Stanford's STORM research method runs a topic through five different expert perspectives instead of a single prompt, so the blind spots one angle misses get caught by another. I turned it into a free Claude skill that spins up a practitioner, academic, skeptic, economist, and historian, maps where they disagree, then verifies every source before handing you a clean HTML briefing. I also put it head to head against Claude Code's built-in Deep Research, and walk through exactly how to install it and tweak the lenses for your own work.

I ingested all my YouTube videos into an LLM wiki and turned them into a connected second brain that my AI OS can actually reason over. In this one I show you how to build the same thing in about five minutes using Claude Code and Obsidian, based on Andrej Karpathy's LLM knowledge base idea. You drop in sources, the AI reads them, splits them into cross-linked wiki pages, and keeps the whole thing organized with routing rules so it can find anything fast. By the end you'll know how to set up the vault, write the schema, ingest a PDF and a URL, and decide when to keep your wiki flat versus structured.

There are a lot of ways to make money with your AI skills. You could start your own agency, you might already run a business, or you might just want to level up at the job you already have. In this video I break down why the path you pick matters less than the skills underneath it and the way you go about using them. I cover why the tools keep changing but the real value sits with the person who can figure out what's actually worth building, the two roads into becoming an AI consultant, and a simple roadmap that works no matter which direction you're headed.

Claude Code just released auto mode, a new permission setting that sits between "ask before every edit" and "dangerously skip permissions." Instead of stopping your workflow every few seconds or giving Claude free rein to do anything, auto mode uses a classifier to check each action for risk before executing it. Safe actions run automatically, risky ones get flagged. In this video I break down how it works, test it with some real examples, and show you how to turn it on.

Fable 5 is back, and it's the strongest model I've used. It's also expensive and won't stay free on your Claude plan for long, so this video breaks down the six habits I'm using to get the most out of it without burning tokens. Everything from giving it the right context, to matching effort levels, to knowing when it quietly hands your task off to Opus.