LLM

• Illustration guide to GPT-2
• Illustration guide to seq2seq with attention

Prompt engineering

• Prompt engineering guide
• By Antrophic:
  • For Claude: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overview
  • Interactive tutorial: https://github.com/anthropics/prompt-eng-interactive-tutorial
• Prompt engineering guide by OpenAI
• Prompt engineering guide by Google Cloud

Context engineering

• Context engineering for AI agents
• 12-factor agents
• Memory & context management with Claude Sonnet 4.5

RAG

• pgvector: for vector similarity search
  • https://neon.com/docs/extensions/pgvector
  • https://neon.com/blog/optimizing-vector-search-performance-with-pgvector
  • https://learn.microsoft.com/en-us/azure/cosmos-db/postgresql/howto-optimize-performance-pgvector

Fine-tuning

• Local LLM fine-tuning on Mac
  • Tested on my own M1 16GB
  • mlx

Serving LLM

• Ollama - for local LLM serving
• SGLang - high performance LLM and multimodal models serving
• vLLM - high performance LLM serving
• llama.cpp - LLM inference in C/C++