Introduction to LLM

This page provides an easy-to-understand guide on LLMs (Large Language Models) from basics to applications for AI enthusiasts.

Total of 45 articles available. | Currently on page 1 of 1.

Chapter 12 — Access Control and Identity

Twelfth post of the LLM Primer VII walkthrough. OAuth 2.0 + PKCE, ABAC vs ReBAC (Zanzibar), multi-tenant isolation, and token-bucket rate limits for LLM APIs.

2026-05-21

Chapter 11 — Observability, Logging, and Incident Response

Eleventh post of the LLM Primer VII walkthrough. Structured LLM logging with PII redaction, OpenTelemetry GenAI conventions, and the NIST SP 800-61 IR cycle adapted for probabilistic systems.

2026-05-20

Chapter 10 — Designing Secure LLM Architectures

Tenth post of the LLM Primer VII walkthrough. Isolation boundaries, policy engines (OPA, Cedar), microVM sandboxes, and the "lethal trifecta" of agent + private data + untrusted content.

2026-05-19

Chapter 8 — Adversarial Attacks on Models

Eighth post of the LLM Primer VII walkthrough. Adversarial examples in NLP (HotFlip, TextFooler), model extraction (Tramèr et al., Carlini et al.), and the defensive strategies for API-boundary abuse.

2026-05-17

Chapter 6 — Retrieval-Augmented Generation Risks

Sixth post of the LLM Primer VII walkthrough. Trust boundaries in RAG, malicious document injection, PoisonedRAG and BadRAG, and monitoring retrieval flows for the attacker's fingerprints.

2026-05-15

Chapter 5 — Input Validation and Output Filtering

Fifth post of the LLM Primer VII walkthrough. Input sanitization, structured guardrails (NeMo, Llama Guard 3, Lakera, Bedrock), and red teaming with Garak, PyRIT, and promptfoo.

2026-05-14

Chapter 4 — Prompt Injection and Jailbreaks

Fourth post of the LLM Primer VII walkthrough. Prompt injection as a structural consequence, the jailbreak taxonomy (DAN, grandma, Zou et al. suffixes, Crescendo, Skeleton Key), and the four-layer mitigation matrix.

2026-05-13

Chapter 1 — Why AI Security Is Different

First post of the LLM Primer VII walkthrough. Why LLM security is structurally different from traditional security — the collapsed code/data boundary, the probabilistic core, and the OWASP LLM Top 10 as a working checklist.

2026-05-10

LLM Primer VII — Series Introduction & Index

Kicking off the chapter-by-chapter walkthrough of Book VII in the LLM Primer series — AI Security. Why in LLM systems code and data are the same string, and the schedule for the seventeen posts that follow, May 10 through May 26. This is the series finale.

2026-05-09

Chapter 16 — Cost-Cutting Strategies in Production

Sixteenth and final post of the LLM Primer VI walkthrough. Intelligent model routing, context compaction, async batch APIs, and semantic caching — plus a look ahead to Volume VII on AI Security.

2026-05-08

Chapter 15 — Serverless APIs vs Dedicated Infrastructure

Fifteenth post of the LLM Primer VI walkthrough. The breakeven math between serverless APIs and dedicated infrastructure, the hidden platform-engineering overhead each side takes on, and microVM sandboxes for agent code execution.

2026-05-07

Chapter 8 — Next-Generation KV Cache Management

Eighth post of the LLM Primer VI walkthrough. PagedAttention, KV eviction algorithms (H2O, InfiniGen), and prefix caching for multi-turn conversations and multi-agent RAG.

2026-04-30

Chapter 6 — Pruning and Knowledge Distillation

Sixth post of the LLM Primer VI walkthrough. Structured vs unstructured pruning, 2:4 sparsity on Hopper, and the distillation lineage from soft probabilities to Patient Knowledge Distillation and MiniLLM.

2026-04-28

Chapter 8 — Optimizing Performance, Serving, and Cost

Eighth and final post of the LLM Primer V walkthrough. Semantic caching, dynamic model routing, and what actually happens inside the inference server — plus a look ahead to Volume VI on scaling.

2026-04-21

Chapter 6 — AI Observability and Tracing

Sixth post of the LLM Primer V walkthrough. OpenTelemetry GenAI conventions, span design for LLM apps, cost tracking, and the loop back into the evaluation harness.

2026-04-19

Chapter 4 — AI Agents and Tool Calling

Fourth post of the LLM Primer V walkthrough. ReAct loops, tool schemas as contracts, and the three memory layers agents actually need in production.

2026-04-17

Chapter 3 — Retrieval-Augmented Generation

Third post of the LLM Primer V walkthrough. The RAG pipeline end to end — chunking, hybrid retrieval, query transformation, multimodal, and text-to-SQL — and where RAG fits versus fine-tuning and long context.

2026-04-16

Chapter 2 — Foundation Models & Prompt Engineering

Second post of the LLM Primer V walkthrough. Model tiering, sampling parameters, defensive prompt patterns, and structured outputs as engineering surfaces — the layer just inside the deterministic wrapper.

2026-04-15

Chapter 1 — The Discipline of AI Engineering

First post of the LLM Primer V walkthrough. Why the demo works and production doesn't — the deterministic wrapper around the probabilistic core, and the five pillars (reliability, quality, performance, cost, evolution) that keep the wrapper honest.

2026-04-14

Chapter 10 — Long-Horizon Task Memory

Tenth post of the LLM Primer IV walkthrough. Short-term memory through windows and ReAct scratchpads, long-term memory through episodic vectors and semantic stores, and the compaction techniques that keep an agent productive over hours and days.

2026-04-08

Chapter 4 — Client Primitives: Agentic Behaviors and Control

Fourth post of the LLM Primer IV walkthrough. Sampling, Roots, and Elicitation are the three small, controlled holes MCP punches through the host-server wall — each a capability granted back, each a risk accepted on the user's behalf.

2026-04-02

Chapter 11 — Continuous Updates and Pipeline Optimization

Eleventh and final post of the LLM Primer III walkthrough. CDC and incremental indexing keep the corpus fresh, semantic caching and model tiering keep latency down, and a four-stage feedback loop closes the gap between what production tells the team and what the team actually changes — plus a bridge to Volume IV on Model Context Protocol.

2026-03-28

Chapter 9 — The RAG Evaluation Triad

Ninth post of the LLM Primer III walkthrough. A RAG system can fail in three different places and the failures look identical from the outside — the Evaluation Triad of Context Relevance, Groundedness, and Answer Relevance is the small vocabulary that prevents fixing one bug while measuring another.

2026-03-26

Chapter 8 — Data Anonymization in the RAG Pipeline

Eighth post of the LLM Primer III walkthrough. Pre-generation versus post-generation anonymisation, the three technique families — masking, synthetic replacement, differential privacy — and the utility-privacy tradeoff that determines whether the system remains useful at all.

2026-03-25

Chapter 6 — RAG Threat Models and Vulnerabilities

Sixth post of the LLM Primer III walkthrough. The expanded attack surface of retrieval — corpus poisoning, adversarial chunks, indirect prompt injection, embedding inversion, and the confused-deputy problem in agentic RAG. Concrete attacks, each demonstrated, each reproducible.

2026-03-23

Chapter 5 — Architecting the Retrieval Pipeline

Fifth post of the LLM Primer III walkthrough. Why a single vector search is not a pipeline — hybrid retrieval, reciprocal rank fusion, cross-encoder reranking, and query-side rewriting and HyDE — assembled into the production architecture that mature RAG systems converge on.

2026-03-22

Chapter 4 — Selecting the Right Vector Database

Fourth post of the LLM Primer III walkthrough. The architectural split between purpose-built vector databases and Postgres-style extensions, the managed leaders (Pinecone, Vertex), the open-source field (Qdrant, Milvus, Weaviate), the embedded options, and the three operational axes — residency, ops, cost — that decide the real choice.

2026-03-21

Chapter 3 — Advanced Chunking Frameworks

Third post of the LLM Primer III walkthrough. The chunking spectrum from fixed-size to structure-aware, the overlap myth, the context cliff that destroys retrieval quietly, and the contextual-retrieval and late-chunking techniques that have reshaped the frontier.

2026-03-20

Chapter 2 — Intelligent Document Parsing

Second post of the LLM Primer III walkthrough. Why a PDF is not a text file, what layout-aware parsers actually preserve, the current tool landscape (LlamaParse, Docling, Unstructured, Marker-PDF, Firecrawl, DeepSeek-OCR), and the multimodal track that retrieves over page images directly.

2026-03-19

Chapter 1 — The Evolution of RAG Architecture

First post of the LLM Primer III walkthrough. The four architectural postures of RAG — Naive, Advanced, Modular, Agentic — read as a story about handing more agency to the LLM one decision at a time, and the honest answer to when fine-tuning is the better tool than retrieval.

2026-03-18

Chapter 12 — Real-World Applications of LLMs

Twelfth post of the LLM Primer II walkthrough. Text generation, summarization, QA, translation, reasoning — and the constrained decoding, agent loops, and multimodal generalization that turn one next-token machine into a dozen kinds of product.

2026-03-14

Chapter 10 — Post-Training and Alignment Mathematics

Tenth post of the LLM Primer II walkthrough. The mathematics that civilizes a brilliant but feral next-word predictor into a helpful assistant — supervised fine-tuning, reward modeling, RLHF on a KL leash, and the elegant DPO derivation that collapses the whole pipeline into a single supervised loss.

2026-03-12

Chapter 7 — Efficiency and Transformer Variants

Seventh post of the LLM Primer II walkthrough. The computational complexity of attention, the GPU memory and throughput math that constrains real systems, FlashAttention derived from first principles, and the family of clever variants — multi-query, gated, low-rank — that keep big models running.

2026-03-09

Chapter 4 — Attention: The Core Mechanism

Fourth post of the LLM Primer II walkthrough. Self-attention derived from intuition, the geometry of queries/keys/values, multi-head structure and normalization, softmax in detail with its temperature knob, and a striking final move: attention seen as a kernel method.

2026-03-06

Chapter 3 — Mathematical Tools for Language Models

Third post of the LLM Primer II walkthrough. The probability and statistics you actually need for language modeling, the slice of linear algebra that matters, and embeddings as the first place those two tools meet inside an LLM.

2026-03-05

Chapter 10 — Safety, Ethics, & Trust: Beyond the Marketing

Chapter 10 of the LLM Primer I series. The honest picture of LLM safety — why hallucinations happen mechanistically, where bias actually lives, how layered guardrails work, and why governance is the institutional layer that technical controls can't replace. For practitioners who need to ship safely.

2026-02-27

Chapter 7 — Beyond Next-Token Prediction: Embeddings, Retrieval, and Multimodality

Chapter 7 of the LLM Primer I series. The capabilities that turn a next-token predictor into something much more — embeddings, semantic search, retrieval-augmented generation, and the move into multimodal inputs. How RAG actually keeps an LLM grounded in real documents instead of confabulating.

2026-02-24

Chapter 4 — The Transformer Architecture: Inside the Engine of Modern AI

Chapter 4 of the LLM Primer I series. A tour of the Transformer block — how self-attention, positional encoding, and stacked layers combine to produce the architecture every modern LLM is built on. Includes a clear explanation of why scaling Transformers works, and what it costs.

2026-02-21

2.1 What Is a Large Language Model?

A clear and in-depth explanation of what Large Language Models (LLMs) are. Learn how LLMs map token sequences to probability distributions, why next-token prediction unlocks general intelligence, and what makes a model “large.” This section builds the foundation for understanding pretraining, parameters, and scaling laws.

2025-09-08