No slides, no hype. I teach by building live on YouTube and X: AI agents, local models, and AI workflows, mistakes included. Join live and ask questions in chat, catch the replays on YouTube, and follow on X for the latest AI updates.
people trained through talks, workshops, and mentoring
2.2k+
GitHub stars on the open-source tools I teach with
25+
years shipping software, the context behind every video
Workshops & talks
Bring an AI workshop to your school or organization.
The same way I teach on the livestreams, run for your students, faculty, or team: hands-on sessions on AI Agents, Local Models, and AI Workflows, in plain language. Online via Zoom, with on-site options on request.
Anthropic opened (Oct 21) a research preview of Claude Duet, a standalone app on iOS, Android, and claude.ai where Claude works as a proactive agent. It runs on Claude Opus 5.5, sends a short morning brief from connected apps, checks those apps every few hours, and keeps working in its own virtual machine and browser after the person steps away. Before it sends a message, makes a payment, signs a document, or deletes anything, it shows the action and waits for approval. Trading securities and moving money between accounts stay off-limits even with approval. Anthropic says it can use more than 6,000 Claude Marketplace connectors, including Gmail, Slack, QuickBooks, Stripe, Gusto, Docusign, and Shopify, and that credentials follow the Claude Managed Agents design so the agent does not directly see passwords or sign-in tokens. A new classifier is meant to block leaks of the strictest data, such as credit card numbers and government IDs. The preview is a US waitlist for Pro and Max subscribers, shares those plans’ usage limits (background checks count), and is not on Team or Enterprise yet. Anthropic says it can misread a thread or misjudge what is urgent, and it cannot yet show its browser. Distinct from Claude Code, Claude Managed Agents, and Meta’s Muse personal agent.
NVIDIA said (Oct 21) Google Cloud A5X instances, built on Vera Rubin NVL72 with ConnectX-9 SuperNICs, the Virgo network, and Google’s fourth-generation liquid cooling, are scheduled for general availability next month, with a planned expansion in Europe. Google Cloud plans to scale that Vera Rubin infrastructure to as many as 960,000 Rubin GPUs across multiple sites. Ineffable Intelligence, founded by AlphaGo creator David Silver, was the first customer to access A5X for large-scale reinforcement learning. WPP demonstrated creative agents on A5X using Nemotron models and OpenShell; NVIDIA says workloads that usually needed a multi-node cluster ran on a single A5X instance in WPP’s initial tests. The same post says Google Cloud will be among the first providers to offer NVIDIA Confidential Computing at rack scale on bare-metal systems such as A4X Max with GB300 NVL72, and that Confidential Computing is generally available on G4 VMs with RTX PRO 6000 Blackwell Server Edition GPUs. Scale and performance notes are NVIDIA’s. Distinct from the Oct 12 Open Compute Project Vera Rubin design contribution and from the same-day OpenShell reference architecture.
TechCrunch reported from Meta’s Oct 21 third-quarter earnings call that Mark Zuckerberg said the Muse personal-agent app has been adopted by more than 10 million users, and that about 25% of people who set up Muse use it daily. He said shopping through the agent is a leading use, with an average purchase size over $200. Zuckerberg said Meta expects to improve Muse’s compute cost efficiency by more than 10× over the next year, is building capacity to serve more than a billion people, and plans to keep Muse free for most users while taking a percentage of commerce on the platform. People who want the most advanced models or more tokens would pay. These figures are as reported from the call, not from Meta’s earnings press release. Distinct from the September Muse personal-agent launch and from the Muse Spark and Muse Wonder model releases.
Source: TechCrunch
Updated October 22, 2026
What I teach: AI Agents, Local Models & AI Workflows
AI Agents
Autonomous agents with memory, tools, and skills that do the work, not just chat about it.
I teach AI Agents, Local Models, and AI Workflows to people who want to use AI, not just read about it. Before the channel: senior engineering roles at Standard Chartered Bank and Ohmyhome (Nasdaq), then a run of AI products built and shipped end to end. That's why every video, talk, and post is grounded in what actually ships.
Livestreams AI builds on YouTube and X
Speaker at NTU Singapore, PSIA, and DICT Philippines
300+ trained through workshops and mentoring
Open-source maintainer: Codex orchestrator, Local Evals, Agent Monitor
Subscribe on YouTube for the next livestream and follow on X for the latest AI updates. Want a workshop for your school or organization, or help with a product? Book a call.
