Notes on AI, Agents, and Beyond
Understanding the atomic write challenge in microservices with hand-drawn diagrams
A critical look at why most "AI Agents" are just glorified scripts
256 Choose 8: The Art of MoE architecture under hardware constraints
A comparative analysis of nsjail, Firecracker, gVisor, Docker & RestrictedPython
Deep dive into how the plan agent implements user interaction with multiple choice questions
Architecture analysis: how agents work, creating custom agents, the skills system
AI-Driven Agile Development framework with 12+ specialized agents and Party Mode
Visual guide to Zero-Shot, Few-Shot, Chain-of-Thought, RAG, ReAct, Tree of Thoughts and more
Structured guide to LLM security: OWASP Top 10, prompt injection, jailbreak testing examples
Complete guide to MMLU, HumanEval, GSM8K, TruthfulQA, MT-Bench and 50+ other benchmarks
Complete guide to code intelligence tools and how to use them in OpenCode/Claude Code with skills
How LLM providers cache attention states for faster, cheaper inference — with animated diagrams and memory math
Unified assistants vs individual AI features: how AI will reshape consumer and enterprise software
A practical, adoption-first framework: approved models, providers, gateway access, guardrails, and observability