🎮 Simulators
Hands-on demos to explore tokens, embeddings, temperature, RAG, and more.
✂️→🧬→📐→🔄→🌡️→⚖️→🧹→💰→🔍→🎯→🪟→📡→🧩→
Tokenization
Type text and see how it breaks into tokens and IDs.
Embeddings & Similarity
Closest-word graph in embedding space.
Cosine vs Distance & 3D
Compare cosine similarity vs Euclidean distance; 3D embedding space.
Cleaning → Embedding → Graph
Pipeline visual: raw text to 2D embedding graph.
Temperature & Sampling
See how temperature shapes next-token probabilities.
Training Data & Weights
How data mix affects output quality.
Normalization
Before/after text cleaning (lowercase, punctuation).
Token Cost
Compare verbose vs concise prompts and token count.
RAG Pipeline
Documents → embeddings → query → top-k → LLM.
Mental Model
Full stack: text → normalization → tokens → vectors → search → generation.
Context Window
See how a fixed token limit fills up; overflow is cut off.
MCP Flow
Step through how app, LLM, and MCP server interact.
Agent Components
Memory, prompting, tools, resources at a glance.