Claude Code just launched routines, which let you run prompts on a schedule from Anthropic's cloud without keeping your laptop open. In this video I walk through exactly how to set them up, the gotchas I ran into migrating my automations, and how to configure your API keys, cloud environments, and permissions so everything actually works on the first try.

Seedance 2.0 just dropped and it's a game changer for web design. In this video I show you how to use it to generate looping background videos, then feed those into Claude Code to build a full, modern website from scratch. You'll see the whole workflow from image generation to video prompting to deploying a live site with GitHub and Vercel. No design experience or production budget needed.

Anthropic just released the advisor strategy, and it's a big deal for anyone building with Claude. Instead of running every task through Opus, you can pair it as an advisor with a cheaper model like Sonnet or Haiku doing the actual work. In this video I built a dashboard to test how it performs across easy, medium, and hard prompts, and I also show you how to use the same idea inside Claude Code with opus plan mode to stretch your session limit further. GITHUB REPO

Can AI actually trade better than a human? In this video, I tried OpenClaw for 1 month and THIS happened. We put artificial intelligence to the test in a real 30-day trading challenge between me and Samin. To push the experiment to the limit, I gave OpenClaw $10,000 to make money and THIS happened. We compared my strategy against Samin’s AI to see which bot performed better in a tough market. We have the full results, the mean emails between bots, and the big reveal right here. Hope you enjoy as much as we did! Win $100 Cash! Just leave a comment on the YouTube video telling us how many more days we should keep the bots running. We will randomly select a winner in one week!

Anthropic built an AI model called Claude Mythos that found critical security bugs most humans never would, including a 27-year-old bug in OpenBSD and one in FFmpeg that 5 million automated tests missed. Instead of releasing it to the public, they launched Project Glasswing to give defenders like AWS, Apple, Google, and Microsoft a head start. In this video I break down what Mythos can do, why Anthropic chose not to release it, and what it means for your security as a regular person.