Johnny Utah

Healthcare is changing at lightning speed!!! Read this: “Right now if you upload your bloodwork to an AI and it tells you your IGF-1 is low and you should consider a peptide protocol, there is nowhere legitimate to go. You can find a gray market vendor with no quality controls. You can spend hours trying to find a clinic. You can hope your primary care physician has heard of peptides, which they almost certainly have not. The recommendation exists. The access does not. That is the gap Stack is built to close. When your AI tells you what to take, Stack is what closes the loop. Licensed physician. Licensed compounding pharmacy. Lowest possible price. Shipped to your door. No gray market. No friction. No markup on the drugs themselves because our goal has never been to own the molecule. Our goal is to be the cheapest compliant path between a clinical recommendation and a fulfilled prescription, for as many people as possible. The vision is bigger than peptides. As AI gets better at understanding your biology, the recommendations it makes are going to get more precise, more personalized, and more actionable. Stack is the infrastructure layer that turns those recommendations into reality. Not just for peptides. For every cash-pay personalized therapeutic that comes next. HRT. Nootropics. GLP-1s. Whatever AI drug discovery produces over the next decade as development costs collapse and new compounds become accessible. We are not building a brand. We are building the rail that every health AI platform, every clinic, every physician, and every agent-driven health tool will eventually need underneath it. The health super cycle is here. The science is ready. The demand is ready. The regulatory window is opening. The only thing missing is the infrastructure that makes all of it accessible at a price that actually works for everyone. That is what we are building.” 📈🚀👏🏼

Grok 4.20 is now officially out of Beta. It's now on Auto, Fast, Expert & Heavy.

🚨 Holy shit...A developer on GitHub just built a full development methodology for AI coding agents and it has 40.9K stars on GitHub. It's called Superpowers, and it completely changes how your AI agent writes code. Right now, most people fire up Claude Code or Codex and just… let it go. The agent guesses what you want, writes code before understanding the problem, skips tests, and produces spaghetti you have to babysit. Superpowers fixes all of that. Here's what happens when you install it: → Before writing a single line, the agent stops and brainstorms with you. It asks what you're actually trying to build, refines the spec through questions, and shows it to you in chunks short enough to read. → Once you approve the design, it creates an implementation plan so detailed that "an enthusiastic junior engineer with poor taste and no judgement" could follow it. → Then it launches subagent-driven development. Fresh subagents per task. Two-stage code review after each one (spec compliance, then code quality). The agent can run autonomously for hours without deviating from your plan. → It enforces true test-driven development. Write failing test → watch it fail → write minimal code → watch it pass → commit. It literally deletes code written before tests. → When tasks are done, it verifies everything, presents options (merge, PR, keep, discard), and cleans up. The philosophy is brutal: systematic over ad-hoc. Evidence over claims. Complexity reduction. Verify before declaring success. Works with Claude Code (plugin install), Codex, and OpenCode. This isn't a prompt template. It's an entire operating system for how AI agents should build software. 100% Opensource. MIT License.

We need more Islamophobia, not less. Fear of Islam is rational.