← Back to LLMs overview

Hand-written tutorials, ordered as a recommended learning path.

1. 21 Context Windows Why bigger context windows are not always better: cost, attention degradation, retrieval design, and how to architect for long-context tasks. 5 min read →
2. 22 Prompt Injection How prompt injection attacks work, why simple filters fail, and the layered defenses production LLM systems should deploy. 6 min read →
3. 23 LLM Cost Tracking A practical guide to attributing, monitoring, and controlling LLM spend per user, per feature, and per request without slowing down delivery. 4 min read →
4. 24 FT vs Prompt Decide between prompt engineering, retrieval, and fine-tuning by weighing cost, latency, control, and data requirements honestly. 4 min read →
5. 25 Function Schemas How to design tool schemas that LLMs actually call correctly, with naming, description, and parameter patterns that survive real users and adversarial inputs. 4 min read →
6. 26 Grok vs Claude vs GPT An engineering-focused comparison of Grok, Claude, and GPT model families across reasoning, tool use, context, latency, and real production trade-offs. 4 min read →
7. 27 Grounding vs RAG RAG and grounding are often used interchangeably but they describe different techniques. Here is how to tell them apart and when each one matters. 4 min read →
8. 28 Jailbreak Defense Practical defenses against prompt injection, role hijacking, and policy bypasses in production LLM systems, with layered controls that actually work. 4 min read →
9. 29 Multi-Turn Chat How to design multi-turn LLM conversations that stay coherent, respect context limits, handle long histories, and support useful features like summarization and recall. 4 min read →
10. 30 Output Parsing Practical techniques for parsing and validating LLM outputs reliably, covering JSON mode, schema enforcement, retries, and repair strategies for production use. 4 min read →
11. 31 Prompt Caching How prompt caching works in modern LLM APIs, when it saves significant cost and latency, and how to design prompts so the cache actually hits in production. 4 min read →
12. 32 Quantization How quantization shrinks LLMs to run on smaller hardware, the math behind 8-bit and 4-bit weights, and the trade-offs between speed, memory, and quality. 4 min read →
13. 33 Rate Limits and Retries How to handle provider rate limits, transient failures, and quota exhaustion in production LLM apps with backoff, queues, and graceful degradation. 4 min read →
14. 34 vLLM Hosting A practical guide to self-hosting open-source language models using vLLM, covering setup, batching, and serving for production workloads. 4 min read →
15. 35 Streaming Stream tokens from an LLM as they are generated to cut perceived latency, handle partial outputs, and build responsive chat UIs. 4 min read →
16. 36 Temp & Top-p Understand how temperature and top-p sampling shape the creativity, determinism, and quality of large language model outputs. 4 min read →
17. 37 Tokens & Cost Learn how tokens are counted, how to estimate API spend before you send a request, and concrete strategies to cut LLM bills without hurting quality. 4 min read →
18. 38 Tool Calling Understand how tool calling lets LLMs invoke functions, why agents loop over tools, and how to design reliable tool schemas. 5 min read →
19. 39 Structured Outputs How to get reliable JSON out of LLMs using tool use, JSON mode, and grammar-constrained decoding, with patterns that work in production. 5 min read →
20. 40 Prompt Engineering A grounded tour of prompt engineering techniques: clear instructions, structured output, few-shot examples, chain-of-thought, role prompts, and evaluation habits that keep prompts honest. 5 min read →