AI/LLM Cheatsheet 13 — Fine-tuning
Cheatsheet: when to fine-tune, LoRA, QLoRA, OpenAI fine-tune.
LLM
AI/LLM Cheatsheet 14 — Multimodal LLMs
Cheatsheet: vision LLMs, image inputs, audio, video.
AI/LLM Cheatsheet 15 — Security and Prompt Injection
Cheatsheet: prompt injection, defenses, PII, jailbreaks.
AI/LLM Cheatsheet 17 — Observability for LLMs
Cheatsheet: logging, traces, metrics, evals in prod.
AI/LLM Cheatsheet 18 — LLM Application Patterns
Cheatsheet: classification, extraction, summarization, routing, decomposition.
FastAPI Cheatsheet 18 — Streaming and LLM Integration
Cheatsheet: streaming Claude / GPT / vLLM tokens via SSE, tool-call loops, cancellation, prompt caching.
AI/LLM Cheatsheet 19 — Building Chat UI
Cheatsheet: chat UI, streaming, markdown rendering, code blocks.
AI/LLM Cheatsheet 20 — Production LLM App
Cheatsheet: full prod LLM app stack.
Self-Hosting LLMs in 2026 — When the Math Actually Works
Practical LLM self-hosting math: GPU pricing, throughput per GPU, sustained load break-even, vLLM tuning, and when API still wins.
Synthetic Data with LLMs in 2026 — Use Cases, Risks, and the Patterns That Work
Practical synthetic data: fine-tune training data, eval set generation, edge case enumeration, and the model-collapse / quality risks to watch.