Thoughts on design, development, AI infrastructure, and building products.
84 hooks intercept 15 of the 26 lifecycle event types Claude Code exposes. Each one traces back to a specific production failure: wiped caches, leaked credentials, phantom tests.
AI & TechnologyTime, cost, resources, and effort are not constraints. The question is what's right, not what's efficient. A philosophy for building with AI agents.
AI & TechnologyThe LiteLLM attacker made one implementation mistake. That mistake was the only reason 47,000 installs got caught in 46 minutes.
AI & TechnologyGooglebot crawls 21,000 pages overnight, Bingbot crawls 10,000, and my nightcheck grinds through 15,000. Bot traffic exceeds all human visitors combined.
AI & Technology\"I believe\" and \"it should\" are not evidence. Every agent completion report needs a file path, test output, or specific code before marking work done.
AI & TechnologyThe model is the same between session 1 and session 500. The project changed. This reframes the entire AI productivity conversation.
AI & TechnologyAgents have capability without opinion. The quality ceiling depends on how well you encode aesthetic judgment into hooks, gates, and constraints.
AI & TechnologyA diagnosis survived three corrections over four days and guided a fix that cut page load from 14s to 108ms. Handoffs carry context agents cannot.
AI & TechnologyEvery night: 15,000 pages checked, TTFB measured, cache verified, sitemaps crawled. The goodnight routine is where operational discipline lives.
AI & TechnologyMy vault has 17,900 signals from arXiv, Semantic Scholar, HN, NVD, and 9 other sources. Most are noise. The noise taught me what signal looks like.
AI & TechnologyEvery problem you solve with an AI agent deposits context that the next session withdraws with interest. This is context compounding.
AI & TechnologyClaude Code autonomously discovered adversarial attacks with 100% success rate against Meta's SecAlign-70B, beating all 33 published methods in 96 iterations.
AI & TechnologyTechnical writing published at Introl
Comprehensive hardware recommendations and cost analysis for running large language models locally.
GPU selection guide comparing NVIDIA's latest datacenter accelerators for different AI workloads.
Deep technical dive into Google's Tensor Processing Unit evolution from TPUv1 to TPUv5.
Resource sharing strategies for GPU clusters in containerized environments.
Guide to building and managing distributed AI computing with Ray framework.
Analysis of open source LLM economics and DeepSeek's competitive positioning.
Future datacenter power requirements and NVIDIA's next-generation GPU roadmap.
Small modular reactor solutions for powering next-generation AI infrastructure.
Technical analysis of DeepSeek's Multi-Head Compression architecture innovations.
ResumeGeni
AI resume builder for ATS optimization
Ace Citizenship
USCIS test prep with spaced repetition
Get Bananas
Hand-drawn family shopping list
Return
Zen meditation timer for Apple devices
Ki
Private iPhone browser
Tappy Color
Fast-paced color matching game
Captain's Log
Daily operational journal for builders
941 Tiles
One-click macOS window manager
Learn Materia
Print-first kindergarten homework
Reps
Strength training on every Apple screen
Randori
Jiu-jitsu training log for iPhone and Watch
Cels
Floating glass notes for macOS 26