The Good Stuff

Yo joins from Sovereign Engineering to talk about how AI has transformed freedom tech development since SEC-04, when Paul demoed a wallet vibed into existence in 30 minutes and blew everyone's minds. The conversation covers the euphoria wearing off, the slot machine addiction problem, why LLMs are "extremely confident, extremely good at English usage, but extremely dumb," and the coming IPO exit liquidity dump. Uber burned their entire annual AI budget in four months and shipped nothing. Claude Code still has that terminal flicker bug from week two. Coding is not solved. But used as tools within their constraints? These things are genuinely great. FIPS, the peer-to-peer internet architecture routing to Nostr identities instead of IPs, was largely written by Claude, but every single line got human review. That's the model: Claude as a team member with specific jobs, not the entire dev team. YOLO++ kicks off July 20th.**Key Moments:**- [02:47] Paul's 30-minute wallet demo at SECO 4: "Everybody was blown away by this capability"- [04:14] "There's no hope if I am to come back to programming by hand. I'm not going to produce anything."- [07:11] Cryptography and AI: "It really, really fucks up. It always wants to do its own cryptography."- [08:13] "If you are a reasonably good programmer, you would always trust yourself more than you would trust the AI"- [10:59] The study where LLMs overtook a codebase: "Absolutely unrecognizable, unmaintainable without the LLM"- [12:52] "As far as Dario is concerned, coding is largely solved. I'm not a good programmer, but I don't see it solving my problems at all."- [23:25] "The euphoria is wearing off. The slot machine is just too addictive. People are tired."- [25:11] IPO bubble discussion: "It should be known by now that it's exit liquidity"- [27:35] 401k rule changes: waiting periods reduced from months to 15 days to force passive buying- [31:01] SECO 5 prediction: specialized local models for Git, bash, commits, PRs—"We didn't really get those, did we?"- [38:02] Uber's AI disaster: "Their year's budget, they finished in four months. What did we actually ship? Nothing."- [42:17] Claude Code terminal flicker: "After coding's been solved for nine months, they still haven't fixed it"- [48:57] FIPS written with Claude: "Every single line of code is getting reviewed. Claude is one of the members of the development team."- [55:21] FIPS architecture: Nostr identities convert to IPv6, devices identify and connect peer-to-peer- [59:10] Cross-pollination at cohorts: "Everybody on Wednesday is talking about their AI setup, their workflow"**Friends of the Pod:** Yo (guest), Paul (OG wallet demo), Gigi (pipeline workflow, phone recordings), Marty Malmi (laptop wanderer, Nostr VPN), Mitchell Hashimoto (spending money to figure out where AI works), Lighthazard (AI for examples, not library code), Jonathan (FIPS creator), Aryan (FIPS collaborator), PrimaGene (Claude Code flicker video), James Checkmatey (bubble commentary)**Projects Mentioned:** FIPS (peer-to-peer Nostr-addressed internet), Tollgate, Wingman (now on v4 with declarative workflow system), Zap Store**Quote:** "These LLMs are extremely confident, extremely good at English usage, but extremely dumb. They have a lot of information, but they don't know how to weigh that information, how to use that information, and what are the consequences of taking certain actions."

The Good Stuff, Episode 44: Is This the Death of Software?Pete and Andy revisit the death of SaaS thesis from episode one. and is it really playing out?**Key Moments:**- [00:40] Andy's hot take: everyone's having opinions on the death of software- [01:05] Callback to episode one: "Where does the value flow?" — they called this two years ago- [02:08] Client realization: "People could just build their own stuff, can't they?" - [02:54] The thesis: software development is now a commodity, value distributes- [03:55] "I've never talked to a Trello engineer. What's the chance they accidentally build something perfect for me?"- [05:04] The Claude Code catalyst: everyone suddenly noticed software is dying- [06:18] Lawyer holdouts still judging AI based on ChatGPT from two years ago- [07:35] The old model: harvest complexity, amortize across millions of users. "You don't need to do that anymore."- [11:11] "Is SaaS dead?" — Big SaaS is dead. Local SaaS is thriving.- [12:10] Rise of the farmer's market: your local dev shop is better than it's ever been- [17:23] Not one-man unicorns — "way more people being a one-man band making one to ten million dollar businesses"- [19:07] "You don't want to be a billionaire. You want to be a 21 millionaire."- [19:55] Sacks defending Salesforce: "A million patches therefore no one can build it" — completely missing the point- [20:22] "There's nothing hard about having a list of customers and a list of tasks, which is what it is."- [21:03] Excel analogy returns: Rolls-Royce ran on spreadsheets and macros before SAP- [25:05] Steel-manning big corp: trust, procurement, compliance gravitates to established vendors- [28:40] "Most people don't use it. They take opinions from people that don't use it."- [29:14] Swimming analogy: "It's hard to stay dry while learning to swim."- [35:02] Elite programmers saying they don't write code anymore — "both can't be true, guys"- [37:14] THE PARENTING ANALOGY: Getting a 10-year-old ready for running practice = prompt engineering- [39:45] "Quarter past five, we're leaving" = one-shotting. Breaking into tasks = prompt engineering.- [41:02] "This is how you explain to people how to work with AIs. It's going to hit so hard if they're parents."- [42:00] Set and setting: telling Claude it's an elite engineer "weirdly makes a difference"- [42:21] Andy throws in "great work, excellent" between tasks — performance management for models- [43:54] Research: getting aggressive makes AI nervous, hides mistakes, won't self-correct- [46:02] Overload problem: "Shit, this thing works so much quicker than me"- [48:03] Stream of consciousness mode for writing — removes the AI-isms- [50:06] "Everything will be software. It really will eat everything. It just won't be delivered by one set of people in Silicon Valley."- [50:38] Hot take: vibe coding is actually NET POSITIVE for cybersecurity- [51:03] "Information wants to be free. The most ridiculous thing you can do is put it all in one place."- [52:25] Much more software. Many more people will build it. More boutique businesses.- [52:49] The 21 millionaire era: "Deca millionaires"- [54:15] Marginal gains plug: "Like a business gym where I get leaner and stronger every month"- [55:22] "Like, comment, subscribe. We're not great at responding but we'll get better."- [56:06] Why they do the podcast: "50 hours of content on this subject that anybody can listen to and vet us"**Quote:** "It's like the rise of the farmer's market. People are going to go back to buying local. Your local person that you can talk to probably understands your problem better than the other person. It's so quick to resolve things that you're going to get a better service by someone that's closer to you."

In this episode, Anthony "DeadmanOz" returns as The Good Stuff's first ever repeat guest to discuss the rapidly evolving landscape of AI-assisted development and the critical importance of data sovereignty. The conversation explores how technical barriers are collapsing, making creative vision the primary requirement for building software. Pete unveils several new projects including SovThing (a Nostr-based file sync alternative) and SuperBased (an encrypted database infrastructure), demonstrating how cryptographic primitives can enable privacy-first applications. The trio dives deep into the challenges of onboarding non-technical users to key-based systems, the network effects building within the Nostr ecosystem, and why the future belongs to apps that respect their users. Anthony "DeadmanOz" shares his own journey building a family life organizer that prioritizes privacy, and the episode closes with reflections on the sustained creative flow states that modern AI tools enable.Sound Bites"The problem is all you need.""What if the internet didn't treat you like a p****""I should never have to see your data.""You can have sustained manic periods of building.""Building apps that respect you."Chapters00:00 Introduction and First Returning Guest01:57 K-pop Demon Hunters Update and Blender MCP03:47 The Cost of AI-Assisted Development05:26 Anthony's Thesis: Technical Skills Becoming Optional07:44 Domain Expertise Meets AI Tools11:02 Scaling Laws and the Data Collection Exercise19:09 SovThing: Nostr-Based File Syncing28:51 Opticon: Collaborative Visual Planning with Nostr33:03 SuperBased: Unruggable Database Infrastructure40:35 Encryption by Default and Data Sovereignty44:51 Key Teleport and Onboarding Normies49:06 Will People Ever Care About Privacy?57:45 The Vision for a Privacy-First Internet1:05:35 Anthony's Family Organizer Project1:17:02 The Irony of Building with Big Tech1:20:01 Sustained Manic Periods and Future OptimismKeywordsNostr, encryption, data sovereignty, SuperBased, SovThing, AI agents, vibe coding, privacy, cryptographic keys, peer-to-peer, local-first, NIP-98, Maple AI, domain expertise, file syncingTakeaways- Technical skills are rapidly becoming less necessary as AI tools mature - creativity and problem identification are becoming the primary requirements.- Domain experts who adopt AI coding tools early will have significant advantages in building bespoke solutions for their industries.- Nostr provides powerful primitives for identity, encryption, and discovery that enable privacy-first application architecture.- The future of software involves apps that never see user data- encryption by default with user-controlled keys.- Onboarding non-technical users to key-based systems requires hiding complexity behind familiar username/password interfaces.- Network effects within privacy-focused ecosystems compound over time as tools built on common standards interoperate seamlessly.- Companies making conscious decisions to trust big tech with their data are engaging in policy theater rather than genuine security.- Local-first applications with encrypted sync capabilities offer the best of both worlds - offline functionality with seamless backup.- The killer app for mass adoption of cryptographic keys may come from agent permissions - the need to give AI fine-grained access to personal data.- AI-assisted development creates ideal conditions for flow states - rapid progress on challenging problems without traditional roadblocks.

Episode 40: Building Digital Lemonade Stands with AIHosts: Pete and Andy (celebrating the big 4.0 at the beach)Episode 40! Pete launches his first digital lemonade stand with Ambulando—a habit tracker you pay for by the hour (4 sats). They explore what it means to build permissionless micro-businesses in cyberspace, why you should just build something (anything), and how their methodologies keep evolving between planning and iteration. Plus: the architect vs gardener approach, pluggable databases, and why Marginal Gains is going public.Key Moments:[00:57] 40 episodes without missing a week—including Christmas and New Year's Day[02:17] Digital Lemonade Stands: concept from Episode 22 with Gigi about permissionless cyberspace businesses[04:00] Ambulando launched: habit tracker with encryption, stores in cloud but can't see your data[05:20] Pay-per-hour pricing: 4 sats an hour, buy a day/week/21 days—fractions of cents[06:44] The beauty of digital lemonade stands: could be anything, ultra-low barrier to entry[07:26] What do we build? The prioritization question—answer: something, doesn't matter what[09:52] Using Nostr for identity and encryption, Bitcoin for permissionless payments[11:25] Marginal Gains evolution: started as Slack clone, became planning space for Wingman[13:30] The controller plane: task on Kanban has threads, whiteboard, context—then sends to Wingman[16:41] This has evolved dramatically based on how we actually work, not how we planned[17:30] Andy's two-instance approach: coding agent + planning/conversation agent in parallel[20:37] Third space problem: dump ideas in Miro/Obsidian but never look at them again[21:25] Stepping away from rigid documentation—more like tending a garden than following blueprints[23:30] Pendulum swing: from planning everything to live dictation, now back to solid plans[25:20] Claude comes to work drunk sometimes—you adjust your management style accordingly[28:36] Garden vs Architect: George RR Martin's two types of writers (still waiting for Winds of Winter)[33:35] Claude Co-Work concerns: YOLOing it onto your main computer gives it access to everything[36:24] Domain expertise unlock: people with specialized knowledge can now build their own tools[40:51] Recursive boards: every Kanban has a board, every task has a board, boards all the way down[46:59] Most AI is sold on laziness—instant gratification vs engaged iteration[49:53] Your job is to steer it: infinite space of what AI can build, you guide it to what you need[52:14] Friend of the pod invite code coming—special access inside Marginal Gains[53:12] Wingman should read transcripts and create tasks automatically[54:58] Look Marks: tag it anywhere, access it anywhere—not siloed bookmarks[57:00] Coming this year: pluggable databases and storage you control, used in SaaS appsQuote: "It's going to build whatever it wants to build if you just let it do that. But you don't have to let it do that. You can just steer it. You steer it over here, it's just going to build whatever you want to build."