Blog
Writing about AI agent systems, gaming technology, and building products at the intersection of AI and entertainment. Drawn from 25+ years of founding companies, shipping games, and working with emerging tech.
Frontier AI Performance at Home, Without the API Bill
Maestro fuses the model CLIs already on your machine into one answer that beats any of them alone. It is the same mixture-of-agents method OpenRouter's Fusion API benchmarked at frontier level for about half the cost, except it runs on the flat-rate subscriptions you already pay for instead of a metered API bill.
Why I Stopped Using Multi-Agent Frameworks (And What Replaced Them)
After 18 months of building with AutoGen, CrewAI, and LangGraph, I replaced all of them with explicit decomposition and deterministic orchestration. Here is why, and what to use instead.
Prompt Engineering Is Dead. Context Engineering Is the Job Now.
Clever prompt wording stopped being the bottleneck once models got good at following instructions. The real work moved to engineering what goes into the context window.
What 18 Months of Production AI Agents Actually Taught Me
Five things that broke, three that worked unexpectedly, and the cost arc that surprised me. A first-person retrospective from running AI agents in production for 18 months.
The Automation Paradox: Why AI Agents Create More Work Before They Create Less
Teams deploying AI agents see a productivity dip before gains materialize. The supervision tax, the correction loop, and the trust calibration period are predictable, manageable phases, not signs of failure.
AI Is Running Out of Power, Data, and Quality All at Once
AI data centers now consume more electricity than Japan. Human training data may already be exhausted. Models are measurably degrading. These three crises are connected, and fixing one makes the others worse. Here's the research, and what might actually help.
1-Bit LLMs Could Make GPUs Obsolete (And Why Nobody Is Betting on It Yet)
Microsoft's BitNet matches full-precision LLMs at 12x less energy using ternary weights on a CPU. If 1-bit LLMs scale, NVIDIA's $3 trillion valuation is built on an assumption that may not hold. Here's why AMD and Intel aren't rushing in.
Why Your Multi-Agent AI System Keeps Failing (And What the Research Actually Says)
Multi-agent LLM systems fail 41-87% of the time. 79% of those failures come from coordination, not capability. Here is what the research says about building systems that actually work.
AI Agents Need Governance, Not Guardrails
For practitioners and engineering leads evaluating governance approaches: SDK wrappers are in-process guardrails agents can bypass. Infrastructure-level governance, where agents never hold API keys, is the only enforceable approach. Here's why.
We Were Live Streaming Before Twitch Existed
In 2008, Nihilum partnered with Xfire and Dyyno to live stream World of Warcraft raids to 2,800 concurrent viewers, years before Twitch launched. Here's what happened.