LLM Fundamentals AI Agents Context Engineering Prompting Techniques Playground My Path Pricing

Neural Networks Training Dynamics Transfer Learning Tokenization Embeddings Attention Mechanism Transformer Architecture Inference & KV-Cache Decoding Strategies LLM Settings Prompt Elements Prompt Engineering Basics Best Practices Quantization Fine-tuning vs Prompting Reasoning Models Open-Source Models RLHF Mixture of Experts (MoE)Knowledge Distillation RLVR and GRPO Diffusion LLMs Test-Time Compute Scaling

ReAct Pattern Function Calling Tool Impact Agent Memory Multi-Agent Systems Planning & Decomposition Agent Architectures Building AI Agents LangChain & LlamaIndex Agent Evaluation & Testing A2A Protocol (Agent-to-Agent)Computer Use & Browser Agents Agent Protocols: A2A, ACP & AP2

Context Engineering System Prompts Context Windows Prompt Structure RAG — Retrieval Augmented Generation Prompt Security Context Engineering Strategies: Write, Select, Compress, Isolate

Zero-Shot Prompting Chain-of-Thought — Step-by-Step AI Reasoning Few-Shot Learning Self-Consistency — Improving Accuracy via Voting Tree of Thoughts Meta-Prompting Reflexion — Self-Correcting LLM Outputs Least-to-Most — Bottom-Up Problem Decomposition Program of Thought Chain of Verification RAG — Retrieval-Augmented Generation Prompt Chaining Generate Knowledge Structured Output APE — Automatic Prompt Engineering DSPy — Programming Language Models ART — Automatic Reasoning and Tool-use Multimodal CoT Prompt Frameworks Practical Patterns Combining Techniques Self-Refine

Code Generation Text Classification Summarization Information Extraction Question Answering Data Generation Chatbots & Conversational AI Text Transformation Semantic Search Content Generation Text-to-SQL — Natural Language to SQL Queries Structured Output Sentiment & Opinion Mining Image Generation Prompting Per-Model Prompting Guides Agentic Coding

Model Selection Guide LLM Benchmarks Vector Databases LLM Observability Cost Optimization API Integration Patterns LLM Deployment Production Guardrails RAG vs Fine-tuning Small Language Models Prompt Caching LLMOps Model Routing Harness Engineering

Vision LLMs Image Analysis Prompt Engineering for Vision Document Understanding Vision Hallucinations Multimodal RAG Voice Agents Real-Time Multimodal Video & Audio Multimodal Costs Diffusion Models

Prompt Injection Jailbreaking — LLM Safety Bypass Techniques Factuality & Hallucinations Biases in LLMs AI Safety & Alignment Data Privacy & PII Leakage Red Teaming for LLMs Context Laundering

Introduction to Claude Code Installation & Setup Your First Session The Agent Loop 18 Built-in Tools File Operations Search & Navigation Sub-agents Overview Built-in Agents Creating Custom Agents Agent Patterns MCP Fundamentals Popular MCP Servers MCP Configuration Advanced MCP Memory & CLAUDE.md Modular Rules Context Management Hooks System Skills & Commands Creating Plugins Agent SDK

Prompting Techniques Comparison AI Prompt Engineering Challenges LLM Playground — Test AI Prompts BPE Tokenizer — See How AI Reads Text Semantic Search Demo — AI Embeddings Token Probabilities — AI Model Predictions Context Window Visualizer Prompt Battle — Technique Comparison

Prompt Constructor

Home
Playground
Tokenizer

Resources

Glossary Learning Path Playground What's New

Legal

Terms of Service Privacy PolicyContact Us About the Author

© 2024-2026 ExplainLLM. All rights reserved.

Telegram channel

BPE Tokenizer — See How AI Reads Text

Interactive BPE tokenizer visualization: see how GPT-4, Claude, and Llama split text into tokens in real time

Tokenization Mode

Local BPE simulation — demonstrates how the algorithm works

Tokenizer Explorer

65Tokens

76Characters

1.17Chars/Token

BPE Merge Process

Show BPE merges

Merge step 0/11

Tokens (76)

T

h

e

␣

q

u

i

c

k

␣

b

r

o

w

n

␣

f

o

x

␣

j

u

m

p

s

␣

o

v

e

r

␣

t

h

e

␣

l

a

z

y

␣

d

o

g

.

␣

L

L

M

s

␣

p

r

o

c

e

s

s

␣

t

e

x

t

␣

u

s

i

n

g

␣

t

o

k

e

n

s

.