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.

📎 SHARED RESOURCES RecapFlow Documentation Site (Patrick's automated meeting recap project) https://recapflow.patchoutech.com/ Assay AI (Ty's hallucination-reduction project) https://tryassay.ai OpenArt Suite (multi-model image and video generation) https://openart.ai/suite/home AI Engineer YouTube Channel (agentic systems, YC-equivalent content) https://www.youtube.com/@aiDotEngineer Nate Jones YouTube: Choosing Coding Models (highly recommended) https://www.youtube.com/watch?v=09sFAO7pklo Lenny's Podcast YouTube (how companies are reorganizing in the AI era) https://www.youtube.com/@LennysPodcast Karpathy AutoResearcher Post https://x.com/karpathy/status/2031135152349524125 Fine-Tuning Modalities Video from AI Engineer channel (rated 10/10, presented by OpenAI employee) https://youtu.be/JfaLQqfXqPA?si=7-dSakV1q98LNsvf Kimi Code (potential Claude Code supplement or review alternative) https://www.kimi.com/code/en CMUX Terminal (gives Claude Code genuine CLI-level terminal and browser control) https://www.cmux.dev/ Symphony by OpenAI (multi-agent coordination using Linear as task board) https://github.com/openai/symphony Claude Facial Expression Analysis via Claude Code (Matt Berman YouTube) https://www.youtube.com/watch?v=cHgCbDWejIs Fieldy AI (wearable ambient audio capture with webhook and N8N integration) https://www.fieldy.ai/ NVIDIA Startup Cloud Credits Program (up to $250K in Google Cloud credits for qualifying startups) — Paul offered to post the application form in the community forum. Watch for that post.