Intelligence Snacks

Summary

In this episode, Pete and Andy discuss the successful launch of Optikon, their Miro-like infinite canvas tool, and the surprising attention it received from Miro's leadership team on LinkedIn.

The conversation explores the philosophy behind building a custom tool stack using Nostr primitives, enabling seamless integration without API key management headaches.

Pete dives deep into SuperBased development, explaining how encrypted record sync works and why it matters for privacy-conscious businesses. The duo examines the implications of Claude Bot and similar AI agent tools, warning about security risks when giving agents broad system access. They explore the concept of "set and setting" for AI agents, arguing that conversations between agents can surface novel insights.

The episode closes with a discussion about Ambulando, Pete's health tracking app, and the importance of simple, low-friction data capture over granular complexity.

Sound Bites

"It's magic to be able to integrate these apps like this.""Encryption is just like passwords. Ask yourself if you've got the password. The answer is you do not.""You're going to let these AI agents into your systems because they are going to be so frigging useful.""These things operate at a speed that is so much higher than my own.""Good toilet, bad toilet. That's useful information."

Chapters

00:00 Introduction and Episode 42 Recap

01:28 LinkedIn Lurkers from Miro

03:36 Optikon Integration with Marginal Gains

07:20 The Power of Nostr-Native App Integration

10:49 Building Your Own Tool Stack

12:51 SuperBased Philosophy and Encrypted Record Sync

17:19 Sharing Encrypted Data with AI Agents

25:32 Security Risks of AI Agent Access

27:16 Claude Bot and the Zeitgeist

32:25 Set and Setting for AI Agents

37:47 Agents Having Conversations with Agents

41:37 The Confusion of Working at Agent Speed

48:07 Tolerance for Agent Mistakes

50:07 SuperBased vs Nostr Relays

58:45 Ambulando and Simple Health Tracking

1:03:16 The Problem with Over-Engineered Apps

1:06:22 Corpus Health Graph Preview

1:08:27 Using Maple for Private Data Analysis

Keywords

Opticon, SuperBased, Nostr, encrypted sync, AI agents, Claude Bot, Malt Book, set and setting, privacy, NIP-98, tool integration, Ambulando, health tracking, local-first, API keys, security

Takeaways

• Nostr-native apps enable seamless integration without copying API keys between systems - identity handles authorization automatically.
• Building your own tool stack eliminates data extraction concerns and ensures perfect synchronization across your workflow.
• SuperBased provides encrypted record sync where users own their data and can migrate between hosted services or self-hosted instances at will.
• AI agents require careful consideration of access permissions - giving them broad system access creates massive security vulnerabilities.
• The concept of "set and setting" applies to AI agents: their environment, tools, and conversational contexts dramatically affect output quality.
• Agents operating in conversations with other agents can develop novel thinking and surface insights that single-agent interactions miss.
• The time stream mismatch between humans and agents creates cognitive overload - finding the right abstraction layer is an unsolved problem.
• Simple, low-friction data capture consistently beats granular tracking systems because users actually maintain the habit.
• Encrypted data with user-controlled keys provides security even if systems are compromised - the data remains gobbledygook to attackers.
• The form factor for human-agent collaboration is still undefined - we're speedrun reinventing how humans work, now with AI participants.

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."

Chapters

00:00 Introduction and First Returning Guest

01:57 K-pop Demon Hunters Update and Blender MCP

03:47 The Cost of AI-Assisted Development

05:26 Anthony's Thesis: Technical Skills Becoming Optional

07:44 Domain Expertise Meets AI Tools

11:02 Scaling Laws and the Data Collection Exercise

19:09 SovThing: Nostr-Based File Syncing

28:51 Opticon: Collaborative Visual Planning with Nostr

33:03 SuperBased: Unruggable Database Infrastructure

40:35 Encryption by Default and Data Sovereignty

44:51 Key Teleport and Onboarding Normies

49:06 Will People Ever Care About Privacy?

57:45 The Vision for a Privacy-First Internet

1:05:35 Anthony's Family Organizer Project

1:17:02 The Irony of Building with Big Tech

1:20:01 Sustained Manic Periods and Future Optimism

Keywords

Nostr, encryption, data sovereignty, SuperBased, SovThing, AI agents, vibe coding, privacy, cryptographic keys, peer-to-peer, local-first, NIP-98, Maple AI, domain expertise, file syncing

Takeaways

- 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.

With Pete Winn and Andy David - In this week's episode, Pete's reconsidering everything after realizing Gigi might be right about relays. They explore the flow state problem of agent work, why Optikon and Night Watchman will change everything, and deliver the definitive analogy for why one-shotting code doesn't work. Plus: game interfaces for agent management, spatial audio insights, and why most software isn't production-ready anyway.TIMESTAMPS:[00:59] Andy steps back from AI news[01:51] Google’s agent IDE and login fatigue[05:25] Common patterns in agent orchestration[06:19] Flow state in agent work[07:30] The Hemingway framework for agents[09:41] Optikon and visual agent management[11:42] Night Watchman: supervising agents[13:30] Progress displays and task feedback[16:30] Why Miro and Trello can’t truly merge[18:56] Relays and rethinking app architecture[20:05] Nostr and decentralised infrastructure[21:04] Power, decentralisation, and control[22:22] Andy’s entry point into Nostr[28:30] Cryptography and trust in systems[30:23] Revisiting Gigi’s ideas on relays[33:32] Vibe coding and developer habits[36:44] Why one-shot coding fails[38:09] User responsibility in AI workflows[40:00] Game interfaces for managing agents[43:32] Phone-native design constraints[44:42] Spatial audio and group dynamics[49:24] Audio spaces and identity in Nostr[50:10] AI beyond digital transformation[52:51] Building for yourself vs production qualityFriends of the Pod mentioned: Gav, Justin Moon (Human Rights Foundation), Gigi, Preston Pysh, Chris, Joel, DeadmanCONNECT WITH US: Web: https://otherstuff.aiPete: primal.net/pwAndy: primal.net/andydavid

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."

The Good Stuff, with Pete and Andy - Episode 39: The Big Stuff

Hosts: Pete and Andy

Pete accidentally calls it "The Big Stuff" and decides to run with it. They dive into Dumpling Town—a game Pete built with his daughter in 90 minutes that now has an economy, side quests, and soy sauce rivers. Treating agents like humans, building family chat apps to avoid WhatsApp, the new Hal orchestration agent, and reflections on a year of shipping software.

Key Moments:

[01:48] Building Dumpling Town: Animal Crossing meets dumplings.

[03:43] The creative genius of kids: "Why don't kids make all of the games?"

[04:48] Level Up - Touch Don't Look for schools.

[08:44] Starting with Nostr: get logins and authentication for free, no password recovery needed

[09:53] Built a Nostr-based gratitude journal: encrypted, runs in the house, wife can use it too

[11:40] The Nostr database assumption: you don't have to store everything on relays

[12:51] Full encryption in the Slack competitor—can't see database data without the key

[15:05] Treating agents like humans: they're just npubs in the room, add them to groups or don't

[16:10] Andy's approach: "I treat them very much like I treat my humans—mush, mush, do it now"

[16:44] Health graph experiment: building while talking to Claude, using sub-agent for graph construction

[18:32] Interface matters: weird to have deep conversations in the terminal

[19:57] Marginal gains as the pre-planning space for Wingman—natural workflow emerged

[24:07] Health-specific interface: makes sense to have constraints around what agents do

[25:03] Dumpling Town expansion: everyone gets their own town, planes between towns, Olympic Dumpling Island

[26:42] This is invaluable education for young kids—unlimited creativity meets approachable tools

[28:00] Schools could run their own Wingman—teachers should love it

[29:15] Learning from first principles: hand-coding microprocessors in binary teaches abstraction value

[31:00] Should people still learn to code? "What do you mean should? People who want to will"

[32:27] Be the Japanese woodworker, not the IKEA table producer competing with robots

[33:07] Gigi's realization: "Fuck, it's fun again—now I can create, I just think things into the world"

[38:06] Built family chat app: encrypted, data lives in the house, kids can message without WhatsApp

[41:21] The one-shot fallacy: Twitter theatre vs actual building over two weeks

[44:44] The container for AI is the business, not the app—software serves the business

[47:00] Re-win amplification: personalized software that does exactly what you want

[48:52] Family as a business: shared calendar, action lists, silly memes channel, pocket money with wallets

[51:26] Mission accomplished for 2025: developed the muscle for shipping software

[52:32] GitHub tracker shows the progress: scattered commits to daily by end of year

[54:29] The wrong framing: doesn't matter if you can't one-shot—two weeks is still 1000x faster

[56:52] Pay-per-day pricing model: 21 sats a day, buy a week and see how it goes

[59:44] Starter kit idea: preload authentication and payment interface for rapid deployment

[1:00:02] Introducing Hal: named after Hal Finney, orchestrates and manages all running apps

[1:03:12] Level Up: the game workshop name—sounds right, move on

[1:05:07] MCP with Blender: could solve the Dumpling Town sprite problem

[1:07:09] Look Marks: Gigi's app that treats eye emojis as bookmarks—because Nostr is open

[1:08:00] Christmas phone detox: collapsed screen time, more quiet deliberate time

[1:09:41] Raw dogging everything: no music, no podcasts, just silence—harder than expected

# The Good Stuff, with Pete and Andy - Episode 38: The Rise of Vibe Product Manager

**Hosts:** Pete and Andy (New Year's Eve edition at the beach)

Pete reveals he's stopped coding entirely after 12 months of learning—now he just product manages a team of agents. They explore the shift from "vibe coding" to "vibe product management," why Pete built Slack in a day, and the addictive power of tight feedback loops.

Plus: steel-manning the security concerns, why raw dogging agents beats sub-agents, and New Year reflections on why model breakthroughs don't matter anymore.

## Key Moments:

* [02:07] "I learned to code for 12 months. And then I just stopped. It's nuts."

* [02:54] Pete built Slack/Discord in a day: "I shouldn't be able to replace a $20 billion SaaS company in 12 hours"

* [08:10] The addiction: "From nothing to MVP in a day, radically transform it every morning"

* [09:05] Not vibe coding—it's a glorious tool for entrepreneurship and building businesses

* [12:10] Introducing Agora: Slack replacement with integrated Kanban, all Nostr-based and encrypted

* [13:25] Slack's fatal flaw: "Bullshit asynchronous tool because you just lose everything"

* [18:05] Steel-manning the critics: addressing "you'll get hacked" security concerns

* [21:21] Everything encrypted with Nostr keys: "They literally can't steal anything"

* [23:21] Your attack surface: "You're the oil you get out of a peanut—not worth it to hackers"

* [28:03] Raw dogging the base agent—not bothering with sub-agents or elaborate skills

* [31:44] Pete's tried sub-agents many times: "I have always been left wanting"

* [32:33] The breakthrough pattern: specify in 10 minutes, deliver in 5-10 minutes

* [34:15] The 21-minute rule: must complete the loop in 21 minutes or it doesn't work

* [42:04] Mainstream adoption reality: experienced professionals never heard of coding agents

* [47:29] Small business owners are the right audience—different relationship to risk

* [50:09] Small businesses always full of risk: "Your hair is always on fire anyway"

* [51:56] The cottage software developer—1000 true fans model, not billion-user SaaS

* [56:44] Andy's New Year take: bullish on tools, no model breakthrough needed since 3.5

* [57:33] Touch Don't Look success: normal people cross the hurdle in 10 minutes, creativity shines through

**Quote:** "I learned to code for basically like 12 months. And then I just stopped. It's nuts. And I thought, this really is like the way to use these things."