Last week Brandon burned through $120 in Claude credits in 30 minutes while proving the "SaaSpocalypse" is real—rebuilding a $20 SaaS in under an hour and making everyone panic about their lack of moats. If you missed the chaos, you missed the survival guide for what happens when AI makes code trivial to replicate. 📞 HOW THE CALLS WORK The calls can run 2+ hours. We want to make sure we're respecting everyone's time. Especially those of you who actually show up. Here's the structure: 👉 Reply to this post with your questions before the call 👉 If you submit a question and you're on the call, you go first 👉 We work through questions in the order they came in 👉 Then we open it up for everyone else If you can't make the call but want your question answered, drop it in the comments. We'll get to it. But priority goes to people who are there. The goal is simple: if you're taking the time to show up, you shouldn't have to wait behind questions from people who aren't even on the call. We've got some delicious follow-ups brewing: Ty is running his ShipSafe security scanner against Morgan's catio site (cybersecurity meets cat patios), Patrick is polishing that elegant multi-model pipeline for open source release, and Tiran is stripping his landing page down to a single address input. Perfect time to jump back in if you want to see how the experiments land. 🔗 ZOOM LINK (save this) https://us06web.zoom.us/j/81995207847?pwd=Xe6u6LmIQOmCP5VTnOwWYjDBfZNKGB.1 📅 WHEN Tuesday April 28th at 6PM ET Looking forward to seeing you on the call!

https://www.youtube.com/watch?v=eBRzdfU-K30

📝 SUMMARY A dense, high-signal call covering self-improving AI pipelines, governance-first agent architecture, Stripe best practices, biometric authentication, and mobile ideation workflows. The strongest through-line: the shift from using AI interactively to building systems that run autonomously — defining quality rubrics, letting agents evaluate and improve their own outputs, and removing the human from the loop wherever possible. Practical tool recommendations (CMux, Codex for autonomous tasks, Terraform for infrastructure, Discord over Telegram for agent memory) were grounded in real production experience. The IronClaw white paper, Ty's FaceGate SDK demo, and Patrick's RecapFlow auto-research experiment are the most concrete follow-ups to watch for in the coming week. 💡 KEY INSIGHTS Self-Improving AI Pipelines — The Most Actionable Framework Shared This Call Build systems that eliminate the human from the evaluation loop. Define explicit pass/fail criteria and a point-based rubric, build a representative input suite (e.g., 60 test cases), let the AI run experiments, grade its own outputs, identify failure modes, update its own system prompt, and iterate. Apply this at the individual pipeline step level first, then at the full system level. Brandon uses Codex for this because it runs autonomously for long periods without prompting for human confirmation. Expensive but produces measurable, compounding improvement. The Hardest Part Is Defining "Good" For mathematical outputs, scoring is straightforward. For language outputs, defining quality is the core challenge. Patrick's approach: use mechanical checks (did all URLs get extracted? is compression within bounds?) for the fast inner loop, and community feedback as the slow outer loop for subjective quality. Governance Before Features for AI Agents Prioritize governance before adding capabilities. Recommended architecture: read-only access to most systems, human-in-the-loop via Discord or Telegram for any state-changing action, full audit trail, and a smart router using local models (Ollama) for routine tasks and frontier models only for complex ones. This is the core principle behind the IronClaw framework.

Has anyone been trying the New Composer 2 model in Cursor? Whats your impressions?

Goldmind here folks...at the vanguard of the LLM space, with a scientific and materialist approach, Ted Kyi (LinkedIn: https://www.linkedin.com/in/tedkyi/) is producing his book that allows us to understand LLM inferences in a comprehensitve yet understandable manner. Please take a look at this work in production: https://tedkyi.github.io/llm-inference/ The next meetup will be: https://www.meetup.com/san-diego-machine-learning/events/313891387/?eventOrigin=group_upcoming_events Since I live in San Diego, I can attend in Person, but the meeting is Zoom hybrid! He is sharing this book and giving a lecture on it for free! This is no trifling Ted Talk, this is the real Ted LLM Talk.