EssayOct 16, 20266 min
REA on a Token Diet
Measure and cut the tokens Reverse Engineering Anything puts in your AI agent's context, keep agents working while big binaries decompile, and see which optimizations are still open proposals.
La Rebelion Labs
Builders who refuse default paths.
A content-first field guide for AI systems, DevOps, cloud-native architecture, and product-minded engineering.
Latest dispatchREA on a Token Diet
Measure and cut the tokens Reverse Engineering Anything puts in your AI agent's context, keep agents working while big binaries decompile, and see which optimizations are still open proposals.
Latest
New essays and field notes
Root-routed permalinks, long-form writing, and practical guides tuned for readers who want the details without the clutter.
Build an MVP with Spec-Driven Development and OpenSpec
A hands-on course on Spec-Driven Development with AI coding agents. Learn the theory, set up OpenSpec, and build a tested MVP in three small changes.
How to Query 100 Million Rows in Under a Second with ClickHouse
Learn what ClickHouse is, why it is fast, when to use it, and how to load 100 million rows and answer a dashboard question in about a third of a second.
EssayOct 14, 202610 min
How to Reverse Engineer Any App Feature with REA and Your AI Agent
Connect REA to your AI coding agent, trace a real app feature from a button to the code that runs it, and check every claim against evidence you can verify yourself.
Start Building an AI Harness Effectively
Learn how to effectively build an AI harness to maximize the value of AI models and create reusable systems.
Models Are Becoming Commodities, Orchestration Is the New Advantage
AI models are rapidly commoditizing. The real advantage now is AI orchestration: memory, verification, safety guardrails, and workflow design. Learn a practical framework to build reliable AI systems.
Are ORMs Still Relevant in the AI Copilot Era?
With AI copilots generating code faster than ever, do we still need ORMs? Explore the tradeoffs between productivity and semantic clarity, and how to use both effectively in 2026.
How to Design Truth-Probe Troubleshooting Endpoints for AI-Generated Backends
When AI helps generate backend code, implementation speed goes up.
Tokenmaxxing: Why AI Token Consumption Is a Vanity Metric
Learn why optimizing for AI token consumption is a vanity metric, how friction drives token waste, and how teams can improve token efficiency with MCP, managed agents, and lower-friction AI infrastructure.