Engineering Notes from the Open-Source Frontier: PSGD, Levanter, TPU Orchestration, and the Inference Economics of LLMs 14 minute read Published: September 13, 2026
Deconstructing the Model Context Protocol (MCP): From stdio Pipes to Streamable HTTP 10 minute read Published: September 12, 2026
Key Concepts in LLM Pre-training Part 2: Taming MoE Router Instability with Trillion-Scale Proven Tweaks 30 minute read Published: September 11, 2026
Diagnosing My Camry’s Low Compression: Engineering First Principles, Red-Teaming AI, and an Overnight Soak 14 minute read Published: September 10, 2026
Key Concepts in LLM Pre-training: Scaling Ladder, Logit z-loss, and Token Dropping from 535B-A23B Training Discussions 20 minute read Published: September 07, 2026
MoE 3D Architecture Visualizer: Interactive 3D Visualization of Modern MoE LLM Architectures 4 minute read Published: September 07, 2026
Core Technical Questions and In-Depth Answers for AI / LLM Engineers (Illustrated Guide) 27 minute read Published: August 23, 2026
AI Model Release Velocity: Comparing Anthropic, OpenAI, and Google (2025–2026) 3 minute read Published: June 29, 2026
Migrating to Antigravity CLI: First Impressions and Incredible Speed 1 minute read Published: June 11, 2026
The Future of AI Interaction: From Low-Bandwidth Language to High-Bandwidth Vision 2 minute read Published: June 07, 2026
Deep Dive vs. Professional Orchestration: My Reflections on the AI Efficiency Paradox 1 minute read Published: May 28, 2026
Deconstructing the Model Context Protocol (MCP): From stdio Pipes to Streamable HTTP 10 minute read Published: September 12, 2026
Diagnosing My Camry’s Low Compression: Engineering First Principles, Red-Teaming AI, and an Overnight Soak 14 minute read Published: September 10, 2026
The Future of AI Interaction: From Low-Bandwidth Language to High-Bandwidth Vision 2 minute read Published: June 07, 2026
Engineering Notes from the Open-Source Frontier: PSGD, Levanter, TPU Orchestration, and the Inference Economics of LLMs 14 minute read Published: September 13, 2026
AI Model Release Velocity: Comparing Anthropic, OpenAI, and Google (2025–2026) 3 minute read Published: June 29, 2026
Migrating to Antigravity CLI: First Impressions and Incredible Speed 1 minute read Published: June 11, 2026
Adding Comments to My Static Website: Understanding Vercel, Neon Database, and Serverless Functions 4 minute read Published: June 11, 2026
Deep Dive vs. Professional Orchestration: My Reflections on the AI Efficiency Paradox 1 minute read Published: May 28, 2026
Key Concepts in LLM Pre-training Part 2: Taming MoE Router Instability with Trillion-Scale Proven Tweaks 30 minute read Published: September 11, 2026
Key Concepts in LLM Pre-training: Scaling Ladder, Logit z-loss, and Token Dropping from 535B-A23B Training Discussions 20 minute read Published: September 07, 2026
MoE 3D Architecture Visualizer: Interactive 3D Visualization of Modern MoE LLM Architectures 4 minute read Published: September 07, 2026
Core Technical Questions and In-Depth Answers for AI / LLM Engineers (Illustrated Guide) 27 minute read Published: August 23, 2026
Adding Comments to My Static Website: Understanding Vercel, Neon Database, and Serverless Functions 4 minute read Published: June 11, 2026