This is the simplest, open knowledge base for everyone building apps and experiences with AI today. We've distilled the key ideas — vibe coding, Software 2.0, code like bacteria, the LLM OS, and evals & taste — into plain English from the best public teachers, above all Andrej Karpathy. Learn the ideas, build something real, and keep it open.
Describe the app or feature you wish existed — like you'd explain it to a friend. The AI writes the first version. You don't need to know the syntax to start; you need to know what "good" looks like.
Try it. Notice what's off. Ask for the change in plain words. This loop — describe, run, react — is "vibe coding": you steer with taste while the machine does the typing.
Ask for small, self-contained chunks you can understand and reuse. Small pieces are easy to fix, easy to share, and easy to trust. (This is "code like bacteria" — more below.)
Keep a few simple tests or examples that prove it works ("evals"). When the AI changes something, your checks tell you the truth. Taste plus tests beats vibes alone.
You describe intent; the model writes the code; you steer with judgment and tests. It opens building to far more people — the skill becomes taste and clarity, not syntax. For you: you can ship a real app this week by describing it well and steering carefully.
Neural nets are a new kind of software you "program" by choosing data and checking results. The dataset and the evals are as important as the code. For you: curate good examples and good checks — that's half the work.
Write pieces so small and self-contained that anyone could copy one out — "yoink" — without importing your whole project. Small life colonizes everywhere; build a bigger backbone only where you must. For you: prefer 5 lines over 50; make each piece a gist someone could love.
Think of the model as a kernel with tools, memory, and peripherals around it. Apps are built by giving it the right context, tools, and guardrails. For you: most of the magic is in the context and tools you give it, not a clever prompt.
Measure behavior with small, honest checks, and keep a human in the loop on what matters. Taste tells you what to build; evals tell you whether it works. For you: a handful of real examples beats a wall of opinions.
The best way to understand is to build the smallest version that works, end to end, then grow it. Small, legible projects teach more than big plans. For you: ship a tiny thing today; understanding compounds.
Distilled from the public teaching and open-source of builders we learn from — especially Andrej Karpathy. See our gratitude & learnings page. Admiration for public work; not an affiliation or endorsement.
We try to practice what this guide preaches: small, self-contained code anyone could yoink; a backbone only where complexity demands it; consent-first by construction; and a public story that maps to real, legible code. We publish our protocol (PCHP) openly, keep our research in the open, and welcome contributions — because a good idea spreads when everyone can build to it.
Our blog on the small-modular-self-contained ethos and how it maps to building consent-first AI.
The people we learn from — Andrej Karpathy and others — and the lessons we carry into the work.
Build on the open, agent-native rails (MCP, A2A, AP2, UCP) wrapped by PCHP consent receipts.
Vibe coding is building software by describing what you want in plain language and letting an AI write the code, while you steer with judgment, taste, and a few honest tests. The skill shifts from memorizing syntax to knowing clearly what you want and what "good" looks like — so far more people can build real apps and experiences.
No. You need clarity about what you want, the patience to try-react-refine, and a few simple checks to keep yourself honest. Start tiny, keep the pieces small and self-contained, and grow from there.
Write code in small, modular, self-contained pieces that anyone could copy out and reuse without importing your whole project — like genes that spread by being useful on their own. Build a larger, coupled "backbone" only where real complexity demands it. It's how open-source communities thrive: small, shareable, remixable.
They're distilled, in plain English, from the publicly shared teaching and open-source of the best builders — especially Andrej Karpathy (Software 2.0, the LLM OS, "code like bacteria," nanoGPT, and his Zero to Hero course). This guide reflects our admiration for that public work; it does not imply any affiliation or endorsement.
Pick one tiny idea, describe it clearly, and ship the smallest version today. Then share it so someone else can yoink it.
This guide reflects admiration for the publicly shared teaching of builders like Andrej Karpathy and does not imply affiliation or endorsement. One is a product of Hushh Technologies Corporation (brand: 🤫 “hussh”), an independent company. One runs on third-party silicon, systems, and cloud; all company names are used solely to describe the platforms on which One software runs. Hushh Technologies is not affiliated with, endorsed by, sponsored by, or partnered with any company named.
