Filed under
Software Engineering
19 entries
-
Software Engineering · 5 min read ·
One ZIP, Two Lists of Files
A small reproducible ZIP lab shows why indexed and streaming readers can inspect different entries in the same archive.
-
AI Agents · 7 min read ·
You Can't Prove the Agent. Prove the Gate.
Formal verification for AI-agent security. You can't prove a probabilistic model does the right thing — but the deterministic gate in front of it is small enough to prove outright. Dafny proofs, a Rego twin, and differential testing, following the method AWS used for Cedar.
-
TypeScript · 10 min read ·
A Month of Modularization: nexus-agents in April 2026
Extracting benchmarks into a standalone package was the punchline. The setup was a month of governance, skills, security, and pipeline discipline that made the extraction possible in an afternoon.
-
Hardware · 10 min read ·
Signed USB Rescue Boot: aegis-boot and the QEMU+OVMF Persona Harness
A UEFI-Secure-Boot-preserving rescue USB for any ISO, and the companion QEMU harness that validates it against 11 hardware personas without physical Frameworks, ThinkPads, or Dells on a lab bench.
-
TypeScript · 7 min read ·
Building US Code Tracker: Federal Law as Git History
How I built an end-to-end pipeline that converts the United States Code from XML into a Git-versioned, searchable static site with 53,000+ sections and inline case law annotations.
-
AI Agents · 12 min read ·
Building Nexus-Agents: What I Learned Creating a Multi-Model AI Orchestration System
The engineering story behind nexus-agents, a research-backed multi-model orchestration system that coordinates Claude, Gemini, and Codex through consensus voting, adaptive routing, and graph workflows.
-
AI Agents · 8 min read ·
Consensus Voting With AI Models: When Three Opinions Beat One
How multi-model consensus voting catches blind spots that single models miss. The research behind adversarial roles, Bayesian aggregation, and structured deliberation across Claude, Gemini, and Codex.
-
Automation · 7 min read ·
Supercharging Development with Claude-Flow: AI Swarm Intelligence for Modern Engineering
Claude-Flow orchestrates multiple AI agents against one task. What it does, what its published numbers actually are, and why the CLI in most write-ups never existed.
-
MCP · 14 min read ·
Down the MCP Rabbit Hole: Building a Standards Server
Build MCP standards server for Claude AI—implement Model Context Protocol for intelligent code standards and context-aware workflows.
-
Compliance · 8 min read ·
Exploring Claude CLI Context and Compliance with My Standards Repository
A CLAUDE.md is a prompt, not a loader. What a standards repository can and cannot enforce, and where the real enforcement has to live.
-
Machine Learning · 17 min read ·
Fine-Tuning LLMs in the Homelab: A Practical Guide
Fine-tune LLMs on homelab hardware with QLoRA and 4-bit quantization. Train Llama 3 8B models on RTX 3090 with dataset prep and optimization strategies.
-
Architecture · 14 min read ·
Context Windows in Large Language Models: The Memory That Shapes AI
What context windows actually cost in memory and latency, why capacity and recall are different things, and where retrieval beat a bigger window in my homelab.
-
Cryptography · 14 min read ·
Large Language Models for Smart Contract Security: Promise and Limitations
Testing GPT-4, Claude and Llama 3 against 47 smart contracts—80% reentrancy detection, but 60% of everything they flagged was wrong, which is substantially noisier than the static analyzer they were supposed to replace.
-
Software Engineering · 3 min read ·
PizzaOps: How a Dumb LLM Experiment Became a Distributed System
I asked an early LLM to build a pizza calculator to find out whether it could write working code. It could. Then it kept adding features nobody asked for, and I made the mistake of encouraging it.
-
Architecture · 13 min read ·
Blockchain Beyond Cryptocurrency: Building the Trust Layer of the Internet
Deploy blockchain beyond cryptocurrency with Ethereum and smart contracts—build decentralized trust for supply chain and identity verification.
-
Robotics · 12 min read ·
Learning from Nature: How Biomimetic Robotics is Revolutionizing Engineering
Design biomimetic robots inspired by nature—implement gecko adhesion, swarm intelligence, and soft robotics using billions of years of evolution.
-
Zero Trust · 12 min read ·
Implementing Zero Trust Security: Never Trust, Always Verify
Deploy zero trust security with continuous verification and identity-centric controls—implement never-trust-always-verify for Federal EO 14028 compliance.
-
Architecture · 6 min read ·
Designing Resilient Systems — Lessons from Things Breaking
The cascade failure that changed how I think about building systems that break gracefully.
-
Vulnerability Management · 11 min read ·
Writing Secure Code: A Developer's Guide to Thwarting Security Exploits
Master secure code development with input validation, parameterized queries, and secrets management—prevent SQL injection and XSS in production systems.