index

Wiki Index

Content catalog. Every wiki page listed under its type with a one-line summary. Read this first to find relevant pages for any query. Last updated: 2026-06-22 | Total pages: 50

Entities

• karpathy-llm-wiki - Andrej Karpathy’s pattern for persistent knowledge bases

Concepts

• self-supervised-learning - Self-Supervised Learning
• unsupervised-learning - Unsupervised Learning
• autoencoder - Autoencoder
• variational-autoencoder - Variational Autoencoder
• variational-inference - Variational Inference
• markov-chain-monte-carlo - Markov Chain Monte Carlo
• bayesian-inference - Bayesian Inference
• monte-carlo-tree-search - Monte Carlo Tree Search
• partially-observable-markov-decision-process - Partially Observable Markov Decision Process (POMDP)
• bellman-equations - Bellman Equations
• ai-agent - AI Agent
• markov-decision-process - Markov Decision Process
• q-learning - Q-Learning
• markov-decision-processes - Markov Decision Process
• recurrent-neural-networks - recurrent-neural-networks
• transformer - Transformer
• self-attention - Self-Attention
• transformer-models - Transformer Models
• natural-language-processing - Natural Language Processing
• artificial-intelligence - Artificial Intelligence
• supervised-learning - Supervised Learning
• knowledge-distillation - Knowledge Distillation
• neural-networks - Neural Networks
• pruning - Pruning
• model-compression - Model Compression
• quantization - Model Quantization in Deep Learning
• parameter-efficient-fine-tuning - Parameter-Efficient Fine-Tuning (PEFT)
• fine-tuning - Fine-Tuning
• low-rank-adaptation-lora - Low-Rank Adaptation (LoRA)
• dynamic-programming - Dynamic Programming
• monte-carlo-methods - Monte Carlo Methods
• temporal-difference-learning - Temporal-Difference Learning
• actor-critic-methods - Actor-Critic Methods
• kullback-leibler-divergence - Kullback-Leibler Divergence
• trust-region-policy-optimization - Trust Region Policy Optimization
• machine-learning - Machine Learning
• policy-gradient-methods - Policy Gradient Methods
• deep-learning - Deep Learning
• reinforcement-learning - Reinforcement Learning
• proximal-policy-optimization - Proximal Policy Optimization
• transfer-learning - Transfer Learning
• supervised-fine-tuning - Supervised Fine-Tuning
• large-language-models - Large Language Models
• reinforcement-learning-from-human-feedback - Reinforcement Learning from Human Feedback (RLHF)
• transformer-architecture - Self-attention based sequence-to-sequence architecture
• quantum-entanglement - Physics phenomenon of non-local correlation between particles
• karpathy-llm-wiki-source - Core resources for Andrej Karpathy’s LLM-Wiki
• retrieval-augmented-generation - Context-fetching architecture for LLMs
• direct-preference-optimization-dpo - Direct optimization of LLMs on human preferences without RL

Comparisons

Queries

---

Recent Pages

• self-supervised-learning (concept)
• unsupervised-learning (concept)
• autoencoder (concept)
• variational-autoencoder (concept)
• variational-inference (concept)
• markov-chain-monte-carlo (concept)
• bayesian-inference (concept)
• monte-carlo-tree-search (concept)
• partially-observable-markov-decision-process (concept)
• bellman-equations (concept)