerDawid „spikain” BojarskiMontaż: Krzysztof „Bastian” Freudenberger

Podcasting 2.0 June 5th 2026 Episode 262 - "Podcleanse" Dave and Adam are joined by John Spurlock and throw a big idea into the boardroom: The Podcast Data Collective Shownotes ----------------------------------------------------------------------------------------------------------------------------------------- John Spurlock - Guest The man behind op3.dev and Livewire.io - From the Great State of New Jersey! ----------------------------------------------------------------------------------------------------------------------------------------- 01 - THE IMPRESSION HEIST — AMP TASK FORCE RATIFIES 4 EXPOSURE DEFINITIONS, NO DISSENTING VOTES Podnews press release Jun 4: AMP Task Force Introduces Cross-Platform Alternative to the Podcast "Download" — "unified impression guidance for audio and video, advancing impression-based measurement as the medium's primary transaction currency." Four exposure definitions ratified. JS Jun 4 quote: "the AMP Task Force ratified a new framework with four exposure definitions, with no dissenting votes." Podcast Play: 30 seconds of content played, audio or video, once per user per session. Podcast Audience: The number of unique users who had a Podcast Play. Ad Impression: A commercial begins playing for the user. Ad Audience: The number of users exposed to an Ad Impression. They wanted to 'hasten the demand' Backstory: AMP first emerged May 29 (Podnews) — same day PC20-261 aired — "to confront podcasting's measurement dilemma." @dave reaction Jun 4 16:12: "RE: [Podnews AMP story] More secretive, back room podcast 'industry' nonsense." PNWR Jun 5 confirms the cabal-composition critique — James and Sam open the show debating AMP. James: "they also want to define what an impression is" + "we don't have a definition of podcast." Sam: "I don't think podcasting is [defined], we can measure consumption." PNWR catches the gaps [0:09:00-0:09:30]: "Spotify yes, Acast no, Art19 missing… Apple is already doing that. Apple is already being cut [out]." Same observation @dave made — who's in the room and who isn't. @js replies @dave on AMP Jun 4: "@dave Dave there were no dissenting votes" — Mastodon-thread confirmation that JS + Dave are on the same page about the consensus-by-cabal red flag. Discussion: V4V counter-thesis — No Agenda is value-for-value (no impressions, no exposures). Open standards vs industry cabals. PNWR is independent-podcaster-aligned; AMP is platform-aligned. Podnews AMP Jun 4 press release Podnews AMP origin May 29 @dave Jun 4 reaction post JS Jun 4 quote post PNWR this week (Pod News Weekly Review) ----------------------------------------------------------------------------------------------------------------------------------------- 02 - THE OPEN COUNTERPART — PODCAST INDEX ISSUE #775 (PNWR + @DAVE BOTH ON IT) ----------------------------------------------------------------------------------------------------------------------------------------- 03 - THE WHY BEHIND IMPRESSIONS — "THE FIRST FOUR AND A HALF MINUTES" ----------------------------------------------------------------------------------------------------------------------------------------- 04 - THE PODCASTING 2.0 DATA COLLECTIVE — THE OPEN ANSWER TO AMP The Podcasting 2.0 Data Collective — the open, V4V-aligned answer to the AMP cabal. Not a consortium with ratified definitions and trade-press releases. A collective of open tools and honest sentinels: OP3 for analytics, Podverse + newpodcasts.net for corpus data, Podcast Index for the namespace, Issue #775 for client identification done right. Matthew 5:6 (KJV): "Blessed are they which do hunger and thirst after righteousness: for they shall be filled." The verse that frames the work. Open data, transparent measurement, value-for-value — righteousness in podcast governance. Those who hunger for it are the ones who'll be filled. The AMP cabal trades righteousness for an ad-tech seat at the table; the Data Collective just keeps the lights on. THE CHARTER — Adam's working document, June 5 2026 We hold more power than we give ourselves credit for. Definition of a Podcast: Syndicated delivery of media files with precise consumption data for all stakeholders. What we brought in (the Podcasting 2.0 namespace contributions): Transcripts Chapters Funding (V4V) Person Location …etc. Statistical relevance: Advertising is based on percentages. Collectively we have about 10% of all apps — statistically enough to be relevant. Godcaster app tracing proves we can measure important metrics. Data to aggregate and display: Follows Plays per episode Completion rate by time Strategy: Become the authoritative source by publishing open stats Monetize We will not be loved initially by the industry, because we will have the truth. Advertisers will love us though, as will Podcasters. Monetization: Data subscriptions Resellers (DJL) Ad Networks Podcasters themselves (consideration) Podcast Index has built the trust needed to house this data. We already have a data exchange relationship with the apps. op3.dev is critical in this equation to offset the old system for correlation. OP3 full podcast support landed this week [PNWR 1:53:00-1:54:30] — OP3.dev now has full episode-level + show-level analytics support for podcasts. Spec work also moving on private feeds (insecure feeds spec). Direct relevance to V4V infrastructure. @dave → @james Jun 5 11:50: "Do you have the daily lists that show up on newpodcasts.net available anywhere as a download? I'd love the full, historical list of feed urls that have appeared there if possible." Open-data request — corpus curation theme. @dave → @mitch May 30: "Would you be able to send me a flat list of all the feed urls in Podverse which have more than X number of subscribers/followers? Let's say more than 5?" Podverse data request — corpus quality. Anchor FM RSS restoration request — Fri 11:01 email to NA inbox (Lusso Lets). Listener can't retrieve feed data from Podcast Index. Adjacent infra beat — the unsung user-facing pain of corpus indexing. Discussion: corpus curation as a steady-state job (Dave's sentinel work) vs measurement standards (the AMP cabal) — which one keeps the ecosystem honest? The Data Collective doesn't ratify, it just shows up to maintain. Hunger and thirst. They shall be filled. OP3.dev — open podcast analytics ----------------------------------------------------------------------------------------------------------------------------------------- 05 - CAPTIVATE LAUNCHES DAX US — THE IMPRESSION ECONOMY IRL ----------------------------------------------------------------------------------------------------------------------------------------- 06 - BBC GOES ALL-IN ON CROSSED WIRES YEAR 3 — IPLAYER DEAL + "EDINBURGH OF PODCASTING" ----------------------------------------------------------------------------------------------------------------------------------------- 07 - STREAMING CONSOLIDATION — YOUTUBE MUSIC + TUBI + NETFLIX ALL WANT "PODCAST" ----------------------------------------------------------------------------------------------------------------------------------------- 08 - SUPPLY CHAIN SECURITY — VS CODE DELAYS, PHP FOUNDATION, SLSA LEVEL 3 IS NOT ENOUGH ----------------------------------------------------------------------------------------------------------------------------------------- 09 - AI BUBBLE PC20-FLAVOR — TOTO CHUCKS, MOTHER COMPUTERS, "NO 'I', ONLY MATH" ----------------------------------------------------------------------------------------------------------------------------------------- 10 - QUIPS / TRANSITIONS ----------------------------------------------------------------------------------------------------------------------------------------- Last Modified 06/05/2026 14:38:09 by Freedom Controller

Podcasting 2.0 June 5th 2026 Episode 262 - "Podcleanse" Dave and Adam are joined by John Spurlock and throw a big idea into the boardroom: The Podcast Data Collective Shownotes ----------------------------------------------------------------------------------------------------------------------------------------- John Spurlock - Guest The man behind op3.dev and Livewire.io - From the Great State of New Jersey! ----------------------------------------------------------------------------------------------------------------------------------------- 01 - THE IMPRESSION HEIST — AMP TASK FORCE RATIFIES 4 EXPOSURE DEFINITIONS, NO DISSENTING VOTES Podnews press release Jun 4: AMP Task Force Introduces Cross-Platform Alternative to the Podcast "Download" — "unified impression guidance for audio and video, advancing impression-based measurement as the medium's primary transaction currency." Four exposure definitions ratified. JS Jun 4 quote: "the AMP Task Force ratified a new framework with four exposure definitions, with no dissenting votes." Podcast Play: 30 seconds of content played, audio or video, once per user per session. Podcast Audience: The number of unique users who had a Podcast Play. Ad Impression: A commercial begins playing for the user. Ad Audience: The number of users exposed to an Ad Impression. They wanted to 'hasten the demand' Backstory: AMP first emerged May 29 (Podnews) — same day PC20-261 aired — "to confront podcasting's measurement dilemma." @dave reaction Jun 4 16:12: "RE: [Podnews AMP story] More secretive, back room podcast 'industry' nonsense." PNWR Jun 5 confirms the cabal-composition critique — James and Sam open the show debating AMP. James: "they also want to define what an impression is" + "we don't have a definition of podcast." Sam: "I don't think podcasting is [defined], we can measure consumption." PNWR catches the gaps [0:09:00-0:09:30]: "Spotify yes, Acast no, Art19 missing… Apple is already doing that. Apple is already being cut [out]." Same observation @dave made — who's in the room and who isn't. @js replies @dave on AMP Jun 4: "@dave Dave there were no dissenting votes" — Mastodon-thread confirmation that JS + Dave are on the same page about the consensus-by-cabal red flag. Discussion: V4V counter-thesis — No Agenda is value-for-value (no impressions, no exposures). Open standards vs industry cabals. PNWR is independent-podcaster-aligned; AMP is platform-aligned. Podnews AMP Jun 4 press release Podnews AMP origin May 29 @dave Jun 4 reaction post JS Jun 4 quote post PNWR this week (Pod News Weekly Review) ----------------------------------------------------------------------------------------------------------------------------------------- 02 - THE OPEN COUNTERPART — PODCAST INDEX ISSUE #775 (PNWR + @DAVE BOTH ON IT) ----------------------------------------------------------------------------------------------------------------------------------------- 03 - THE WHY BEHIND IMPRESSIONS — "THE FIRST FOUR AND A HALF MINUTES" ----------------------------------------------------------------------------------------------------------------------------------------- 04 - THE PODCASTING 2.0 DATA COLLECTIVE — THE OPEN ANSWER TO AMP The Podcasting 2.0 Data Collective — the open, V4V-aligned answer to the AMP cabal. Not a consortium with ratified definitions and trade-press releases. A collective of open tools and honest sentinels: OP3 for analytics, Podverse + newpodcasts.net for corpus data, Podcast Index for the namespace, Issue #775 for client identification done right. Matthew 5:6 (KJV): "Blessed are they which do hunger and thirst after righteousness: for they shall be filled." The verse that frames the work. Open data, transparent measurement, value-for-value — righteousness in podcast governance. Those who hunger for it are the ones who'll be filled. The AMP cabal trades righteousness for an ad-tech seat at the table; the Data Collective just keeps the lights on. THE CHARTER — Adam's working document, June 5 2026 We hold more power than we give ourselves credit for. Definition of a Podcast: Syndicated delivery of media files with precise consumption data for all stakeholders. What we brought in (the Podcasting 2.0 namespace contributions): Transcripts Chapters Funding (V4V) Person Location …etc. Statistical relevance: Advertising is based on percentages. Collectively we have about 10% of all apps — statistically enough to be relevant. Godcaster app tracing proves we can measure important metrics. Data to aggregate and display: Follows Plays per episode Completion rate by time Strategy: Become the authoritative source by publishing open stats Monetize We will not be loved initially by the industry, because we will have the truth. Advertisers will love us though, as will Podcasters. Monetization: Data subscriptions Resellers (DJL) Ad Networks Podcasters themselves (consideration) Podcast Index has built the trust needed to house this data. We already have a data exchange relationship with the apps. op3.dev is critical in this equation to offset the old system for correlation. OP3 full podcast support landed this week [PNWR 1:53:00-1:54:30] — OP3.dev now has full episode-level + show-level analytics support for podcasts. Spec work also moving on private feeds (insecure feeds spec). Direct relevance to V4V infrastructure. @dave → @james Jun 5 11:50: "Do you have the daily lists that show up on newpodcasts.net available anywhere as a download? I'd love the full, historical list of feed urls that have appeared there if possible." Open-data request — corpus curation theme. @dave → @mitch May 30: "Would you be able to send me a flat list of all the feed urls in Podverse which have more than X number of subscribers/followers? Let's say more than 5?" Podverse data request — corpus quality. Anchor FM RSS restoration request — Fri 11:01 email to NA inbox (Lusso Lets). Listener can't retrieve feed data from Podcast Index. Adjacent infra beat — the unsung user-facing pain of corpus indexing. Discussion: corpus curation as a steady-state job (Dave's sentinel work) vs measurement standards (the AMP cabal) — which one keeps the ecosystem honest? The Data Collective doesn't ratify, it just shows up to maintain. Hunger and thirst. They shall be filled. OP3.dev — open podcast analytics ----------------------------------------------------------------------------------------------------------------------------------------- 05 - CAPTIVATE LAUNCHES DAX US — THE IMPRESSION ECONOMY IRL ----------------------------------------------------------------------------------------------------------------------------------------- 06 - BBC GOES ALL-IN ON CROSSED WIRES YEAR 3 — IPLAYER DEAL + "EDINBURGH OF PODCASTING" ----------------------------------------------------------------------------------------------------------------------------------------- 07 - STREAMING CONSOLIDATION — YOUTUBE MUSIC + TUBI + NETFLIX ALL WANT "PODCAST" ----------------------------------------------------------------------------------------------------------------------------------------- 08 - SUPPLY CHAIN SECURITY — VS CODE DELAYS, PHP FOUNDATION, SLSA LEVEL 3 IS NOT ENOUGH ----------------------------------------------------------------------------------------------------------------------------------------- 09 - AI BUBBLE PC20-FLAVOR — TOTO CHUCKS, MOTHER COMPUTERS, "NO 'I', ONLY MATH" ----------------------------------------------------------------------------------------------------------------------------------------- 10 - QUIPS / TRANSITIONS ----------------------------------------------------------------------------------------------------------------------------------------- Last Modified 06/05/2026 14:38:09 by Freedom Controller

Halloweed Out Horror is back as Simon & Phill dive deep into the latest Halloween Horror Nights 35 Speculation Map 3.0! From insane IP rumours and returning icons to crazy original house theories, we're breaking down everything fans are talking about for HHN35 at Universal Studios Orlando Resort.   Could Stranger Things return? Is Jack the Clown about to take over HHN again?  What surprises could Universal have planned for the biggest Horror Nights anniversary yet?  We give our thoughts, predictions, hype levels and what we think could actually make it into the event. Are you hyped for HHN35 or are the rumours getting out of control?  Let us know your dream lineup in the comments!   ━━━━━━━━━━━━━━━ HHE PODCAST SOCIALS TikTok: @hhepod1 Instagram / Facebook / YouTube / X: @hhepod EPIC PHILL SOCIALS TikTok / YouTube / Facebook / Instagram: @epicphill1 ━━━━━━━━━━━━━━━   #HHN35 #HalloweenHorrorNights #HHN #UniversalOrlando #UniversalStudiosFlorida #HalloweedOutHorror #HHNSpecMap #HHNRumors #JackTheClown #HalloweenHorrorNightsPodcast

English Edition: Will spec-driven development replace agile processes? My guest Graham Lee  (https://chironcodex.com/ ) and I discuss if there is still a place for agile software engineering in a world of AI assisted coding.Links:https://martinfowler.com/articles/exploring-gen-ai/sdd-3-tools.html the discussion on spec driven development by Brigitta Boeckeler https://dev.to/cleberdelima/the-end-of-agile-when-the-assumptions-beneath-your-methodology-collapse-3g12 the blog post by Cleber de Lima quoted in the episodehttps://www.sicpers.info/2025/12/is-spec-driven-development-the-end-of-agile-software-development/ Graham's blog post on spec driven developmentDiscussions on Spec Driven and agile development:https://www.inflectra.com/Ideas/Whitepaper/Is-Agile-Dead.aspxhttps://www.thoughtworks.com/en-gb/insights/blog/agile-engineering-practices/spec-driven-development-unpacking-2025-new-engineering-practiceshttps://dev.to/jmontagne/mckinsey-just-killed-agile-why-commando-units-are-the-only-way-to-survive-legacy-migration-40lkhttps://marmelab.com/blog/2025/11/12/spec-driven-development-waterfall-strikes-back.htmlhttps://ronjeffries.com/categories/dark-scrum/ "dark scrum"https://www.linkedin.com/posts/adamsandman_is-agile-dead-is-ai-killing-agile-development-activity-7367308312620527616--3-2/ https://www.linkedin.com/pulse/death-agile-story-points-why-im-trading-sprints-spec-driven-park-6dfke/Some tools for spec driven developmenthttps://kiro.dev/ KIROhttps://github.com/github/spec-kit GitHub's spec-kithttps://docs.tessl.io/ TeslaGet in touchThank you for listening! Merci de votre écoute! Vielen Dank für´s Zuhören!Contact Details/ Coordonnées / Kontakt:Email mailto:peter@code4thought.orgUK RSE Slack (ukrse.slack.com): @code4thought or @piddie Bluesky: https://bsky.app/profile/code4thought.bsky.socialLinkedIn: https://www.linkedin.com/in/pweschmidt/  (personal Profile)LinkedIn: https://www.linkedin.com/company/codeforthought/ (Code for Thought Profile)This podcast is licensed under the Creative Commons Licence:  https://creativecommons.org/licenses/by-sa/4.0/

The G5 is out! So, it's a bit over due for Charlie and Matthew to talk about what's new! Have suggestions for the show, or want to Enter to Win Free RC Stuff?  - Email us!  RCStuff@Hobbywing.comDon't forget to check out the Hobbywing Official Youtube Channel : https://www.youtube.com/c/HOBBYWINGOfficial

Sinners has officially been announced as HHN35's 2nd haunted house!! Listen in as we discuss the big drop and our thoughts on the announcement and film. To start the episode off, we discuss all the changes and updates around the park, as well as ending the episode with going over the latest Horror Night Nightmares spec map.

This interview was recorded for GOTO Unscripted.https://gotopia.techDaniel Terhorst-North - Originator of Behavior Driven Development (BDD) & Principal at Dan North & AssociatesGojko Adzic - Software Delivery Consultant & Author of "Lizard Optimization" and many more BooksCheck out more here:https://gotopia.tech/articles/441RESOURCESDanielhttps://bsky.app/profile/tastapod.comhttps://www.linkedin.com/in/tastapodhttps://github.com/tastapodhttps://mastodon.social/@tastapodhttp://dannorth.net/blogGojkohttps://www.linkedin.com/in/gojkohttps://github.com/gojkohttps://twitter.com/gojkoadzichttps://gojko.netDESCRIPTIONGojko Adzic and Daniel Terhorst-North tackle the question every software team is wrestling with right now: does AI-assisted development actually work, and if so, how?Their verdict is nuanced. One-shot "spec-to-product" approaches are doomed — both compare them to CASE tools and model-driven architecture of past decades, great for selling to enterprise buyers, disappointing in practice. What does work is tight, iterative feedback loops where AI handles the more deterministic, structural parts of the job while humans retain ownership of domain knowledge, semantic correctness, and architectural judgment.The most practically useful thread of the conversation is Gojko's insight on guardrails: instead of relying on markdown files and hoping your AI agent stays in line, encode your rules as real, automated linting checks — ones that run in CI, apply to humans and bots alike, and include actionable error messages.Daniel adds a complementary observation: AI shines brightest not on core domain code, but on the "quality of life" tasks that never quite make it to the backlog. Their shared conclusion is that the teams winning with AI right now are the ones treating published frameworks as starting templates to rapidly adapt — not gospel to follow blindly.RECOMMENDED BOOKSGojko Adzic • Lizard Optimization • https://leanpub.com/lizardoptimizationGojko Adzic • Impact Mapping • https://amzn.to/3dQFCOqAdzic, Evans & Roden • Fifty Quick Ideas To Improve Your Tests • https://amzn.to/3yuDaoLAdzic, Evans & Korac • Fifty Quick Ideas to Improve Your User Stories • https://amzn.to/3jQ4QjPAdzic & Korac • Humans vs Computers • https://amzn.to/2Utz55AGojko Adzic • Specification by Example • https://amzn.to/3hHrEjbEliyahu M. Goldratt • Beyond the Goal • https://amzn.to/3wDbAL1Kent Beck, Fowler, John, William, Don & Gamma • Refactoring • https://amzn.to/3SFBYbNBlueskyInstagramLinkedInFacebookCHANNEL MEMBERSHIP BONUSJoin this channel to get early access to videos & other perks:https://www.youtube.com/channel/UCs_tLP3AiwYKwdUHpltJPuA/joinLooking for a unique learning experience?Attend the next GOTO conference near you! Get your ticket: gotopia.techSUBSCRIBE TO OUR YOUTUBE CHANNEL - new videos posted daily!

Semantic diffusion, combined with the pace of technology change, makes talking about AI-adjacent practices and techniques incredibly diffficult. There are few better examples of this issue than the term 'spec-driven development'. Although it's not new — its coinage precedes our current AI moment — it has become ubiquitous over the last six months or so as software professionals attempt to develop a vocabulary for talking about how they're developing methods for working successfully with coding agents. On this episode of the Technology Podcast, Birgitta Böckeler is joined by Laura Tacho — Developer Experience at AWS — to discuss all things spec-driven development. From competing definitions to different interpretations, implementations and workflows, the discussion provides a frank and grounded look at one of the most discussed and debated terms in modern software engineering. Learn more about Laura's work by visiting her website: https://lauratacho.com/ Read Birgitta's article on spec-driven development on Martin Fowler's website: https://martinfowler.com/articles/exploring-gen-ai/sdd-3-tools.html Learn more about The Future of Software Development Retreat discussed on this episode and explore some of the key insights: https://www.thoughtworks.com/about-us/events/the-future-of-software-development

Join Haunt Girl Nikki as she discusses the latest news and speculations from HHN35. Follow along as she takes a dive into the latest speculation map from Horror Night Nightmares. Follow Haunt Girls on social media TikTok/Instagram/ Twitter: @HauntGirlsPod Subscribe to the Haunt Girls YouTube channel!

Industrial Advisors Podcast Live at IAMC: Dallas Bulk Demand, Spec Development, Shallow Bay Challenges, and Power Constraints Live from the IAMC forum in Little Rock, the Industrial Advisors podcast hosts interview Chloe Garside of the Sansone Group about her move to Dallas as a development partner and what she's seeing in industrial real estate. She describes accelerating bulk demand nationally and in Dallas, noting Sansone has six million-square-foot spec buildings under construction or existing, with four already in lease talks, contributing to pushback toward build-to-suit for bulk due to limited availability. In Dallas, rent premiums favor bulk over sub-300,000-square-foot product, and she prefers 300,000–600,000-square-foot cross-dock specs, with 900,000–1.2 million as the big-box range. The group discusses shallow-bay/flex demand but high costs and infill site challenges, plus rising competition for land and power as data centers drive pricing expectations and utility delays, making power a daily tenant concern and prompting bridge solutions like alternative generation. 0:00 Intro and Chloe Garside's Career Journey 3:30 The State of the Dallas Industrial Market 6:45 Trends in Bulk Speculative Development 10:15 The Challenge of Shallow Bay and Flex Space 13:45 Data Centers and the Competition for Power 17:30 Creative Power Solutions and Market Outlook

The Water Colors team gathers around the table with special guest, Andrej Spec, to talk about aquarium plants. Andrej shares his aquarium journey and how he quickly went from hobbyist to passionate collector. He talks about his successes, some of his methods to that success, and so much more. Thank you so much for your kindness and inspiration, Andrej and we look forward to seeing you again. Looking for more content? Become a YouTube member for exclusive access to behind the scenes livestreams! https://www.youtube.com/@watercolorsaquariumgallery Enjoying the show? Support the gallery by shopping aquarium plants, merch, equipment, and more! https://watercolorsaquariumgallery.com/ Join the discussion on the Water Colors Aquarium Gallery Podcast Listeners Facebook group! https://www.facebook.com/groups/788428861825086/ Join our growing community on Discord! https://go.watercolors.shop/discord Sources mentioned in this episode: Andrej Spec Missouri Aquarium Society – https://missouriaquariumsociety.com/ Christel Kasselmann – https://www.instagram.com/christel.kasselmann/ Aquatic Gardeners Association – https://www.aquatic-gardeners.org/ Dennis Wong – www.2hraquarist.com Plants from Test Tubes: An Introduction to Micropropagation by Lydiane Kyte (with co-authors like John Kleyn, Holly Scoggins, and Mark Bridgen in later editions) Species mentioned in this episode: Crinum asiaticum – Crinum “Centorum” Cuphea anagalloidea Ludwigia inclinata var. verticillata – Ludwigia “Tornado” Rotala ramosior ‘Florida’ Rotala ramosior ‘Sunset’ Lobelia cardinalis – Cardinal Plant Lobelia kalmii – Kalm’s Lobelia Lobelia siphilitica – Blue Cardinal Plant Lobelia x Speciosa Oomycetes Xylaria Vallisneria spiralis var. denserrulata – Lake Tanganyika Vallisneria Cryptocoryne wendtii (‘Mi Oya’ and green) Barclaya motleyi Barclaya wellyi Nymphae – Water Lily Nymphaea sp. Peru Puerto Maldonado Nymphaea aff. dimorpha (minuta) Cryptocoryne keei Cryptocoryne nurii Cryptocoryne striolata Cryptocoryne spiralis Fenestratarum Bucephalandra ultramafica Bucephalandra kishii Cryptocoryne striolata – “Red Tiger” Crypt Osteogaster hephaestus – Fireball Cory Corydoras sp. CW113 Lagenandra ovata – “Mayan Sword” Pseudogastromyzon fasciatus “Zhejiang” Pseudogastromyzon lepidogaster

In Episode 6 of Keldabe Talk Radio, Scarif Mando, Johnny, and Lomas sit down with Spec'Troz Ma'ar to talk about an unforgettable experience as members of the Mando Mercs Costume Club were invited by Lucasfilm to tour the set of The Mandalorian & Grogu and attend the global red carpet premiere!From seeing iconic props and sets up close to walking alongside cast, crew, and fellow fans, the crew shares behind-the-scenes stories and what this once-in-a-lifetime opportunity meant to them and the club as a whole.Then, we shift gears to MercsCon 4 with our boots-on-the-ground Mandos, Yvie and Vale, as they bring us all the energy, excitement, and local secrets straight from the mandos that live there. Strap in, vod. This is one you won't want to miss.

On this week's edition of Spec says, the boss gave his list of unicorns we have seen inside of sports.

This week on the Oakley Podcast, Jeremy Kellett talks sits down with Todd Venable, General Manager at MHC Kenworth in Little Rock, to break down the current truck market, from how COVID, fuel prices, interest rates, and freight rates have impacted new and used truck values to why now may be a better time to trade than a year ago. They cover the Kenworth order board and pent-up demand, owner-operators tied to strong carriers versus independents struggling with freight and fuel, and how being leased to a company like Oakley helps with financing approvals. Todd explains the upcoming 2027 EPA emissions changes, new technology in trucks (safety systems, digital dashes, video mirrors), and the importance of dealer training and communication. They also dive into warranties and extended coverage, modern maintenance intervals, common mistakes when spec'ing a truck (especially PTO capability), the appeal of models like the W900 and T880, and how MHC, as a family-owned dealer group, is investing for the future while supporting Oakley's owner-operators. Key topics in today's conversation include: Welcome to Today's Episode with Todd Venable (0:43) State of the Truck Market, Order Board, and Demand (3:50) New Truck Orders, Fleets vs Owner-Operators, and Pent-Up Demand (5:28) Trading Out of High-Payment Trucks and Used Market Recovery (9:54) Independent Owner-Operators vs Leased-On with a Carrier (11:19) Financing Realities, Credit, Down Payments, and Lender Options (15:20) 2027 EPA Emissions Changes and What They Mean (18:26) Cummins Gas Medium-Duty Engines and Technology Shifts (21:19) Favorite and Most Hated New Safety Tech (Bendix Wingman, Alerts) (24:40) Warranties, Real-World Warranty Wins, and Why They Matter (29:08) Spec'ing a Truck: Common Mistakes and Factory Options (35:09) Making Spec'ing Less Intimidating with Line-By-Line Reviews (38:23) Best-Selling Kenworth Models: W900, T880, and Market Favorites (42:38) Future of MHC Kenworth, Alternative Powertrains, and Investment (46:07) How Oakley Owner-Operators Should Approach MHC and Contacts (51:43) Final Thoughts and Takeaways (52:12) Oakley Trucking is a family-owned and operated trucking company headquartered in North Little Rock, Arkansas. For more information, check out our show website: podcast.bruceoakley.com. Hosted by Simplecast, an AdsWizz company. See pcm.adswizz.com for information about our collection and use of personal data for advertising.

Need to specify a new elevator? Don't just copy and paste from your last elevator specs—you're missing out on new features that add to the occupant experience, deliver needed data, and keep you compliant with codes and standards.

Watch on YouTube: https://youtu.be/n2-i0RKCoWs Craig Broerman left a corporate mechanical engineering career, sold the money meant for his grandparents' farm, and bought a belt trailer in 2019. Six years later, he and his cousin Alan Lennartz are running 7–10 trucks across the Midwest hauling DDGs, soybean meal, cottonseed, and industrial products — and they did it before either of them turned 32. In this episode, Jared sits down with Craig and Alan on location in Portland, Indiana to talk about the BulkLoads find that changed everything, the phone call in a North Carolina cornfield that made Craig get out of the truck for good, the mistakes they made buying "shiny" equipment, and the insurance and scaling realities nobody warns young carriers about. If you're an owner-operator, small fleet, or thinking about getting into bulk trucking — this one's a roadmap.   ⏱ TIMECODES 00:00 – On location in Portland, Indiana 00:43 – From mechanical engineer to belt trailer owner 02:25 – Finding BulkLoads and the first direct customer 03:25 – Retiring his wife from her corporate job 04:40 – Alan's path: asphalt, COVID, and "buy a truck" 06:00 – The conversation that split the businesses 06:30 – The cornfield phone call that changed everything 09:40 – How they funded the first truck (the farm gamble) 11:00 – Why posted loads = desperation (and opportunity) 13:30 – Reading the cottonseed market before it shifted 15:30 – Playing the long game on rates and relationships 17:15 – Why Craig thinks 5 years ahead, not 5 days 20:30 – What's actually moving in/out of Ohio–Indiana ag country 22:18 – Why they can't run hoppers in this region 24:40 – The real ROI of the BulkLoads Conference 27:30 – Trust, transparency, and family in business 28:00 – Biggest mistakes: overpriced trucks and hiring too soon 31:30 – How they decide when to scale (and when to wait) 36:50 – Spec'ing equipment: powertrains, trailers, and tonnage 39:00 – 48' vs 53' Conestoga — three months of research 42:30 – DDG market shifts and lane risk 44:00 – The insurance ceiling nobody talks about 47:20 – Advice for young people getting into trucking and logistics 51:30 – Why this part of the country looks the way it does

New episode of The Epic Joys of Travel Podcast! Simon & Phill dive into the latest Halloweed Out Horror HHN35 Spec Map and discuss whether this rumoured lineup would make an epic year for Universal Studios Florida Halloween Horror Nights 35! Which scare houses excite us most? Which rumours seem believable?

En este episodio vamos a hablar sobre lo que es el Spec Driven Design, sugerencias, puntos para escribir buenos specs y recomendaciones de cuándo no usarlo.

PREVIEW for Later Today: The Strategy of Electoral Delays. Guest: Evan Ellis. Negotiations regarding election dates involve complex demands for voter role purges and machine replacements. Ellis examines how slow-walking these reforms serves specific political interests while complicating international policy goals.1940 VENEZUELA

The Drive played what the boss had to say when it comes to how many of the Chiefs 2026 draft picks will be on the roster when the Chiefs open their new stadium.

Hosts Tasha Huo and Josh Hallman check in on their current specs, break down their process for starting a new idea, and talk about why uninterrupted writing time is nearly impossible to protect. Also, TWIW!   Questions / Comments: ActTwoWriters@gmail.com Edited by the GREAT Paul Lundquist 

Join Dan Vega and DaShaun Carter for the latest updates from the Spring Ecosystem. In this episode, Dan and DaShaun are joined by Java Champion, Vaadin Champion, and Oracle ACE Pro Simon Martinelli to talk about Spec-Driven Development. With AI reshaping how we write code, Simon makes the case that requirements, not code, should be the single source of truth. We will explore what Spec-Driven Development looks like in practice, how it fits into a Java and Spring workflow, and how teams can use it to move from use case to running code with AI in the loop. You can participate in our live stream to ask questions or catch the replay on your preferred podcast platform.Show NotesSimon Martinelli on LinkedInSimon Martinelli on XSpec-Driven Development: How AI Changed Everything (And Nothing) by Simon Martinelli at Spring I/O 2026

There are two things that Subaru has told us the BRZ will never get from the day that the design was revealed.1. It will never get a turbocharged engine2. It will never be All Wheel DriveBut now they have built the Boxer Rally spec.Z which is both.How did we get to this point?When we thought that this AWD BRZ Rally Car was just going to be a clone of the Toyota Celica that we have seen testing for the 2027 WRC season, it seemed like this was at least going to be part of Subaru's return to the WRC. But it seemed like it was going to be using Toyota's engine and drivetrain.Now we know that the Boxer Rally spec.Z is at least using a Subaru engine (A turbocharged BRZ FA24 from the looks of it), but that also makes it seem like this may not have nearly as much to do with a return to the WRC as we thought.So why is Subaru building this car? What are they testing and what do they hope to learn?After going through a number of videos from the launch of the car, I have a couple of guesses.Thanks for watching and Stay Tuned!

工程師都宅宅的不太會講話？ 其實工程師的幹話多到你聽不下去！ ------ 加入粉絲團留言互動！ https://www.facebook.com/%E5%B7%A5%E7%A8%8B%E5%B8%AB%E8%81%8A%E4%BB%80%E9%BA%BC-109229084578194 ------ softwaretalkthreesmall@gmail.com -- Hosting provided by SoundOn

Terrazzo Talk, Fun Money vs Easy Money, and Client Talk! Subscribe and don't for get to leave questions and topics in the comments below. Thanks for watching! #podcast #modernmaker #makerFull Episode Link: https://youtu.be/155eiGNa0us?si=Gkm5xKSdQXjefokz

Spring is here and I'm shaking off the winter funk with a little honesty and a lot of heart. I've been in a weird low energy season, but I'm finally starting to feel that spark again. Enough to kick off … Continue reading → The post It’s OK to not be OK appeared first on NIMLAS Studios.

Hour 4: Matt Quatraro, We Call Out Spec for Hating full 2746 Wed, 29 Apr 2026 14:59:46 +0000 j6zo3gKtpGAtBYuSYv5hT4sm0iEibvuw nfl,mlb,kansas city chiefs,kansas city royals,sports Fescoe & Dusty nfl,mlb,kansas city chiefs,kansas city royals,sports Hour 4: Matt Quatraro, We Call Out Spec for Hating Fescoe in the Morning. One guy is a KU grad.   The other is on the KU football broadcast team,  but their loyalty doesn't stop there as these guys  are huge fans of Kansas City sports and the people  of Kansas City who make it the great city it is.   Start your morning with us at 5:58am!   2024 © 2021 Audacy, Inc. Sports False https://player.amperwavepodcasting.com?fee

Is the final frontier the ultimate high-trust marketing channel? In this content, I break down how a single floating jar of Nutella during the Artemis II NASA livestream might have just rewritten the CPG marketing playbook. Traditional advertising is dying behind adblockers, but space remains one of our last "monocultural moments." When a CPG product appears in a lunar habitat, it carries an implicit "seal of authenticity" that no Super Bowl spot can buy. From Nutella's reactive marketing readiness to Astreas performance nutrition in orbit "R&D as Marketing" strategy, I'm exploring how the CPG industry is moving from Earth-based goods to space-engineered excellence.In my latest video, I dive deep into topics like:Nutella "Moon Drift" = How an accidental moment turned into a global commercial.Is "Space-Spec" the New Organic? = Why being "good enough for orbit" is becoming the ultimate validator for durability and nutrition. Future of the Orbital Pantry: Moving from "accidental ads" to a future of Direct-to-Orbit supply chains. Will your next snack be delivered to a lunar habitat?Avoiding "Space-Washing": The "billionaire's playground" narrative is a risk, but the winners won't be the CPG brands that put logos on the moon. Instead, it'll be the ones that use space-based R&D to make life better on Earth.Also, do you think the Apollo moon landings were real, or just the world's most powerful propaganda?

Can you help me make more podcasts? Consider supporting me on Patreon as the service is 100% funded by you: https://EVne.ws/patreon You can read all the latest news on the blog here: https://EVne.ws/blog Subscribe for free and listen to the podcast on audio platforms:➤ Apple: https://EVne.ws/apple➤ YouTube Music: https://EVne.ws/youtubemusic➤ Spotify: https://EVne.ws/spotify➤ TuneIn: https://EVne.ws/tunein➤ iHeart: https://EVne.ws/iheart CHINA APRIL NEV PENETRATION TOPS 60% https://evne.ws/4eKWnec PORSCHE PRICES ELECTRIC CAYENNE TURBO IN CHINA https://evne.ws/42Azi6E CHINA'S CHARGING NETWORK HITS 21.481 MILLION https://evne.ws/41WVxDS BYD GREAT TANG TOPS 30,000 PRE-ORDERS https://evne.ws/4mTxcs8 GAC HYPER OPENS S600 ORDERS IN BEIJING https://evne.ws/42wFHQo FREELANDER 8 BREAKS COVER ON WEIBO https://evne.ws/4tA3oDp LEAPMOTOR CHASES 1 MILLION SALES IN 2026 https://evne.ws/4euEEb9 ARIDGE TOPS 7,000 PRE-ORDERS IN BEIJING https://evne.ws/3Op0ulK CHERY SHOWS FULWIN A9 WAGON CONCEPT https://evne.ws/3QtvqSt SAIC VOLKSWAGEN LAUNCHES ID. ERA 9X https://evne.ws/4euEtfZ NIO OPENS BLUE LIGHT RETROFIT PRE-ORDERS https://evne.ws/4uckozu

Spector joined The Drive to voice his displeasure that Cdot stole his take over the weekend on social media.

In today's episode, we go through the our daily update from the Strait of Hormuz and how it is impacting borrower behavior. Plus, Robbie sits down with Paddington Capital Management's Paul Musson for a discussion on how policymakers are repeatedly propping up asset prices at the expense of long-term economic health and fairness. And we close by looking at the latest labor market indicators.Thank you to Experian Verify, a comprehensive income and employment verification solution for mortgage lenders. By uniting instant payroll data, permissioned access, and research verification in one seamless experience, Experian Verify helps lenders reduce friction, accelerate decisions, and confidently verify every U.S. worker.The Chrisman Commentary is your go-to daily mortgage news podcast, where industry insights meet expert analysis. Hosted by Robbie Chrisman, this podcast delivers the latest updates on mortgage rates, capital markets, and the forces shaping the housing finance landscape. Whether you're a seasoned professional or just looking to stay informed, you'll get clear, concise breakdowns of market trends and economic shifts that impact the mortgage world.

Steven Spector joined The Drive with a conspiracy theory that the Bengals made the trade for Dexter Lawrence because Joe Burrow told them to make the team better or he's out.

In this video, I break down why spec projects don't belong on your P&L, how they should be tracked on your balance sheet, and why getting this wrong makes your business look less profitable than it really is. And if you want help cleaning this up in your own books so your numbers actually reflect reality, book a call with our team and we'll walk through it with you.

Want to be on the show? Leave us a voicemail! (407) 906-4134 Follow The Hauntline on social media: Instagram: @thehauntline Twitter: @thehauntline YouTube: @TheHauntline Follow HHN 365 on social media: Instagram HHN365 Twitter @HHN365 TikTok: @HHN365pod Join our Discord Server: https://discord.gg/jUD9nZav2U Merch: HHN365.com Featured audio is courtesy of White Bat Audio

Every public company's R&D number is a lie hiding in plain sight. Not because anyone falsified it. Because the number was never built to tell the truth. It was built to satisfy an accounting standard written in 1974. And for fifty years, boards, analysts, and CEOs have been making billion-dollar innovation decisions based on a number designed by accountants to solve a different problem entirely. Here's what makes this genuinely strange. The real number exists. The government has been collecting it from every major US company for decades. It would answer the question every innovation leader and investor actually needs answered. And it is locked away by federal law. Confidential. Never published. Never seen by the people who need it most. It's sitting in a federal database right now. And there's a way to estimate it for any public company, without asking anyone's permission. I know it exists because I spent years building it from the inside. Why the R&D Signal Was Blurry When I was running innovation at HP, we discovered this problem firsthand. We had a connection between R&D investment and gross margin that held up across decades of HP history. Better than anything Wall Street was using. But the signal was blurry. None of us could figure out why. The answer came from a question someone on the team asked almost as an aside. What if R&D isn't one thing? Research and Development Are Not the Same Thing Think about what actually lives inside a typical R&D budget. There's a team somewhere investigating whether a new approach could enable a capability that doesn't exist yet. No product defined. No spec written. Asking whether something is even possible. And there's a team building the next version of a product that ships in eighteen months. Spec locked. Timeline set. Engineering executing against a defined target. Both show up on the same line in the budget. Both get called R&D. Both count equally toward the number that gets reviewed every quarter. They are not the same thing. One is Research. The other is Development. Research is the work you do when you don't yet know what you're building. The output is understanding. New knowledge that might enable future products nobody has designed yet. You can't know exactly what you'll find. If you already knew, it wouldn't be research. Development is the work you do when you know exactly what you're building. The spec exists. The product is defined. The question isn't what to make. It's whether it can be made, on time, at cost, at quality. One creates the future. The other delivers the present. And for fifty years, every public company in America has been required to report them as one indistinguishable number. When we split the HP data along that line, Research on one side and Development on the other, the signal sharpened immediately. Research spend, measured against gross margin three to five years later, was a meaningfully stronger predictor than the combined number had ever been. The blur hadn't been in the gross margin data. It had been in the R&D number itself. Two fundamentally different things, averaged together, producing a number that looked precise and predicted almost nothing. But splitting R from D at the company level was only the beginning. The model was still lying to us. Just more quietly. Why Company-Level R&D Splits Still Mislead Even with the split, something was still soft. HP wasn't one business. It was dozens. Printers, PCs, servers, software, each running on different timelines, different technology cycles, different competitive dynamics. What if the R/D split meant something different depending on where it was applied? We pushed it to the product line level. Then further, to the platform level within product lines. Printers were the clearest example. HP's printer business wasn't one story. There were platforms built on established technology. Mature ink systems, proven print head chemistry, products that had been shipping for years. And there were platforms built on genuinely new core technology. New chemistry. New mechanisms. New approaches to fundamental problems that nobody had solved yet. Research investment by platform told a completely different story than Research investment by product category. The Research going into new technology platforms had a completely different relationship to future margin than Research going into mature platforms. Different time horizons. Different risk profiles. Different margin implications years down the road. Laptops told the same story. A traditional consumer laptop line and a high-performance portable workstation weren't the same investment. One was Development-heavy. Defined product, known market, engineering executing against spec. The other had genuine Research behind it. Unsolved thermal problems, new form factor constraints, and materials questions that hadn't been answered yet. When a single R&D assumption is applied across all of that, treating every dollar the same regardless of what it actually does, the signal disappears into the average. Peanut butter across the portfolio. The model only got honest when it got specific. Research by platform and Development by platform, matched against the margin performance of those specific platforms years later. Which platforms were building future margin? Which ones were running on margin that past Research had already bought? We could see it because we were inside the company. The question is whether anyone on the outside could ever see the same thing. The R&D Data the Government Collects and Won't Release Outside the internal budget process, everyone sees the same thing: a single line on the income statement. The US government recognized decades ago that the combined R&D number was analytically useless. So they built a system to collect the real one. The National Science Foundation runs a survey called the Business Enterprise Research and Development survey. The BERD survey. Every year, roughly 47,500 US companies are required to report their R&D spending broken into three categories: basic research, applied research, and experimental development. The split that every board and every investor needs to see. Mandatory. Collected. Verified. And then locked away. The firm-level data is confidential under federal law. The NSF publishes only industry-level aggregates. So every company fills out this survey and reports its real R/D split to the government. That data sits in a federal database. And the boards, investors, and analysts who need it most cannot access it. Researchers at Northwestern and Boston University were given rare access to that confidential data. What they found is striking. When companies face financial pressure and cut R&D, they don't cut Development. They cut Research. Almost entirely. Development barely moves. Every earnings squeeze. Every activist campaign. Every cost optimization program. Systematically targeting the one part of R&D that builds future margin. And because the combined number barely moves, nobody on the outside sees it happening. That's not a coincidence. That's the accounting standard doing exactly what it was designed to do: produce one clean number for the income statement. It was never asked to protect the future. How to Estimate the Research-to-Development Split Without Inside Access So what can actually be done without access to the locked data? More than most people realize. Step 1. Find the industry baseline. The aggregate BERD data is public at the sector level. Ask an AI tool for the Research-to-Development ratio for the relevant industry. That's the benchmark. Everything else gets measured against it. A company spending 8% of its R&D on Research in an industry where the average is 25% is telling you something the combined number never would. Step 2. Look at the gross margin trend compared to peers. Gross margin over time is the most honest external signal of Research health. A company with a declining margin relative to peers, while reporting flat or growing R&D spend, is almost certainly shifting the mix toward Development. The math works in the other direction, too. An AI tool can pull this comparison for any public company in minutes. This is exactly the signal that was invisible at HP until it was too late. Step 3. Look at patent trends compared to peers over time. Patents are an imperfect but useful directional indicator. Not because more patents always means more Research. It doesn't. But a sustained decline in patent output relative to peers, alongside flat R&D spend, suggests the investment is maintaining existing products rather than creating new knowledge. Combined with the gross margin trend, it starts to triangulate where the split actually sits. None of these three steps requires access to an internal budget. All of them can be done in an afternoon with public data and an AI tool. Together, they produce a working picture of the R/D split that the income statement was never designed to reveal. What the R&D Split Revealed at HP That No One Outside Could See When Hurd took over in 2005, HP was spending $3.5 billion on R&D. Roughly 4% of revenue. By 2009, his last full year as CEO, that had dropped to $2.8 billion. Revenue had grown significantly over that period, so the percentage had fallen further still, to under 2.5%. Both the dollar amount and the ratio were declining simultaneously while the company got larger. Wall Street tracked the combined number. The board reviewed it. Nobody raised a structural alarm. The Research component within that total was well below the industry average for comparable technology companies. Not slightly. Significantly. The margin consequences arrived years later. They always do. What Happens When the Definition of Research Doesn't Exist The R/D split gave us a real predictive signal. We ran with it. The conversations were sharper. But the team kept pulling on a thread that nobody expected. When we looked closely at what was actually being called Research, project by project and budget line by budget line, things that didn't feel the same kept appearing. Work aimed at fundamental discovery. Work aimed at solving a specific defined problem using entirely new methods. Both labeled Research. Up close, they behaved differently, predicted different things, and when budgets got tight, got treated very differently. So we went looking for the agreed definition. The official standard that would tell exactly where to draw the lines inside Research. It didn't exist. Not the way we needed it to. And without it, everything we'd built was sitting on sand. How do you build a predictive model on a definition that doesn't exist? That's the next episode. If this helped you see something you might have missed, subscribe wherever you listen to podcasts. On YouTube, hit subscribe and the bell so you don't miss the next episode. And if you want to go deeper every Monday, join us at Studio Notes — free, at philmckinney.com. Until next time. See the pattern. Make the call.  

Vibe coding: give AI a description of what you want, the model writes the code, you ship it, and then you hope for the best. It works great for side projects, but it can fall apart the moment you point an AI agent at production infrastructure. Today, William and Eyvonne sit down with John Capobianco,... Read more »

Send us Fan MailYour AI can write code fast, but it can also wander fast. That's why we sat down with Jason Belk from Learning at Cisco to unpack spec-driven development, a simple idea with huge impact: write the rules and requirements first, then let your coding agent execute with far fewer surprises.We talk through what “agentic coding” looks like in practice with Claude Code, including the trust and permission model of a local AI agent that can create files, run bash commands, and iterate on a real project. Jason explains how GitHub Spec Kit turns plain markdown and scripts into a repeatable workflow: start with a constitution that defines governing principles, then cycle feature by feature through specify, plan, tasks, and implement. Along the way we cover common gotchas like initializing in the wrong directory so skills never load, plus practical tips like using voice-to-text to improve prompts and choosing the right model tier when implementation quality matters.We also zoom out to the bigger picture: why context windows break long builds, how keeping plans on disk helps the agent “re-ground” itself, and where the industry may be heading with small specialized models versus one giant general LLM. Jason shares learning resources too, including a Cisco U tutorial that frames spec-driven development for network engineers, and the Cisco AI Technical Practitioner course and certification, plus upcoming Cisco Live sessions.Subscribe for more real-world AI workflows, share this with a teammate who keeps fighting prompt drift, and leave a review with the one automation project you want an agent to build next.Connect with Jason:https://linktr.ee/renobelkhttps://github.com/jabelk/claude-speckit-templateSDD Relevant Material mentioned in this episode:https://sdd.goecke.io/https://substack.com/home/post/p-189415335https://ondemandelearning.cisco.com/apollo-alpha/tc-ai-spec-driven-dev/pages/1 https://learningnetwork.cisco.com/s/aitech-exam-topicshttps://u.cisco.com/paths/cisco-ai-technical-practitioner-20806https://u.Purchase Chris and Tim's book on AWS Cloud Networking: https://www.amazon.com/Certified-Advanced-Networking-Certification-certification/dp/1835080839/Check out the Monthly Cloud Networking Newshttps://docs.google.com/document/d/1fkBWCGwXDUX9OfZ9_MvSVup8tJJzJeqrauaE6VPT2b0/Visit our website and subscribe: https://www.cables2clouds.com/Follow us on BlueSky: https://bsky.app/profile/cables2clouds.comFollow us on YouTube: https://www.youtube.com/@cables2clouds/Follow us on TikTok: https://www.tiktok.com/@cables2cloudsMerch Store: https://store.cables2clouds.com/Join the Discord Study group: https://artofneteng.com/iaatj

We're proud to release this ahead of Ryan's keynote at AIE Europe. Hit the bell, get notified when it is live! Attendees: come prepped for Ryan's AMA with Vibhu after.Move over, context engineering. Now it's time for Harness engineering and the age of the token billionaires.Ryan Lopopolo of OpenAI is leading that charge, recently publishing a lengthy essay on Harness Eng that has become the talk of the town:In it, Ryan peeled back the curtains on how the recently announced OpenAI Frontier team have become OpenAI's top Codex users, running a >1m LOC codebase with 0 human written code and, crucially for the Dark Factory fans, no human REVIEWED code before merge. Ryan is admirably evangelical about this, calling it borderline “negligent” if you aren't using >1B tokens a day (roughly $2-3k/day in token spend based on market rates and caching assumptions):Over the past five months, they ran an extreme experiment: building and shipping an internal beta product with zero manually written code. Through the experiment, they adopted a different model of engineering work: when the agent failed, instead of prompting it better or to “try harder,” the team would look at “what capability, context, or structure is missing?”The result was Symphony, “a ghost library” and reference Elixir implementation (by Alex Kotliarskyi) that sets up a massive system of Codex agents all extensively prompted with the specificity of a proper PRD spec, but without full implementation:The future starts taking shape as one where coding agents stop being copilots and start becoming real teammates anyone can use and Codex is doubling down on that mission with their Superbowl messaging of “you can just build things”.Across Codex, internal observability stacks, and the multi-agent orchestration system his team calls Symphony, Ryan has been pushing what happens when you optimize an entire codebase, workflow, and organization around agent legibility instead of human habit.We sat down with Ryan to dig into how OpenAI's internal teams actually use Codex, why the real bottleneck in AI-native software development is now human attention rather than tokens, how fast build loops, observability, specs, and skills let agents operate autonomously, why software increasingly needs to be written for the model as much as for the engineer, and how Frontier points toward a future where agents can safely do economically valuable work across the enterprise.We discuss:* Ryan's background from Snowflake, Brex, Stripe, and Citadel to OpenAI Frontier Product Exploration, where he works on new product development for deploying agents safely at enterprise scale* The origin of “harness engineering” and the constraint that kicked off the whole experiment: Ryan deliberately refused to write code himself so the agent had to do the job end to end* Building an internal product over five months with zero lines of human-written code, more than a million lines in the repo, and thousands of PRs across multiple Codex model generations* Why early Codex was painfully slow at first, and how the team learned to decompose tasks, build better primitives, and gradually turn the agent into a much faster engineer than any individual human* The obsession with fast build times: why one minute became the upper bound for the inner loop, and how the team repeatedly retooled the build system to keep agents productive* Why humans became the bottleneck, and how Ryan's team shifted from reviewing code directly to building systems, observability, and context that let agents review, fix, and merge work autonomously* Skills, docs, tests, markdown trackers, and quality scores as ways of encoding engineering taste and non-functional requirements directly into context the agent can use* The shift from predefined scaffolds to reasoning-model-led workflows, where the harness becomes the box and the model chooses how to proceed* Symphony, OpenAI's internal Elixir-based orchestration layer for spinning up, supervising, reworking, and coordinating large numbers of coding agents across tickets and repos* Why code is increasingly disposable, why worktrees and merge conflicts matter less when agents can resolve them, and what it really means to fully delegate the PR lifecycle* “Ghost libraries”, spec-driven software, and the idea that a coding agent can reproduce complex systems from a high-fidelity specification rather than shared source code* The broader future of Frontier: safely deploying observable, governable agents into enterprises, and building the collaboration, security, and control layers needed for real-world agentic workRyan Lopopolo* X: https://x.com/_lopopolo* Linkedin: https://www.linkedin.com/in/ryanlopopolo/* Website: https://hyperbo.la/contact/Timestamps00:00:00 Introduction: Harness Engineering and OpenAI Frontier00:02:20 Ryan's background and the “no human-written code” experiment00:08:48 Humans as the bottleneck: systems thinking, observability, and agent workflows00:12:24 Skills, scaffolds, and encoding engineering taste into context00:17:17 What humans still do, what agents already own, and why software must be agent-legible00:24:27 Delegating the PR lifecycle: worktrees, merge conflicts, and non-functional requirements00:31:57 Spec-driven software, “ghost libraries,” and the path to Symphony00:35:20 Symphony: orchestrating large numbers of coding agents00:43:42 Skill distillation, self-improving workflows, and team-wide learning00:50:04 CLI design, policy layers, and building token-efficient tools for agents00:59:43 What current models still struggle with: zero-to-one products and gnarly refactors01:02:05 Frontier's vision for enterprise AI deployment01:08:15 Culture, humor, and teaching agents how the company works01:12:29 Harness vs. training, Codex model progress, and “you can just do things”01:15:09 Bellevue, hiring, and OpenAI's expansion beyond San FranciscoTranscriptRyan Lopopolo: I do think that there is an interesting space to explore here with Codex, the harness, as part of building AI products, right? There's a ton of momentum around getting the models to be good at coding. We've seen big leaps in like the task complexity with each incremental model release where if you can figure out how to collapse a product that you're trying to.Build a user journey that you're trying to solve into code. It's pretty natural to use the Codex Harness to solve that problem for you. It's done all the wiring and lets you just communicate in prompts. To let the model cook, you have to step back, right? Like you need to take a systems thinking mindset to things and constantly be asking, where is the Asian making mistakes?Where am I spending my time? How can I not spend that time going forward? And then build confidence in the automation that I'm putting in place. So I have solved this part of the SDLC.swyx: [00:01:00] All right.[00:01:03] Meet Ryan swyx: We're in the studio with Ryan from OpenAI. Welcome.Ryan Lopopolo: Hi,swyx: Thanks for visiting San Francisco and thanks for spending some time with us.Ryan Lopopolo: Yeah, thank you. I'm super excited to be here.swyx: You wrote a blockbuster article on harness engineering. It's probably going to be the defining piece of this emerging discipline, huh?Ryan Lopopolo: Thank you. It is it's been fun to feel like we've defined the discourse in some sense.swyx: Let's contextualize a little bit, this first podcast you've ever done. Yes. And thank you for spending with us. What is, where is this coming from? What team are you in all that jazz?Ryan Lopopolo: Sure, sure.Ryan Lopopolo: I work on Frontier Product Exploration, new product development in the space of OpenAI Frontier, which is our enterprise platform for deploying agents safely at scale, with good governance in any business. And. The role of VMI team has been to figure out novel ways to deploy our models into package and products that we can sell as solutions to enterprises.swyx: And you have a background, I'll just squeeze it in there. Snowflake, brick, [00:02:00] stripe, citadel.Ryan Lopopolo: Yes. Yes. Same. Any kind of customerswyx: entire life. Yes. The exact kind of customer that you want to,Vibhu: so I'll say, I was actually, I didn't expect the background when I looked at your Twitter, I'm seeing the opposite.Stuff like this. So you've got the mindset of like full send AI, coding stuff about slop, like buckling in your laptop on your Waymo's. Yes. And then I look at your profile, I'm like, oh, you're just like, you're in the other end too. Oh, perfect. Makes perfect.Ryan Lopopolo: I it's quite fun to be AI maximalist if you're gonna live that persona.Open eye is the place to do it. And it'sswyx: token is what you say.Ryan Lopopolo: Yeah. Certainly helps that we have no rate limits internally. And I can go, like you said, full send at this stay.swyx: Yeah. Yeah. So the Frontier, and you're a special team within O Frontier.Ryan Lopopolo: We had been given some space to cook, which has been super, super exciting.[00:02:47] Zero Code ExperimentRyan Lopopolo: And this is why I started with kind of a out there constraint to not write any of the code myself. I was figuring if we're trying to make agents that can be deployed into end to enterprises, they should be [00:03:00] able to do all the things that I do. And having worked with these coding models, these coding harnesses over 6, 7, 8 months, I do feel like the models are there enough, the harnesses are there enough where they're isomorphic to me in capability and the ability to do the job.So starting with this constraint of I can't write the code meant that the only way I could do my job was to get the agent to do my job.Vibhu: And like a, just a bit of background before that. This is basically the article. So what you guys did is five months of working on an internal tool, zero lines of code over a mi, a million lines of code in the total code base.You say it was cenex, more like it was cenex faster than you would've. If you had done it by end. SoRyan Lopopolo: yeah, thatVibhu: was the mindset going into this, right?Ryan Lopopolo: That's right.[00:03:46] Model Upgrades LessonsRyan Lopopolo: Started with some of the very first versions of Codex CLI, with the Codex Mini model, which was obviously much less capable than the ones we have today.Which was also a very good constraint, right? Quite a visceral feeling to ask the [00:04:00] model to build you a product feature. And it just not being able to assemble the pieces together.Which kind of defined one of the mindsets we had for going into this, which is whenever the model just cannot, you always pop open at the task, double click into it, and build smaller building blocks that then you can reassemble into the broader objective.And it was quite painful to do this. Honestly, the first month and a half was. 10 times slower than I would be. But because we paid that cost, we ended up getting to something much more productive than any one engineer could be because we built the tools, the assembly station for the agent to do the whole thing.[00:04:43] Model Generations, Build Systems & Background ShellsRyan Lopopolo: But yeah, so onward to G BT 5, 5, 1, 5, 2, 5, 3, 5 4. To go through all these model generations and see their kind of corks and different working styles also meant we had to adapt the code base to change things up when the model was revved. [00:05:00] One interesting thing here is five two, the Codex harness at the time did not have background shells in it, which means we were able to rely on blocking scripts to perform long horizon work.But with five, three and background shells, it became less patient, less willing to block. So we had to retool the entire build system to complete in under a minute and. This is not a thing I would expect to be able to do in a code base where people have opinions. But because the only goal was to make the Asian productive over the course of a week, we went from a bespoke make file build to Basil, to turbo to nx and just left it there because builds were fast at that point.swyx: Interesting. Talk more about Turbo TenX. That's interesting ‘cause that's the other direction that other people have been doing.Ryan Lopopolo: Ultimately I have. Not a lot of experience with actual frontend repo architecture.swyx: You're talking that Jessica built the sky. So I'm like, I know the NX team. I know Turbo from Jared [00:06:00] Palmer.And I'm like, yeah, that's an interesting comparison.[00:06:02] One Minute Build LoopRyan Lopopolo: The hill we were climbing right, was make it fast.swyx: Is there a micro front end involved? Is it how how complex reactRyan Lopopolo: electron base single app sort of thingswyx: And must be under a minute. That's an interesting limitation. I'm actually not super familiar with the background shelf stuff.Probably was talked about in the fight three release.Ryan Lopopolo: BA basically means that codex is able to spawn commands in the background and then go continue to work while it waits for them to finish. So it can spawn an expensive build and then continue reviewing the code, for example.swyx: Yeah.Ryan Lopopolo: And this helps it be more time efficient for the user invoking the harness.swyx: And I guess and just to really nail this, like what does one minute matter? Like why not five, okay, good. We want no. WeRyan Lopopolo: want the inner loop to be as fast as possible. Okay. One minute was just a nice round number and we were able to hit it.swyx: And if it doesn't complete, it kills it or some something,Ryan Lopopolo: No.We just take that as a signal that we need to stop what we're doing, double click, decompose a build graph a bit to get us to high back under so that we [00:07:00] can able the agent continue to operate.swyx: It's almost like you're, it's like a ratchet. It's like you're forcing build time discipline, because if you don't, it'll just grow and grow.That's right. And you mentioned that my current, like the software I work on currently is at 12 minutes. It sucks.Ryan Lopopolo: This has been my experience with platform teams in the past, where you have an envelope of acceptable build times and you let it go up to breach and then you spend two, three weeks to bring it back down to the lower end of the average low bed stop.But because tokens are so cheap Yeah. And we're so insanely parallel with the model, we can just constantly be gardening this thing to make sure that we maintain these in variants, which means. There's way less dispersion in the code and the SDLC, which means we can simplify in a way and rely on a lot more in variance as we write the software.[00:07:45] Observability, Traces & Local Dev StackVibhu: Lovely.[00:07:46] Humans Are BottleneckVibhu: You mentioned in your article, like humans became the bottleneck, right? You kicked off as a team of three people. You're putting out a million line of code, like 1500 prs, basically. What's the mindset there? So as much as code is disposable, you're doing a lot of review. A lot [00:08:00] of the article talks about how you wanna rephrase everything is prompting everything, is what the agent can't see.It's kind of garbage, right? You shouldn't have it in there. So what's like the high level of how you went about building it, and then how you address okay, humans are just PR review. Like how is human in the loop for this?Ryan Lopopolo: We've moved beyond even the humans reviewing the code as well.[00:08:19] Human Review, PR Automation & Agent Code ReviewRyan Lopopolo: Most of the human review is post merge at this point.But post, post merge, that's not even reviewed. That's justswyx: Oh, let's just make ourselves happy by YouRyan Lopopolo: haven't used fundamentally. The model is trivially paralyzable, right? As many GPUs and tokens as I am willing to spend, I can have capacity to work with my hood base.The only fundamentally scarce thing is the synchronous human attention of my team. There's only so many hours in the day we have to eat lunch. I would like to sleep, although it's quite difficult to, stop poking the machine because it makes me want to feed it. You have to step back, right?Like you need to take a systems thinking mindset to things and [00:09:00] constantly be asking where is the agent making mistakes? Where am I spending my time? How can I not spend that time going forward? And then build confidence in the automation that I'm putting in place. So I have solved this part of the SDLC, and usually what that has looked like is like we started needing to pay very close attention to the code because the agent did not have the right building blocks to produce.Modular software that decomposed appropriately that was reliable and observable and actually accrued a working front end in these things, right?[00:09:35] Observability First SetupRyan Lopopolo: So in order to not spend all of our time sitting in front of a terminal at most, doing one or two things at a time, invested in giving the model that observability, which is that that graph in the post here.swyx: Yeah. Let's walk through this traces and which existed firstRyan Lopopolo: we started with just the app and the whole rest of it. From vector through to all these login metrics, APIs was, I dunno, half an [00:10:00] afternoon of my time. We have intentionally chosen very high level fast developer tools. There's a ton of great stuff out there now.We use me a bunch, which makes it trivial to pull down all these go written Victoria Stack binaries in our local development. Tiny little bit of python glue to spin all these up. And off you go. One neat thing here is we have tried to invert things as much as possible, which is instead of setting up an environment to spawn the coding agent into, instead we spawn the coding agent, like that's the entry point.It's just Codex. And then we give Codex via skills and scripts the ability to boot the stack if it chooses to, and then tell it how to set some end variables. So the app and local Devrel points at this stack that it has chosen to spin up. And this I think is like the fundamental difference between reasoning models and the four ones and four ohs of the past, where these models could not think so you had to put them in [00:11:00] boxes with a predefined set of state transitions.Whereas here we have the model, the harness be the whole box. And give it a bunch of options for how to proceed with enough context for it to make intelligent choices. SoVibhu: sales, so like a lot of that is around scaffolding, right? Yes. Previous agents, you would define a scaffold. It would operate in that.Lube, try again. That's pivoted off from when we've had reasoning models. They're seeming to perform better when you don't have a scaffold, right? That's right.[00:11:28] Docs Skills GuardrailsVibhu: And you go into like niches here too, like your SPEC MD and like having a very short agent MG Agent md.swyx: Yes. Yes.Vibhu: Yeah. So you even lay out what it is here, but I likeswyx: the table contents.Vibhu: Yeah.swyx: Like stuff like this, it really helps guide people because everyone's trying to do this.Ryan Lopopolo: This structure also makes it super cheap to put new content into the repository to steer both the humans and the agents.swyx: You, you reinvented skills, right?Vibhu: One big agents andswyx: skills from first princip holdsRyan Lopopolo: all skills did not exist when we started doing this.Vibhu: You have a short [00:12:00] one 100 line overall table of contents and then you have little skills, right? Core beliefs, MD tech tracker. Yeah. Yeah. The scale is overRyan Lopopolo: The tech jet tracker and the quality score are pretty interesting because this is basically a tiny little scaffold, like a markdown table, which is a hook for Codex to review all the business logic that we have defined in the app, assess how it matches all these documented guardrails and propose follow up work for itself.Before beads and all these ticketing systems, we were just tracking follow up work as notes in a markdown file, which, we could spa an agent on Aron to burn down. There's this really neat thing that like the models fundamentally crave text. So a lot of what we have done here is figure out ways to inject textswyx: intoRyan Lopopolo: the system right when we get a page, because we're missing a timeout, for example.I can just add Codex in Slack on that page and say, I'm gonna fix this by adding a timeout. Please update our reliability documentation. To require that all network calls have [00:13:00] timeouts. So I have not only made a point in time fix, but also like durably encoded this process knowledge around what good looks like.swyx: Yeah.Ryan Lopopolo: And we give that to the root coding agent as it goes and does the thing. But you can also use that to distill tests out of, or a code review agent, which is pointed at the same things to narrow the acceptable universe of the code that's produced.swyx: I think one of the concerns I have with that kind of stuff is you think you're making the right call by making, it's persisted for all time across everything.Yes. But then you didn't think about the exceptions that you need to make, right? And that you have to roll it back.Vibhu: Part of it isswyx: also sometimes it can follow your s instructions too.Vibhu: It's somewhat a skill, right? So it determines when it uses the tools, right? Like it's not like it'll run outta every call.It'll determine when it wants to check quality score, right?Ryan Lopopolo: Yeah. And we do in the prompts we give these agents, allow them to push back,[00:13:51] Agent Code Review RulesRyan Lopopolo: When we first started adding code review agents to the pr, it would be Codex, CLI. Locally writes the change, pushes up a PR on [00:14:00] those PR synchronizations of review agent fires.It posts a comment. We instruct Codex that it has to at least acknowledge and respond to that feedback. And initially the Codex driving the code author was willing to be bullied by the PR reviewer, which meant you could end up in a situation where things were not converging. So yeah, we had to,swyx: he's just a thrash.Ryan Lopopolo: We had to add more optionality to the prompts on both of these things, right? The reviewer agents were instructed to bias toward merging the thing to not surface anything greater than a P two in priority. We didn't really define P two, but we gave it, youswyx: did define P two.Ryan Lopopolo: We gave it a framework within which to score its outputswyx: and then greater than P zero is worse, right?Yes. P two is very good.Ryan Lopopolo: P zero is you will mute the code place ifswyx: you merch thisRyan Lopopolo: thing, right?swyx: Yeah.Ryan Lopopolo: But also on the code authoring agent side, we also gave it the flexibility to either defer or push back against review feedback, right? This happens all the time, right? Like I happen to notice something and leave a code review, [00:15:00] which.Could blow up the scope by a factor of two. I usually don't mean for that to be addressed Exactly. In the moment. It's more of an FYI file it to the backlog, pick it up in the next fix it week sort of thing. And without the context that this is permissible, the coding agents are gonna bias toward what they do, which is following instructions.swyx: Yeah.[00:15:19] Autonomous Merging Flowswyx: I do wanted to check in on a couple things, right? Sure. All the coding review agent, it can merge autonomously. I think that's something that a lot of people aren't comfortable with. And you have a list here of how much agents do they do Product code and tests, CI configuration and release tooling, internal Devrel tools, documentation eval, harness review, comments, scripts that manage the repository itself, production dashboard definition files, like everything.Yes. And so they're just all churning at the same time, is there like a record that, that any human on the team pulls to stop everythingRyan Lopopolo: Because we are building a native application here. We're not doing continuous deploy. So there's still a human in the loop for cutting the release branch.I see. We require a blessed [00:16:00] human approved smoke test of the app before we promote it to distribution, these sort of things.swyx: So you're working on the app, you're not building like infrastructure where you have like nines of reliability, that kinda stuff?Ryan Lopopolo: That's correct. That's correct. Okay. And also like full recognition here that all of this activity took in a completely greenfield repository.There's. Should be no script that this applies generally toswyx: this is a production thing, you're gonna shipRyan Lopopolo: toswyx: customers. Of course. Yeah, of course. So this is realVibhu: And like one of the things there is, you mentioned you started this as a repo from scratch. The onboarding first month or so was pretty, it was like working backwards, right?Yeah. And then you had to work with the system and now you're at that point where you know, you're very autonomous. I'm curious like, okay, so what, how human in the loop is it? So what are the bottlenecks that you wish you could still automate? And part of that is also like, where do you see the model trajectory improving and offloading more human in the loop?We just got 5.4. It's a really good,Ryan Lopopolo: fantastic model, by the way.Vibhu: Yeah. Yeah. It's the first one that's merged. Top tier coding. So it's codex level coding and reasoning. So general reasoning both in one model. SoRyan Lopopolo: andVibhu: computer [00:17:00] use vision.Ryan Lopopolo: Now we now with five four, I can just have Codex write the blog post, whereas for this one I had to balance between chat.swyx: Oh, I need to, I might be out of a job. Oh my God.Ryan Lopopolo: Oh,swyx: I know. You just gave me an idea for a completely AI newsletter that five four could do. Yeah, I get it Now.Ryan Lopopolo: This sort of thing is just one example of closing the loop, right? Like the dashboard thing you mentioned. We have Codex authoring the Js ON, for the Grafana dashboards and publishing them and also responding to the pages, which means when it gets the page, it knows exactly which dashboards are defined and what alerts.What alert was triggered by which exact log in the code base. ‘cause all of this stuff is collated together.swyx: It has to own everything.Yes. Yeah. Yeah.Ryan Lopopolo: And it means that if we have an outage that did not result in a page. It has the existing set of dashboards available to it. It has the existing set of metrics and logs and can figure out where the gaps in the dashboard are or [00:18:00] in the underlying metrics and fix them in one go.In the same way, you would have a full stack engineer be able to drive a feature from the backend all the way to the front end.Vibhu: So it, it seems like a lot of the work you guys had to do was you as a small team are fully working for a way that the model wants the software to be written. It's like less human legible for better. Code legibility, agent legibility. How do you think that affects broader teams? So one at OpenAI, do liaison, like this is how software should be written. Like I can imagine, say you join a new team with this methodology, this mindset there's ways that, teams do code review, teams write code, like teams are structured and a lot of it is for human legibility.So should we all swap? Like how does this play back one broader into OpenAI and then like broader into the software engineering, right? Is it like teams that pick this up will it's pretty drastic, right? You have to make a pretty big switch. Should they just full send Yeah.Ryan Lopopolo: The mindset is very much that I'm removed from the process, right? I can't really have deep code level opinions about [00:19:00] things. It's as if I'm. Group tech leading a 500 person organization.Vibhu: Yeah.Ryan Lopopolo: Like it's not appropriate for me to be in the weeds on every pr. This is why that post merge code review thing is like a good analog here, right?Like I have some representative sample of the code as it is written, and I have to use that to infer what the teams are struggling with, where they could use help, where they're already moving quickly and I can pivot my focus elsewhere.Vibhu: Yeah.Ryan Lopopolo: So I don't really have too many opinions around the code as it is written.I do, however, have a command based class, which is used to have repeatable chunks of business logic that comes with tracing and metrics and observability for free. And the thing to focus on is not how that business logic is structured, but that it uses this primitive ‘cause I know that's gonna give leverage by default.Vibhu: Yeah.Ryan Lopopolo: Yeah, back to that sort of systems stinking,Vibhu: and you have part of that in your blog post, enforcing architecture and ta taste how you set boundaries for what's used. There's also a section on redefining [00:20:00] engineering and stuff, but yeah, it's just, it's interesting to hear,Ryan Lopopolo: and as the models have gotten better, they have gotten better at proposing these abstractions to unblock themselves, which again, lets me move higher and higher up the stack to look deeper into the future on what ultimately blocked the team from shipping.swyx: Yeah. You mentioned so you, this is primarily a, it is like a 1 million line of code base electron app. But it manages its own services as well, so it's like a backend for front end type thing.Ryan Lopopolo: We do have a backend in there, but that's hosted in the cloud.Yeah. This sort of structure is actually within the separate main and render processesWithin theswyx: electric.That's just how electronic works.Ryan Lopopolo: Yeah, of course. So have also treated like. MVC style decomposition with the same level of rigor, which has been very fun.swyx: I have a fun pun. This is a tangent, NVC is model view controller. Any sort of full stack web Devrel knows that.But my AI native version of this is Model view Claw, the clause the harness.Ryan Lopopolo: That's right. That's right. I do think that there is an interesting space to [00:21:00] explore here with Codex, the harness as part of building AI products, right? There's a ton of momentum around getting the models to be good at coding.We've seen big leaps in like the task complexity with each incremental model release where if you can figure out how to collapse a product that you're trying to build, a user journey that you're trying to solve into code, it's pretty natural to use the Codex Harness to solve that problem for you. It's done all the wiring and lets you just communicate and prompts to let the model cook.Yeah. It's been very fun. And there's also a very engineering legible way of increasing capabil. It's fantastic, right? Yeah. Just give you, just give the model scripts, the same scripts you would already build for yourself.swyx: Yeah.Yeah. So for listeners, this is Ryan saying that software engineering or coding against will eat knowledge work like the non-coding parts that you would normally think.Oh, you have to build a separate agent for it. No, start a coding agent and go out from there. Which open Claw has like it's pie Underhood.Ryan Lopopolo: [00:22:00] Yes.Vibhu: Basically define your task in code. Everything is a codingswyx: agent by the way. Since I brought it up, it's probably the only place we bring it up. Is any open claw usage from you?Any?Ryan Lopopolo: No. No. Not for me. I don't have any spare Mac Minis rattling around my house.swyx: You can afford it? No. I just, I'm curious if it's changed anything in opening eye yet, but it's probably early days. And then the other, the other thing I, I wanna pull on here is like you mentioned ticketing systems and you mentioned prs and I'm wondering if both those things have to go away or be reinvented for this kind of coding.So the git itself and is like very hostile to multi-agent.Ryan Lopopolo: Yeah. We make very heavy use of work trees.swyx: But like even then, like I just did a, dropped a podcast yesterday with Cursors saying, and they said they're getting rid of work trees ‘cause it still has too many merge conflicts.It's still un too un unintuitive. But go ahead.Ryan Lopopolo: The models are really great at resolving merge conflicts. Yeah. And to get to a state where I'm not synchronously in the loop in my terminal, I almost don't care that there are mergeswyx: with disposable.[00:23:00] Yeah.Ryan Lopopolo: We invoke a dollar land skill and that coaches codex to push the PR Wait for human and agent reviewers Wait for CI to be green.Fix the flakes if there are any merged upstream. If the PR comes into conflict, wait for everything to pass. Put it in the merge queue. Deal with flakes until it's in Maine. End. This is what it means to delegate fully, right? This is in a, very large model re probably a significant tax on humans to get PRS merged, but the agent is more than capable of doing this and I really don't have to think about it other than keep my laptop open.swyx: Yeah. I used to be much more of a control freak, but now I'm like, yeah, actually you could do a better job of this than me. Yeah. With the right context. Yes.[00:23:47] Encoding Requirementsswyx: Anything else in harness in general? Just this piece, I just wanna make sure we,Ryan Lopopolo: I think one thing that I maybe didn't make super clear in the article that I heard on Twitter as an interesting, that's respond [00:24:00]swyx: to them.What's the chatter and then what's your response?Ryan Lopopolo: Ultimately, all the things that we have encoded in docs and tests and review agents and all these things are ways to put all the non-functional requirements of building high scale, high quality, reliable software into a space that prompt injects the agent.We either write it down as docs, we add links where the error messages tell how to do the right thing. So the whole meta of the thing is to basically tease out of the heads of all the engineers on my team, what they think good looks like, what they would do by default, or what they would coach a new hire on the team to do to get things to merch.And that's why we pay attention to all the mistakes, mistakes that the agent makes, right? This is code being written that is misaligned with some as yet not written down, non-functional requirement.swyx: Sorry, what? Did the online people misunderstand orRyan Lopopolo: No,swyx: whatyouRyan Lopopolo: responded to? Somebody just literally said that.I was like, oh yeah,swyx: okay,Ryan Lopopolo: This is the [00:25:00] thing. This is what I've been doing. Oh, youswyx: agree? Yeah. I see. Interesting.Ryan Lopopolo: One other neat thing, which I did totally did not expect is folks were just. Taking the link to the article and giving it to pi or Codex and say, make my repo this,Vibhu: you achi a whole recursion.Ryan Lopopolo: And it was wildly effective. Really? It was wildly effective. NoVibhu: way. It just actually is something I tried with five, four yesterday. I didn't have time. Last time I was like out speaking of something, and this is one of my things, I was like, okay, I have this article. Can we just scaffold out what it would be like to run this?And I, I did it first as that and then I was like, okay, let me take another little side repo and say okay, if I was to fully automate this like this because I haven't written a line of code, it'sRyan Lopopolo: like over full, setVibhu: it right. The side thing I'm doing of voice. TTS I'm just like, slobbing out, whatever.It's nothing production. I'm like, how would I make this like this? And it's actually like a really good way. It's like a good way to learn what could be changed, what could be like, it's just a good analyzing, right? You give it all the codes, you give it all the context, you give it the article and it walks you through it very well.That's right. That's right.[00:25:57] Inlining Dependencies[00:25:57] Dependencies Going Away & Brett Taylor's Responseswyx: I guess one more thing before we go to Symphony is I wanted to cover [00:26:00] Brett Taylor's response. We had him on the show. He is your chairman, which is wild. Yeah. That he's reading your articles as well and like getting engaged in it. He says software dependencies are going away.Basically they can just be like vendored. Yes. Response.Ryan Lopopolo: Aswyx: hundred percent. A hundred percent agree. You still pro qr, you still pay Datadog. You still pay Temporal. Thank you.Ryan Lopopolo: Yep. The level of complexity of the dependencies that we can internalize is, I would say low, medium right now. Just based on model capability.What does the,swyx: what is medium?Ryan Lopopolo: I would say like a. A couple thousand line dependency is a thing that we could in-house No problem. Call in an afternoon of time. One neat thing about it is like probably most of that code you don't even need. Like by in-house and abstraction, you can strip away all the generic parts of it and only focus on what you need to enable the specific thing.Yes. You're building,swyx: I've been calling this the end of b******t plugins.Ryan Lopopolo: Yeah.swyx: Because there's so much when I published an open source thing, I want to accept everything, be liberal. I want to accept, this is post's law, but that means there's so much bloat. Yes. There's so much overhead.Ryan Lopopolo: One other neat thing about [00:27:00] this too is when we deploy Codex Security on the repo, it is able to deeply review and change. The internalized dependencies in a much lower friction way than it would be to like, push patches upstream, wait for them to be released, pull them down, make sure that's compatible with all the transitive I have in my repo and things like that.So it's also much lower friction to internalize some of these things if code is free. ‘cause the tokens are cheap sort of thing.swyx: Yeah. Yeah. I think like the only argument I have against this is basically scale testing, which obviously the larger pieces of software like Linux, MySQL, he calls up even the Datadog and Temporals and then maybe security testing where Yes.Classically, I think, is it linis tos, it said security open source is the best disinfectant.Ryan Lopopolo: Many eyes.swyx: Many eyes. And if inline your dependencies and code them up, you're gonna have to relearn mistakes from other people that Yep.Ryan Lopopolo: Yep. And to internalize that dependency, you're back to zero and you have to start.Reassembling all those bits and pieces to Yeah. Have [00:28:00] high confidence in the code as it is written. Yeah.Vibhu: Even part of the first intro of this, you basically mentioned like everything was written by codex, including internal tooling, right? So internal tooling, like when you're visualizing what's going on it's writing it for itself.swyx: Yeah. I'm built internal tools way I now, and like I just show them off and they're like, how long did you spend? And I didn't spend any time. I just prompted it,Ryan Lopopolo: very funny story here.swyx: Yeah, go ahead.Ryan Lopopolo: We had deployed our app to the first dozen users internally had some performance issues, so we asked them to export a trace for us get a tar ball, gave it to our on-call engineer, and he did a fantastic job of working with Codex to build this beautiful local Devrel tool, next JS app, the drag and drop the tar ball in, and it visualizes the entire trace.It's fantastic. Took an afternoon, but none of this was necessary. Because you could just spin up codex and give it the tar ball and ask the same thing and get the response immediately. So in a way, optimizing for human [00:29:00] legibility of that debugging process was wrong. It kept him in the loop unnecessarily when instead he could have just like Codex cooked for five minutes and gotten this same.swyx: Yeah, you verify your instincts here of this is how we used to do it. Or this is how I would have used to solve it.Ryan Lopopolo: Yeah. In this local observability stack. Like sure, you can de deploy Yeager to visualize the traces, but I wouldn't expect to be looking at the traces in the first place because I'm not gonna write the code to fix them.swyx: Yeah. So basically there needs to be like this kind of house stack and owning the whole loop. I think that is very well established. And it sounds like you might be like sharing more about that in the future, right?Ryan Lopopolo: Yeah. I think we're excited to do[00:29:36] Ghost Libraries Specs[00:29:36] Ghost Libraries & Distributing Software as SpecsRyan Lopopolo: We're gonna talk about Symphony in a little bit, but like the way we distribute it as a spec, which I think folks are calling Ghost Libraries on Twitter.This is like a such a cool name. It does mean it becomes much cheaper to share software with the world, right? You define a spec, how you could build your own specifying as much as is required for a coding agent to reassemble it [00:30:00] locally. The flow here is very cool. Like we have taken. All the scaffolding that has existed in our proprietary repo spun up a new one.Ask Codex with our repo as a reference. Write the spec. We tell it. Spin up a team ox spawn a disconnected codex to implement the spec. Wait for it to be done. Spawn another codex and another team ox to review the spec com or review the implementation compared to upstream and update the spec so it diverges less.And then you just loop over and over Ralph style until you get a spec that is with high fidelity able to reproduce the system as it is. It's fantastic.Vibhu: And you're basically, you're not really adding any of your human bias in there, right? That's correct. A lot of times people write a spec and be like, okay, I think it should be done this way, and you'll riff on something.And it's no, the agent could have just handled it like you're still scaffolding in a sense, right? I want it done this way. It can determine its spec better.swyx: That's right. That's right. Part of me it, I'm, I've been working a lot on evals recently, and part of me is wondering if [00:31:00] an agent can produce a spec that it cannot solve.Is it always capable of things that he can imagine or can you imagine things that it is impossible to do?Ryan Lopopolo: I think with Symphony, we, there's like this there's this axis where you have things that are easier, hard, or established or new, right? And I think things that are hard and new is still something that the models need humans.Yeah. Drive.swyx: Yeah. Yeah.Ryan Lopopolo: But I think those other quadrants are largely salt. Given the right scaffold and the right thing that's gonna drive the agent to completion,swyx: it's crazy that it solved,Ryan Lopopolo: but it means that the humans, the ones with limited time and attention get to work on the hardest stuff, like the problems where it's pure white space out in front. Or like the deepest refactorings where you don't know what the proper shape of the interfaces are. And this is where I wanna spend my time. ‘cause it lets me set up for the next level of scale.swyx: Yeah. Yeah. Amazing. Let's introduce Symphony.I think we've been mentioning it every now and then. Elixir. Interesting option.Ryan Lopopolo: Yeah.swyx: Yeah. I'm not,Ryan Lopopolo: again, like the [00:32:00] elixir manifestation here is just a derivative. Is it a modelswyx: chosen? Yeah.Ryan Lopopolo: Yeah. Yeah. And it chose that because the process supervision and the gen servers are super amenable to the type of process orchestration that we're doing here.You are essentially spinning up little Damons for every task that is in execution and driving it to completion, which. Means the mall gets a ton of stuff for free by using Elixir and the Beam.swyx: I had to go do a crash course in Beam and Elixir, and I think most people are not operating at that scale of concurrency where you need that.But it is a good mental model for Resum ability and all those things. And these are things I care about. But tell me the story, the origin story of Symphony. What do you use it for? Is this, how did it form maybe any abandoned paths that you didn't take?[00:32:46] Terminal Free Orchestration[00:32:46] Symphony: Removing Humans from the LoopRyan Lopopolo: At the end of December we were at about three and a half PRS per engineer per day.This was before five two came out in the beginning of January. Everyone gets back from holiday with five two and no other work [00:33:00] on the repository. We were up in the five to 10 PRS per day per engineer. And I don't know about y'all, but like it's very taxing to constantly be switching like that. Like I was pretty tapped out at the end of the day, again, where are the humans spending their time? They're spending their time context switching between all these active tmox pains to drive the agent forward.swyx: Yeah. No way. Yeah.Ryan Lopopolo: So let's again, build something to remove ourselves from the loop. And this is what frantic sprinted adapt here to find a way to remove the need for the human to sit in front of their terminal.So a lot of experimentation with Devrel boxes and, automatically spinning up agents, like it seems like a fantastic end state here, where my life is beach. I open live twice a day and say yes no to these things. Yeah. And this is again, a super, super interesting framing for how the work is done.Because I become more latency and sensitive. I have [00:34:00] way less attachment to the code as it is written. Like I've had close to zero investment in the actual authorship experience. So if it's garbage. I can just throw it away and not care too much about it. In Symphony, there's this like rework state where once the PR is proposed and it's escalated to the human for review, it should be a cheap review.It is either mergeable or it is not. And if it's not, you move it to rework. The elixir service will completely trash the entire work tree NPR and start it again from scratch. Okay. And this is that opportunity again to say, why was it trash right? What did the agent do that wasswyx: bad. Yeah.Ryan Lopopolo: Fix that before moving the ticket toswyx: endRyan Lopopolo: of progress again.swyx: Yeah. Why is this not in codex app? I guess this, you guys are ahead of Codex app,Ryan Lopopolo: yeah, so the way the team has been working is basically to be as AI pilled as possible and spread ahead. And a lot of the things we have worked on have fallen out [00:35:00] into a lot of the products that we have.Like we were in deep consultation with the Codex team to. Have the Codex app be a thing that exists, right? To have skills be a thing that Codex is able to use. So we didn't have to roll our own to put automations into the product. So all of our automatic refactoring agents didn't have to be these hand rolled control loops.It has been really fantastic to be, in a way, un anchored to the product development of Frontier and Codex and just very quickly try to figure out what works and then later find the scalable thing that can be deployed widely. It's been a very fun way to operate. It's certainly chaotic. I have lost track very often of what the actual state of the code looks like.‘cause I'm not in the loop. There was. One point where we had wired playwright directly up to the Electron app. With MCPM CCPs, I'm pretty bearish on because the harness forcibly injects all those tokens in the [00:36:00] context, and I don't really get a say over it. They mess with auto compaction. The agent can forget how to use the tool.There's probably only what three calls in playwright that I actually ever want to use. So I pay the cost for a ton of things. Somebody vibed a local Damon that boots playwright and exposes a tiny little shim CLI to drive it. And I had zero idea that this had occurred because to me, I run Codex and it's able to, it's oh, it's better.Yeah. Like no knowledge of this at all. Uhhuh.[00:36:30] Multi Human ChaosRyan Lopopolo: So we have had like in human space to spend a lot of time doing synchronous knowledge sharing. We have a daily standup that's 45 minutes long because we almost have to. Fan out the understanding of the current state.swyx: Yeah, I was gonna say this is good for a single human multi-agent, but multi human, multi-agent is a whole like po like explosion of stuff.Ryan Lopopolo: Yeah. And that this is fundamentally why we have such a rigid, like 10,000 [00:37:00] engineer level architecture in the app because we have to find ways to carve up the space so people are not trampling on each other.swyx: Sorry, I don't get the 10,000 thing. Did I miss that?Ryan Lopopolo: The structure of the repository is like 500 NPM packages.It's like architecture to the excess for what you would consider, I think normal for a seven person team. But if every person is actually like 10 to 50. Then the like numbers on being super, super deep into decomposition and sharding and like proper interface boundaries make a lot more sense.swyx: Yeah. To me, that's why I talked about Microfund ends and I, an anex is from that world, but Cool. It is just coming back to, to, to this I dunno if you have other, thoughts on. Orchestrating so much work coin going through this. Is this enough? Is this like any aha moments?Vibhu: It'll be interesting to see like where, okay, so right now you pick linear as your issue tracker, right?swyx: Or it's like a is it actually linear? This is actually linear.[00:37:55] Linear vs Slack WorkflowVibhu: Oh, that's linear. It's linear.swyx: Oh I never looked atVibhu: video. The demo video I had to download to [00:38:00] run.swyx: So I, because I'm a Slack maxie, but Yeah, linear. Linear is also really good. Yes,Ryan Lopopolo: we do make a good use of Slack. We we fire off codex to do all these lotion, elasticity, fix ups, the things that like sync that knowledge into the repository.It's super cheap. Yeah.swyx: Yeah.Ryan Lopopolo: Just do it in Codex.swyx: My biggest plug is OpenAI needs to build Slack. You need to own Slack. Build yours. Turn this into Slack.Ryan Lopopolo: I did read about it. Youswyx: did?Ryan Lopopolo: Yeah.[00:38:25] Collaboration Tools for AgentsRyan Lopopolo: I would say that if we think that we want these agents to do economically valuable work, which is like this is the mission, right?We want AI to be deployed widely, to do economically valuable work, then we need to find ways for them to naturally collaborate with humans, which means collaboration tooling, I think, is an interesting space to explore.swyx: Yeah, totally. Yeah. GitHub, slack, linear.Vibhu: Yeah, that was my thing. Okay, where do we see right now Codex has started Codex Model, then CLI, now there's an app, app can let me shoot off multiple Codex is in parallel, but there's no great team collaboration for Codex.And it [00:39:00] seems like your team had some say into what comes out, right? So you talked to ‘em, codex kind of was a thing. From there, if you guys are on the bound, what stuff that like, you might not focus on, but what do you expect other people to be building, right? So people that are like five x 50 Xing.Should you build stuff that's like very niche for your workflow, for your team? Should it be more general so other people can adopt? Is there a niche there? ‘Cause part of it is just okay, is everything just internal tooling? Do we have everything our own way? Like the way our team operates has our own ways that we like to communicate or is there a broader way to do it?Is it something like a issue tracker? Just thoughts if you wanna riff on that.[00:39:35] Standardizing Skills and CodeRyan Lopopolo: I think TBD we have not figured this out in a general way. I do think that there is leverage to be had in making the code and the processes as much the same as possible. If you think that code is context, code is prompts, it's better from the agent behavior perspective to be able to look in a package in directory X, Y, Z, and it not to have to page so [00:40:00] deeply into directory if you C, because they have the same structure, use the same language, they have the same patterns internally.And that same like leverage comes from aligning on a single set of skills that you're pouring every engineer's taste into to make sure that the agent is effective. So like in our code base, we have, I think, six skills. That's it. And if some part of the software development loop is not being covered, our first attempt is to encode it in one of the existing setup skills, which means that we can change the agent behavior.Yeah. More cheaply than changing the human driver behavior.swyx: Yeah.[00:40:39] Self Improvement via Logsswyx: Have you ever, have you experimented with agents changing their own behavior?Ryan Lopopolo: We do.swyx: Yeah. Or parent agent changing a subagents, behavior or something like that.Ryan Lopopolo: We have some bits for skill distillation. So for example, there's one neat thing you can do with Codex, which is just point it at its own session logs to ask it to tell you how you can use [00:41:00] the tool pedal better.swyx: It's like introspectionRyan Lopopolo: or ask it to do things. I useVibhu: this session better. What skills should Iswyx: high? I like the modification of, you can do, just do things to you can just ask agent to do things.Ryan Lopopolo: Yeah. You can just codex things. This is like a, this is like a silly emoji that we have, right? You can just codex things, you can just prompt things.It's really glorious future we live in, but okay, you can do that one-on-one. But we're actually slurping these up for the entire team into blob storage and. Running agent loops over them every day to figure out where as a team can we do better and how do we reflect that back into the repositories?Yes, though everybody benefits from everybody else's behavior for free. Same for like PR comments, right? These are all feedback. That means the code as written, deviated from what was good, a PR comment, a failed build. These are all signals that mean at some point the agent was missing context. We gotta figure out how toswyx: Yeah.Ryan Lopopolo: Slurp it up and put it back in the reboot.swyx: By the way, I do this exactly right. I used to, when I use cloud code for [00:42:00] knowledge work, cloud cowork is like a nice product, right? Yes. In I think you would agree. I always have it tell me what do I do better next time? And that's the meta programming reflection thing.So I almost think like you have six reflection extraction levels in symphony and almost like the zero of layer. So the six levels are PO policy, configuration, coordination, execution, integration, observability. We've talked about a couple of these, but the zero layer is like the, okay, are we working well?Can we improve how we work? Yes. Can I modify my own workflow without MD or something? I don't know.Ryan Lopopolo: Yeah, of course. Yeah, of course you can. Like this thing is also able to cut its own tickets ‘cause we give it full access.Yeah. Make it a ticket to have it cut. Tickets you can.Put in the ticket that you expect it to file as on follow up work,swyx: like Yeah. Self-modifying. Yeah.Ryan Lopopolo: Yeah.[00:42:44] Tool Access and CLI FirstRyan Lopopolo: Put, don't put the agent in a box. Give the agent full accessibility over it. Domain.swyx: I had a mental reaction when you said don't put the agent in a box. So I think you should put it in a box. Like it's just that you're giving the box everything it needs.Ryan Lopopolo: Yeah. Context and tools.swyx: But we're like, as developers, we're used to calling [00:43:00] out to different systems, but here you use the open source things like the Prometheus, whatever, and you run it locally so that you can have the full loop. I assume.Ryan Lopopolo: Yep.Vibhu: I think likeRyan Lopopolo: another, you wanna minimize cloud, cloud dependencies.Vibhu: You also want to make sure that you think about what the agent has access to. What does it see? Does it go back into the loop, like from the most basic sense of you let it see its own like calls, traces it can determine where it went wrong. But are you feeding that back in? So you know, just the most basic level of you wanna see exactly what's input output, like does the agent have access to.What is being outputted, right? It can self-improve a lot of these things. It's allRyan Lopopolo: text, right? My job is to figure out ways to funnel text from one agent to the other.swyx: It's so strange like way back at the start of this whole AI wave Andre was like, English is the hottest day programming language.It's here, it's just Yeah. The feature as well.Vibhu: A lot of, okay. Like a lot of software, a lot of stuff. There's a gui, it's made for the human. We're seeing the evolution of CLI for everything, right? All tools have CLIs. Your agents can use [00:44:00] them well, do we get good vision? Do we get good little sandboxes?Like right now? It's a really effective way, right? Models love to use tools. They love the best. They love to read through text. So slap a CLI let it go loose. That works for everything.Ryan Lopopolo: It does. Yeah. Yeah.[00:44:14] UI Perception and RasterizingRyan Lopopolo: We've also been adapting nont, textual things to that shape in order to improve model behavior in some ways, right?We want the agent to be able to see the UI agents do not perceive visually in the same way that we do. They don't see a red box, they see red box button, right? They see these things in latent space. So if we want, Hey, yeah, I do. We haveswyx: a ding if that goes off every time. Alien spaceRyan Lopopolo: ding.Anyway if we wanna actually make it see the layout, it's almost easier to rasterize that image to ask EOR and feed it in to the agent. Ha. And there's no reason you can't do both, right? To like further refine how the model perceives the object it's [00:45:00] manipulating.swyx: Cool. Could we, you wanna talk about a couple more of these layers that might bear more introspection or that you have personal passion for?[00:45:07] Coordination Layer with ElixirRyan Lopopolo: I will say that the coordination layer here was a really tricky piece to get right.swyx: Let's do it. Yep. I'm all about that. And this is Temporal core.Ryan Lopopolo: This is where when we turn the spec into Elixir, where like the model takes a shortcut, right? Like it's oh, I have all these primitives that I can make use of in this lovely runtime that has native process supervision.Which is I think, a neat way to have taken the spec and made it more choices achievable by making choices that naturally mapswyx: Yeah.Ryan Lopopolo: To the domain, right? In the same way that like you would prefer to have a TypeScript model repo if you are doing full stack web development, right? Because the ability to share types across the front end and backend reduces a lot of complexity.And becauseswyx: that's what graph kill used to be.Ryan Lopopolo: That's right. Andswyx: I don't know if it's still alive, butRyan Lopopolo: [00:46:00] no humans in the loop here. So like my own personal ability to write or not write elixir. Doesn't really have to bias us away from using the right tool for the job. It is just wild.swyx: Love it. I love it.Yeah. I wonder if any languages struggle more than others because of this? I feel like everyone has their own abstractions. That would make sense. But maybe it might be slower, it might be more faulty where like you'd have to just kick the server every now and then. I, I don't know. I think observability layer is really well understood.Integration layer, CP is dead. I think all these just like a really interesting hierarchy to travel up and down. It's common language for people working on the system to understandRyan Lopopolo: The policy stuff is really cool, right? Yeah. You don't really have to build a bunch of code to make sure the system wait for the, to passswyx: it's institutional knowledge.Ryan Lopopolo: Yeah. You just give it the G-H-C-L-I with some text that say CI has to pass. It makes the maintenance of these systems a lot easier.[00:46:57] Agent Friendly CLI Outputswyx: Do you think that CLI maintainers need to be [00:47:00] do anything special for agents or just as is? It's good because like I don't think when people made the G GitHub, CLI, they anticipated this happening.Ryan Lopopolo: That's correct. The GH CLI is fantastic. It's great super industry.swyx: Everyone go try GH repo create GH pull and then pull request number, right? GH HPR, like 1 53, whatever. And then it like pullsRyan Lopopolo: basically my only interaction with the GitHub web UI at this point is GH PR view dash web.Exactly. Glanceswyx: at the diffRyan Lopopolo: and be like Sure thing. Send it. Yeah. But the CLI are nice ‘cause they're super token efficient and they can be made more token efficient really easily. Like I'm sure you all have seen like I go to build Kite or Jenkins and I could just get this massive wall of build output.And in order to unblock the humans, your developer productivity team is almost certainly gonna write some code that parses the actual exception out of the build logs and sticks it in a sticky note at the top of the page. And you basically [00:48:00] want CLI to be structured in a similar way, right? You're gonna want to patch dash silent to prettier because the agent doesn't care that every file was already formatted.Just wants to know it's either formatted or not. So it can then go run a right command. Similarly, like in our PNPM distributed script runner, when we had one, when you do dash recursive, like it produces a absolute mountain of text. But all of that is for passing. Test suites. So we ended up wrapping all of this in another scriptswyx: to suppress the,Ryan Lopopolo: which you can vibe the channel only output the failing parts of the tests.swyx: You make a pipe errors versus the standard, standard out. I don't know. Okay. Whatever. Too much thinking have to do that. The CII used to maintain SCLI for my company and yeah, this is like core, very core to my heart. But you're vibing my job.Ryan Lopopolo: That's right.swyx: Cool. Any other things?This is a long spec. [00:49:00] I appreciate that. It's got a lot of strong opinions in here. Any other things that we should highlight? I think obviously you can spend the whole day going through some of these, but I do think that some of these have a lot of care or some of this you might wanna tell people, Hey, take this, but, make it your own.[00:49:15] Blueprint Spec and GuardrailsRyan Lopopolo: Fundamentally, software is made more flexible when it's able to adapt to the environment in which it is deployed, which means that things like linear or GitHub even are specified within the spec, but not required pieces of it. There's like a more platonic ideal of the thing that you could swap in like Jira or Bitbucket, for example.But being able to tightly specify things like the ID formats or how the Ralph Loop works for the individual agents. Basically means you can get up and running with a fully specified system quickly that you then evolve later on. I think we never intended for this to be a static spec that you can [00:50:00] never change.It's more like a blueprint to get something worth a starting point up and running.swyx: Yeah.Ryan Lopopolo: For you then to vibe later to your heart's content,swyx: you have like code and scripts in here where it's oh, I think this is a really good prompt. It's just a very long prompt.Ryan Lopopolo: Fundamentally, the agents are good at following instructions, so give them instructions.And it will, improve the reliability of the result. We, much like the way we use Symphony, we don't want folks to have to monitor the agent as it is vibing the system into existence. So being very opinionatedVery strict around what these success criteria are means that our deployment success rate goes up. Yeah. It means we don't have to get tickets on this thing.Vibhu: Think it all goes back to that like code to disposable, right? Like early on when you had CLI or you'd kick off a Codex run, it would take two hours. You would wanna monitor okay, I'm in the workflow of just using one.I don't want it to go down the wrong path. I'll cut it off and, just shoot off four, like that was my favorite thing of the Codex app, right? Yeah. Just Forex it like, [00:51:00] it's okay. One of them will probably be right, one of them might be better. Stop overthinking it. Like my first example was probably like deep research.When you put out deep research and I'd ask it something like, I asked it something about LLM, it thought it was legal something and spent an hour, came back with a report completely off the rails. And I was like, okay, I gotta monitor this thing a bit. No don't monitor it. Just you want to build it so it's that it, it goes the right way.And you don't wanna, you don't wanna sit there and babysit, right? You don't want to babysit your agentsRyan Lopopolo: with that deep research query that you made. Looking at the bad result, you probably figured out you needed to tweak your prompt Yeah. A bit, right? That's that guardrail that you fed back into the code base for the task, your prompt to further align the agent's execution.Same sort of concept supply there too.swyx: When you talk, how are the customers feelingRyan Lopopolo: for Symphony? I think we have none, right? This is a thing we have put out into theswyx: world. Symphony's internal, right? As long as you are happy, you are the customer. That'

The Drive played what the boss had to say about Royals fans who have custom Mahomes Royals jersey, and why he hates it.

Episode 382  James B and Eddie conclude 1998 and Volume 1 of many Spider-Man titles with a nine-book arc ending with Spider-Man quitting and the return of a beloved character. Sponsored by: BKLK Sports Network Theme Music by Jeff Kenniston.  This Episode Edited by James B using Audacity and Cleanfeed.  Summaries written by James B and Eddie and Mattie Franklin.  Most Sound effects and music generously provided royalty free by www.fesliyanstudios.com and https://www.zapsplat.com/  Check out all the episodes on letsreadspiderman.podbean.com or wherever you get your podcasts. Check out our live meetup and Discord Channel here https://docs.google.com/document/d/1_mW6htjJUHOzlViEvPQqR-k68tClMGAi85Bi_xrlV7w/edit