Still the best one-hour mental model of what an LLM actually is before you build on one.
[1hr Talk] Intro to Large Language Models
Andrej Karpathy Nov 2023
Watch on YouTube youtube.com →Your first AI feature is usually one API call: send the model your instructions plus the user's input, get text or structured JSON back, and wrap it in your existing UI. RAG simply means fetching your own data (docs, tickets, listings) and pasting the relevant bits into the prompt so the model answers from your facts instead of its memory. Ship a thin version in days with the OpenAI or Claude API and a toolkit like Vercel's AI SDK, then iterate on prompts before touching anything fancier.
19 resources.
Still the best one-hour mental model of what an LLM actually is before you build on one.
Andrej Karpathy Nov 2023
Watch on YouTube youtube.com →Karpathy's updated general-audience walkthrough covering training, hallucinations, and tool use.
Andrej Karpathy Feb 2025
Watch on YouTube youtube.com →Retrieval-augmented generation explained without jargon, the concept behind most useful first AI features.
KodeKloud Aug 2025
Watch on YouTube youtube.com →A 90-minute end-to-end build you can follow along with, from empty repo to deployed chatbot.
freeCodeCamp (Ania Kubow) 2024
Watch on YouTube youtube.com →30-minute episodes where real builders demo exactly how they shipped AI features, demos included.
Claire Vo (How I AI) 2025
Listen on Apple Podcasts podcasts.apple.com →The default podcast of people who ship AI features for a living; subscribe and skim show notes.
swyx and Alessio Fanelli 2025
Open latent.space →Free, thorough, and taught by the engineer who wrote much of LangChain's RAG tooling.
freeCodeCamp (Lance Martin, LangChain) 2024
Open freecodecamp.org →The follow-on course for when your prototype RAG needs to survive real users.
freeCodeCamp 2025
Open freecodecamp.org →The primary source for letting the model trigger your app's actions, the step from chatbot to feature.
OpenAI 2025
Open developers.openai.com →Guaranteed-JSON responses ended a whole class of parsing bugs; read this before writing a parser.
OpenAI Aug 2024
Open openai.com →Free structured course covering prompting, extraction, streaming, and tool calls in real product code.
Vercel Academy 2025
Open vercel.com →Six practitioners condense a year of production LLM scar tissue into tactical advice.
Eugene Yan, Hamel Husain, Jason Liu, Shreya Shankar, et al. May 2024
Open oreilly.com →The whole LLM-product stack in one thread; a map of every decision you will eventually face.
Eugene Yan (Anthropic) Aug 2023
Open x.com →The most-read O'Reilly book of 2025; the reference text once you outgrow tutorials.
Chip Huyen Jan 2025
Open oreilly.com →An India-based walkthrough from API key to working app, aimed at non-ML developers.
Analytics Vidhya Jun 2025
Open analyticsvidhya.com →The gentlest possible on-ramp if your team writes Python but has never called a model API.
Machine Learning Mastery 2024
Open machinelearningmastery.com →A CPO livebuilds a real feature with AI tools, showing how fast the idea-to-ship loop has become.
Peter Yang (Creator Economy) with Claire Vo 2025
Open creatoreconomy.so →The most popular TypeScript toolkit for streaming AI features, with 25+ providers behind one API.
Vercel 2025
Open github.com →A production-ready open-source chatbot with auth and persistence; fork it instead of starting from zero.
Vercel 2025
Open github.com →The same ground, over in Build the product, our Starting Up track.