Neural.Literacy
Neural.Literacy
A field guide · from zero to building
Neural.Literacy is an interactive field guide that turns the black box of modern AI into something you can actually see, name, and steer. No hype. No jargon wall. Just clarity, by design.
Start at Zero Knowledge. Each level unlocks the next. Go all the way and you'll understand the full stack, from tokens to agents. Pick a level — every card is a way in.
AI vs ML vs LLMs, how AI "learns," hallucination, the models, and tokens. The un-confuser.
Read Level 0 →How AI generates an answer, the 80/20 of prompts, temperature & top-p, context windows, system prompts.
Read Level 1 →The CRIC framework, few-shot & chain-of-thought, tool calling, memory, RAG, multi-model strategy.
Read Level 2 →API vs web vs CLI, inference, the provider landscape, quantization, open vs closed source, the tool loop.
Read Level 3 →Embeddings, vector databases, multi-agent systems, and fine-tuning. The deep end.
Read Level 4 →Applied AI: research, coding, content, and business automation. Theory is cheap; execution is everything.
Open Workflows →A toy tokenizer. Type a sentence and watch it split into the fragments a model actually sees.
12 moves to steer the model like you mean it.
Read the PlaybookNot marketing copy — actual lines from the guide. Click any card to read the whole level.
You type something into ChatGPT. In milliseconds, out comes an answer. Fluent, coherent, sometimes better than what you'd write yourself. But what actually happened? The model guessed. Literally guessed the next most likely word.Read Level 0 → Level 2 · Power User
Every good prompt has four components: Context, Role, Instruction, Constraints. You don't always need all four, but the more you include, the better the result.Read Level 2 → Level 4 · Advanced
Traditional search matches exact words. Embeddings match meaning. Search for "canine" and it finds "dog," "puppy," "hound" — because they're all close in embedding space.Read Level 4 →
The tools will change every quarter. The mental models won't. Learn the model beneath the models, and you'll never be at the mercy of a release note again.