Claude Opus 4.6, Codex 5.3, and the Rise of Multi-Agent AI скачать в хорошем качестве

Claude Opus 4.6, Codex 5.3, and the Rise of Multi-Agent AI

The biggest shift in AI isn’t a new model. It’s agents managing other agents. In Episode 30 of Built This Week, Sam Nadler and Jordan Metzner break down how they’re actually using the latest AI releases — including Claude Opus 4.6 and OpenAI Codex 5.3 — to build real software inside their own workflows. Jordan walks through a private, fully local AI system built with Claude Code that turns raw 23andMe data, blood work, medications, and personal health inputs into a unified health dashboard. The goal isn’t diagnostics — it’s creating a long-term, living record that surfaces insights doctors don’t easily connect. Sam then demos an AI-powered personal trainer built using the new Codex desktop Mac app and high-reasoning models. The system adapts workouts rep-by-rep, adjusts volume in real time, and highlights the tradeoffs between fast iteration tools and slower, deeper reasoning workflows. We close with the biggest AI platform launches of the week: Anthropic’s Opus 4.6 and Agent Teams OpenAI Frontier and enterprise AI coworkers Perplexity’s Council Mode and LLM swarms The era of one chatbot at a time is over. The new skill is learning how to manage AI agents that manage other agents. No hype. No abstractions. Just what actually happens when builders use AI on themselves first. New episodes every Friday. TIMESTAMPS (0:00) The shift from single-agent AI to multi-agent systems (0:21) Welcome to Built This Week Episode 30 (1:00) Agenda and why this week matters (1:38) Why Jordan downloaded his 23andMe data (2:30) Turning unreadable DNA files into usable insights (3:50) Combining genetics, blood work, and medications (5:05) Drug response insights and hereditary signals (6:10) Generating doctor-ready reports for family (7:20) Why this system runs fully local (8:00) Building personal software instead of buying tools (8:40) Sam’s AI personal trainer built with Codex (9:50) Rep-by-rep workout feedback and fatigue detection (10:45) Designing AI interfaces for real-world use (11:40) Codex vs Claude Code: speed vs deep reasoning (12:20) Anthropic Opus 4.6 and Agent Teams (13:00) OpenAI Frontier and AI coworkers (13:25) Perplexity Council Mode and model swarms (14:05) Why multi-agent management is the real inflection (15:15) Becoming a manager of AI managers (16:00) How many agents one human can manage (17:00) AI’s impact on legacy software companies (18:15) Episode 30 wrap-up and what’s next LINKS Built This Week New episodes every Friday https://builtthisweek.com Jordan Metzner https://x.com/mrjmetz Sam Nadler https://x.com/Gravino05