Eye of the Storm
Archive
Series

Research, in arcs

AI Basics11 posts
A ground-up introduction to working with AI tools — from prompting fundamentals to integrating AI into your development workflow.
Building in Public2 posts
Behind-the-scenes posts on how this devblog gets built — workflow, tooling, and the decisions behind the decisions.
LLM Driven SDLC1 post
How large language models are reshaping every phase of the software development lifecycle — from requirements and planning through implementation, review, testing, and deployment. A practitioner's view of what actually changes when AI enters the loop.
AI Engineering Research2 posts
Deep-dive research notes on building AI-powered tools — from designing LLM-driven requirements generators to understanding architecture, inference, and production AI systems.
On GitHub

Projects in flight

codagatchiTypeScript
A tamagotchi-style desktop pet built with Tauri — a small always-on-top companion whose stats decay in real time and need tending.
groundworkTypeScript
SDLC discipline plugin for Claude Code — requirements, plans, and structured development workflows.
— Updated as projects evolveAll research & projects
ActivityAbout
GitHubXRSS
© 2026 stormbreaker9000 · charted with care
Archive

// series

AI Engineering Research

Deep-dive research notes on building AI-powered tools — from designing LLM-driven requirements generators to understanding architecture, inference, and production AI systems.

in progress

The Complete Stack

  1. Applicationswhere it is heading
    1. 17The Scaling Wall Debate and What's Next
  2. Modelswhat they are
    1. 01What an LLM Actually Is
    2. 02The Training Pipeline End-to-End
    3. 07Evaluation and the Benchmark Crisis
  3. Traininghow they learn
    1. 03Inside Pretraining
    2. 04Post-Training and RLHF
    3. 05Constitutional AI and the Alignment Stack
    4. 06Reasoning Models and RL on Verifiable Rewards
  4. Distributed computingsoftware systems at extreme scale
    1. 10Networking and "One Giant Computer"
  5. Siliconthe chips
    1. 08The Transformer at the Hardware Level
    2. 09HBM and the Memory Wall
    3. 13NVIDIA's Moat: CUDA and Why Competitors Struggle
    4. 14The Supply Chain Behind Every Chip
  6. Hardwareracks and cooling
    1. 11The Rack as the New Unit of Compute
    2. 16Training vs Inference and Where Compute Is Going
  7. Earthpower and politics
    1. 12Power, Grid, and the Binding Constraint
    2. 15Geopolitics, Export Controls, and Sovereign AI
01

Designing an LLM-Driven Requirements Generator

How to build an LLM-powered requirements generator using EARS notation, ISO 25010:2023 NFR coverage, and a multi-agent generator/critic/formatter split that avoids the failure modes empirical studies now document.

May 1302

Designing the design stage: a comprehensive synthesis for an LLM-driven architecture plugin

A practical playbook for the architecture/design stage of an LLM-driven SDLC plugin: what makes design artifacts good, a file-per-artifact schema that mirrors the requirements layer, a methodology-agnostic core (ISO 42010 + arc42 + C4 + MADR + SEI), and a multi-agent pipeline with deterministic validation gates.

May 17