How LLMs Work vs Open Vibe

"How LLMs Work" is a free, browser-based interactive guide that walks through the complete pipeline for building large language models — from raw web scraping to RLHF-trained conversational assistant. Created by Yash Narwal and based on Andrej Karpathy's technical deep-dive lecture, it's been getting significant traction on Hacker News (214+ points) for turning dense ML theory into something genuinely accessible. The site covers data collection and deduplication, Byte Pair Encoding tokenization with a live demo, pre-training and next-token prediction, inference with a probability sampling simulator, post-training with RLHF, and RAG. Each section uses animated visualizations, clickable pipeline diagrams, and canvas-based graphics — not static explainer images. The progressive narrative structure follows a single piece of text through every stage of the pipeline, making abstract concepts concrete. In an era where everyone uses LLMs but few understand how they work, this kind of high-quality educational resource matters for a different reason than tools: it raises the baseline competency of the entire developer ecosystem. Better-informed builders ask better questions, make better design decisions, and push vendors toward more transparency. This is the kind of project the HN community rewards — and deserves the signal boost.

Open Vibe is a free, open-source 10-week curriculum that teaches web development by having you build real SaaS apps guided interactively by your AI agent (Claude Code, Cursor, etc.). You paste a single prompt into your agent, which downloads the curriculum and then mentors you through building — explaining concepts, quizzing understanding, and pairing live as you code. The curriculum runs entirely on your local machine. No platform lock-in, no token-limit surprises from a hosted sandbox. Phase 1 covers foundational web dev through increasingly complex projects. Phase 2 builds on the Open SaaS template, a production-ready boilerplate with auth, payments, and email already wired up. Interactive overlay diagrams show you how running code works in real time. The core insight is smart: AI coding tools are great at generating code but terrible at building mental models. Open Vibe breaks what it calls the "prompt-fix loop" — where learners endlessly tweak prompts without ever understanding what's happening. MIT licensed and free forever, you only need your own AI subscription to run it.