Development Methods & Design PatternsVibe coding is a development style coined by Andrej Karpathy in 2025 in which humans describe intent in natural language and an LLM produces the code. Learn its tools, patterns, and limits.
Generative AI & LLMsA multi-agent system is an architecture where several LLMs collaborate to solve a task. Learn orchestrator-worker patterns, real-world examples, and Anthropic's research configuration.
Generative AI & LLMsOpenAI o3 is a reasoning-focused LLM released April 16, 2025. It uses reinforcement learning to think before answering, achieving state-of-the-art results on math, science, and coding benchmarks.
Generative AI & LLMsPlan Mode is Claude Code's read-only operating mode that forces Claude to plan without editing files. Use it for safe multi-file refactors, exploration, and production-impacting changes.
Generative AI & LLMsCLAUDE.md is a Markdown file Claude Code auto-loads to learn your codebase's commands, conventions, and constraints. Learn placement rules, structure, and practical patterns with examples.
Generative AI & LLMsHugging Face is the largest open AI hub, hosting over a million models, hundreds of thousands of datasets, and Spaces demo apps. Learn its architecture (Hub, Transformers, Datasets, Diffusers), how to use it, license caveats, and how it compares to GitHub and Kaggle.
Natural Language Processing (NLP)A tokenizer splits text into tokens and maps them to integer IDs that LLMs can process. Learn how subword tokenization works, what BPE, WordPiece, and SentencePiece do differently, and why tokenization affects API cost, context limits, and multilingual performance.
Version Control & CI/CDThe Claude Code Action is Anthropic's official GitHub Action that runs Claude Code on your repository in response to @claude mentions, issue assignments, or scheduled triggers. Learn its modes, authentication options (API key, OAuth, Bedrock, Vertex AI, Foundry), setup steps, and security trade-offs.
Generative AI & LLMsOllama is an open-source runtime that lets you run Llama 3.1, Mistral, Gemma, Qwen, DeepSeek-R1, and other LLMs locally with one command. Learn its architecture, REST API, OpenAI compatibility, hardware requirements, and how it compares to LM Studio and llama.cpp.
APIs & SDKsAn MCP Server is a process that exposes tools, resources, and prompts to AI models like Claude through the Model Context Protocol. Learn its architecture, JSON-RPC mechanics, Python and TypeScript SDKs, and how it powers Claude Desktop, Cursor, and other AI clients.
