“The age of the idea guys has begun.”

• LLMs as a tool for thought by Amelia Wattenberger
• Micropayments and Mental Transaction Costs by Nick Szabo
• How our interfaces have lost their senses by Amelia Wattenberger

• The Art of Bitcoin Rhetoric by Bitstein

• Human Action by Ludwig von Mises
• Working in Public by Nadia Eghbal

• nak 
• Files
• SyncThing (and how it BitTorrent Sync became Resilio Sync) 
• Convention over configuration 
• Changes & speciation 
• File systems as sources of truth 
• Vibe-coding shower thoughts 
• Inspiration and The Muse 
• Justin's LLM setup 
• Tony's setup (o1-pro as the architect) 
• Being okay with paying for LLMs 
• Anthropomorphising LLMs
• Dialog, rubber-duck debugging, and the process of thinking 
• Being nice and mean to LLMs
• Battlebots & Gladiators
• Hedging your bets by being nice to Skynet
• Pascal's Wager for AI
• Thinking models vs non-thinking faster models
• Sandwich-style LLM prompting, again (waterfall stuff, HLDD / LLDD) 
• Cursor rules & Paul's Prompt Buddy 
• Giving lots of context vs giving specific context 
• The benefit of LLMs figuring out obscure bugs in minutes (instead of days) 
• The phase change of fast iteration and vibe coding 
• Idea level vs coding level 
• High-level vs low-level languages 
• Gigi's "vibeline" 
• Peterson's Logos vs Vervaeke's Dia-Logos 
• Entering into a conversation with technology 
• Introducing MCPs into your workflow
• How does Claude think? 
• How does it create a rhyme?
• How does thinking work? 
• And how does it relate to dialogue?
• Gzuuus' DVMCP & using nostr as an AI substrate
• Language Server Protocols (LSPs)
• VAAS: Vibe-coding as a service
• Open models vs proprietary models
• What Cursor got right
• What ChatGPT got right 
• What Google got right
• Tight integration of tools & remaining in a flow state
• LLMs as conversational partners
• The cost of context switching 
• Conversational flow & how to stay in it 
• Prompts VS diary entries 
• Solving technical vs philosophical models 
• Buying GPUs & training your own models 
• Training LLMs to understand Zig 
• Preventing entryism by writing no documentation 
• Thin layers & alignment layers 
• Working in public & thinking in public 
• Building a therapist / diary / notes / idea / task system
• "The age of the idea guys has begun."
• Daemons and spirits 
• Monological VS dialogical thinking 
• Yes-men and disagreeable LLMs 
• Energy cost vs human cost 
• Paying by the meter vs paying a subscription 
• The equivalence of storage and compute 
• Thinking needs memory, and memory is about the future 
• Nostr+ecash as the perfect AI+human substrate 
• Real cost, real consequence, and Human Action 
• The cost of words & speaking 
• Costly signals and free markets 
• From shitcoin tokens to LLM tokens to ecash tokens 
• Being too close to the metal & not seeing the forest for the trees 
• Power users vs engineers 
• Participatory knowing and actually using the tools 
• Nostr as the germination ground for ecash 
• What is Sovereign Engineering? 
• LLVM and the other side of the bell-curve 
• How nostr gives you users, discovery, mircopayments, a backend, and many other things for free 
• Echo chambers & virality 
• Authenticity & Realness 
• Growing on the edges, catering to the fringe 
• You don't own your iPhone 
• GrapheneOS 
• WebRTC and other monolithic "open" standards 
• Optimizing for the wrong thing 
• Building a nostr phone & Gigi's dream flow 
• Using nostr to sync dotfile setups and other things 
• "There are no solutions, only trade-offs" 
• Cross-platform development 
• Native vs non-native implementations
• Vitor's point on what we mean by native 
• Does your custom UI framework work for blind people? 
• Ladybird browser & how to build a browser from scratch 
• TempleOS 
• Form follows function & 90's interfaces 
• Lamentations on the state of modern browsers 
• Complexity & the downfall of the Legacy Web 
• Nostr as the "new internet" 
• Talks by Ladybird developer Andreas Kling
• Will's attempt of building it from scratch with Notedeck & nostr-db
• Justin's attempt with rust-multiplatform 
• "If it doesn't have a rust implementation, you shouldn't use it."
• Native in terms of speed vs native in terms of UI/UX 
• Engineer the logic, vibe-code the UI 
• From Excalidraw to app in minutes 
• What can you one-shot? 
• What do you need to care about? 
• Pablo's NDK snippets 
• 7GUIs and GUI benchmarks for LLMs
• "Now we're purpose-building tools to make it easier for LLMs" 
• "Certain tools really make your problems go away."
• Macros and meta-programming 
• Zig's comptime 
• UNIX tools and pipes 
• Simple tools & composability
• Nostr tools for iOS & sharing developer signing keys 
• Building 10 apps as one guy 
• Simplicity in a community context 
• Most people are on phones 
• Most people don't install PWAs 
• Zapstore & building our own distribution channels
• Web-of-trust and pushing builds quickly 
• Improving homebrew by 10x 
• (Micro)payments for package managers 
• Guix and bitcoin-core 
• Nix vs Guix 
• Reproducible builds & web-of-trust 
• Keet vs "calling an npub" 
• Getting into someone's notifications 
• Removing the character limit was a mistake